
import pandas as pd
import numpy as np
import statsmodels.api as sm
import statsmodels.formula.api as smf
import scipy.stats as stats
from statsmodels.stats.multitest import multipletests


import matplotlib.pyplot as plt
import seaborn as sns

from skimage import filters, morphology, measure, color
import aicsimageio as aics

import glob

plt.rcParams['pdf.fonttype'] = 'truetype'
plt.rcParams['font.size'] = 20
plt.style.use('seaborn-v0_8-ticks')


color_palette = {'DMSO' : '#4d4d4d',
                 'ARYL_AG':'#F8766D', 'ARYL_INH':'#F8766D50',
                 'ANDR_AG':'#fccb17', 'ANDR_INH':'#C49A0050',  
                 "ESTR_AG": '#53B400', "ESTR_INH": '#53B40050', 
                 'GC_AG' : '#00C094', 'GC_INH' : '#00C09450',
                 'LX_AG' : '#00B6EB', 'LX_INH' : '#00B6EB50', 
                 'RET_AG' : '#A58AFF', 'RET_INH' : '#A58AFF50', 
                 'THYR_AG' : '#FB61D7', 'THYR_INH' : '#FB61D750'
}

line_palette = {
    'CTL08A': "#99cfd670",  
    'CTL04E': "#f8c88a70",  
}


color_palette_expanded = {'DMSO_CTL08A': '#cacaca',
 'DMSO_CTL04E': '#4d4d4d',
 'ARYL_AG_CTL08A': '#fdd6d3',
 'ARYL_AG_CTL04E': '#F8766D',
 'ARYL_INH_CTL08A': '#fdd6d3',
 'ARYL_INH_CTL04E': '#F8766D50',
 'ANDR_AG_CTL08A': '#feefb9',
 'ANDR_AG_CTL04E': '#fccb17',
 'ANDR_INH_CTL08A': '#ede1b250',
 'ANDR_INH_CTL04E': '#C49A0050',
 'ESTR_AG_CTL08A': '#cbe8b2',
 'ESTR_AG_CTL04E': '#53B400',
 'ESTR_INH_CTL08A': '#cbe8b250',
 'ESTR_INH_CTL04E': '#53B40050',
 'GC_AG_CTL08A': '#b2ecdf',
 'GC_AG_CTL04E': '#00C094',
 'GC_INH_CTL08A': '#b2ecdf50',
 'GC_INH_CTL04E': '#00C09450',
 'LX_AG_CTL08A': '#b2e9f9',
 'LX_AG_CTL04E': '#00B6EB',
 'LX_INH_CTL08A': '#b2e9f950',
 'LX_INH_CTL04E': '#00B6EB50',
 'RET_AG_CTL08A': '#e4dcff',
 'RET_AG_CTL04E': '#A58AFF',
 'RET_INH_CTL08A': '#e4dcff50',
 'RET_INH_CTL04E': '#A58AFF50',
 'THYR_AG_CTL08A': '#fed0f3',
 'THYR_AG_CTL04E': '#FB61D7',
 'THYR_INH_CTL08A': '#fed0f350',
 'THYR_INH_CTL04E': '#FB61D750'}


hormonal_conditions = ['ESTR_AG', 'ESTR_INH', 'ANDR_AG', 'ANDR_INH', 'ARYL_INH',
       'ARYL_AG', 'LX_AG', 'GC_AG', 'LX_INH', 'GC_INH', 'THYR_INH',
       'THYR_AG', 'DMSO', 'RET_AG',
       'RET_INH']
hormonal_conditions.remove('DMSO')
hormonal_conditions.sort()
hormonal_conditions = ['DMSO'] + hormonal_conditions


blank_mix1 = glob.glob('/group/testa/Project/EndPoints/TPSSU/analysis/single_tif_scanregion/*0136*.tif')
blank_mix1 = [f.split('/')[-1].split('.')[0] for f in blank_mix1]
blank_mix2 = glob.glob('/group/testa/Project/EndPoints/TPSSU/analysis/single_tif_scanregion/*0145*.tif')
blank_mix2 = [f.split('/')[-1].split('.')[0] for f in blank_mix2]


check_qc_ch1 = pd.read_csv('../../preprocessing/tables/Treshold_QC_check - Channel1_no_dup.csv')
check_qc_ch2 = pd.read_csv('../../preprocessing/tables/Treshold_QC_check - Channel2_no_dup.csv')


check_qc_ch1['general QC (keep or not)'] = check_qc_ch1['general QC (keep or not)'].str.upper()
check_qc_ch1['general QC (keep or not)'] = check_qc_ch1['general QC (keep or not)'].replace({'BETTER NOT': 'LIMIT', 'MAYBE': 'LIMIT', 'YES?': 'LIMIT', 'SUS': 'LIMIT', 'NOT SURE': 'LIMIT', 'YES ': 'YES', 'YES - 2 CBO': 'YES'})
check_qc_ch1['general QC (keep or not)'].value_counts().index

Index(['YES', 'LIMIT', 'NO'], dtype='object', name='general QC (keep or not)')


check_qc_ch1['Reference Image Report'] = check_qc_ch1['Reference Image Report'].str.replace('.pdf', '')


check_qc_ch1['Reference Image Report'].value_counts()

Reference Image Report
20240424_manuel_lessi_0148_ScanRegion1_rep_1_channel_1    1
20240424_manuel_lessi_0145_ScanRegion2_rep_2_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_0_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_1_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_2_channel_1    1
                                                         ..
20240424_manuel_lessi_0136_ScanRegion2_rep_1_channel_1    1
20240424_manuel_lessi_0136_ScanRegion2_rep_2_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_0_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_1_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_2_channel_1    1
Name: count, Length: 153, dtype: int64


check_qc_ch2['general QC (keep or not)'] = check_qc_ch2['general QC (keep or not)'].str.upper()
check_qc_ch2['general QC (keep or not)'] = check_qc_ch2['general QC (keep or not)'].replace({'NOT SURE': 'LIMIT', '?': 'LIMIT', 'YES ': 'YES'})
check_qc_ch2['general QC (keep or not)'].value_counts().index

Index(['YES', 'NO', 'LIMIT'], dtype='object', name='general QC (keep or not)')


check_qc_ch2['Reference Image Report'] = check_qc_ch2['Reference Image Report'].str.replace('.pdf', '')


check_qc_ch1['Reference Image Report'].value_counts()

Reference Image Report
20240424_manuel_lessi_0148_ScanRegion1_rep_1_channel_1    1
20240424_manuel_lessi_0145_ScanRegion2_rep_2_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_0_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_1_channel_1    1
20240424_manuel_lessi_0145_ScanRegion3_rep_2_channel_1    1
                                                         ..
20240424_manuel_lessi_0136_ScanRegion2_rep_1_channel_1    1
20240424_manuel_lessi_0136_ScanRegion2_rep_2_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_0_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_1_channel_1    1
20240424_manuel_lessi_0136_ScanRegion3_rep_2_channel_1    1
Name: count, Length: 153, dtype: int64


check_qc_ch1['ImageName_ScanRegion_Rep'] = check_qc_ch1['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[:7]))
check_qc_ch2['ImageName_ScanRegion_Rep'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[:7]))

to_keep_ch1 = check_qc_ch1[check_qc_ch1['general QC (keep or not)'].isin(['YES', 'LIMIT'])]
to_keep_ch2 = check_qc_ch2[check_qc_ch2['general QC (keep or not)'].isin(['YES', 'LIMIT'])]

len(set(to_keep_ch1['ImageName_ScanRegion_Rep']).intersection(set(to_keep_ch2['ImageName_ScanRegion_Rep'])))

100


len(check_qc_ch1['ImageName_ScanRegion_Rep'])

153


len(check_qc_ch2['ImageName_ScanRegion_Rep'])

275


good_tissue_to_keep_limit = list(set(check_qc_ch1[check_qc_ch1['general QC (keep or not)'].isin(['YES', 'LIMIT'])]['ImageName_ScanRegion_Rep']).union(set(check_qc_ch2[check_qc_ch2['general QC (keep or not)'].isin(['YES', 'LIMIT'])]['ImageName_ScanRegion_Rep'])))


len(good_tissue_to_keep_limit)

245


good_tissue_to_keep_limit_df = pd.DataFrame(good_tissue_to_keep_limit, columns=['ImageName_ScanRegion_Rep'])


good_tissue_to_keep_limit_df['ImageName_ScanRegion'] = good_tissue_to_keep_limit_df['ImageName_ScanRegion_Rep'].apply(lambda x: '_'.join(x.split('_')[:5]))
good_tissue_to_keep_limit_df


sample_sheet  = pd.read_csv('../../preprocessing/tables/ImageAnalysisSampleSheet.csv')


sample_sheet = sample_sheet[sample_sheet['Condition'].isin(hormonal_conditions)]


sample_sheet['Condition'] = sample_sheet['Condition'].str.replace('_ANT', '_INH')


sample_sheet['Condition'].unique()

array(['ESTR_AG', 'ESTR_INH', 'ANDR_AG', 'ARYL_INH', 'ARYL_AG', 'LX_AG',
       'GC_AG', 'LX_INH', 'GC_INH', 'THYR_INH', 'THYR_AG', 'DMSO',
       'RET_AG', 'RET_INH', 'ANDR_INH'], dtype=object)


sample_sheet['ImageName'] = sample_sheet['Path'].apply(lambda x: x.split('\\')[-1].split('.')[0])
sample_sheet['ImageName_ScanRegion'] = sample_sheet['ImageName'] + '_' + sample_sheet['Scan Area']
sample_sheet['Condition_Line'] = sample_sheet['Condition'] + '_' + sample_sheet['Line ']
sample_sheet


sample_dict= {i:j for i, j in zip(sample_sheet['ImageName_ScanRegion'], sample_sheet['Condition_Line'])}


mix_1_names = sample_sheet[sample_sheet['MIX'] == 1]['ImageName'].tolist()
mix_2_names = sample_sheet[sample_sheet['MIX'] == 2]['ImageName'].tolist()


sample_sheet['Condition'].unique()

array(['ESTR_AG', 'ESTR_INH', 'ANDR_AG', 'ARYL_INH', 'ARYL_AG', 'LX_AG',
       'GC_AG', 'LX_INH', 'GC_INH', 'THYR_INH', 'THYR_AG', 'DMSO',
       'RET_AG', 'RET_INH', 'ANDR_INH'], dtype=object)


measurements_files = glob.glob("/group/testa/Project/EndPoints/TPSSU/analysis/measurements/*.csv")
measurements_files_mix_1 = [f for f in measurements_files if any(name in f for name in mix_1_names)]
measurements_files_mix_2 = [f for f in measurements_files if any(name in f for name in mix_2_names)]


mask_file = pd.read_csv("/group/testa/Project/EndPoints/TPSSU/analysis/cytoplasmatic_measures/cyto_mask_measures.csv", index_col=0)
mask_file


mask_file['OriginalImageName'] = mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:4]))
mask_file['ImageName_ScanRegion'] = mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:5]))
mask_file['ImageName_ScanRegion_Rep'] = mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:7]))
mask_file


mask_file_df_mix_1 = mask_file[mask_file.OriginalImageName.isin(mix_1_names)]
mask_file_df_mix_1


mask_file_df_mix_2 = mask_file[mask_file.OriginalImageName.isin(mix_2_names)]
mask_file_df_mix_2


SOX2_KI67_mask_file = pd.read_csv("/group/testa/Project/EndPoints/TPSSU/analysis/SOX2_signal_mask_measures/SOX2_mask_measures.csv", index_col=0)
SOX2_KI67_mask_file


SOX2_KI67_mask_file['OriginalImageName'] = SOX2_KI67_mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:4]))
SOX2_KI67_mask_file['ImageName_ScanRegion'] = SOX2_KI67_mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:5]))
SOX2_KI67_mask_file['ImageName_ScanRegion_Rep'] = SOX2_KI67_mask_file['level_1'].apply(lambda x: '_'.join(x.split('_')[0:7]))
SOX2_KI67_mask_file


SOX2_KI67_mask_file_df_mix_1 = SOX2_KI67_mask_file[SOX2_KI67_mask_file.OriginalImageName.isin(mix_1_names)]
SOX2_KI67_mask_file_df_mix_1


SOX2_KI67_mask_file_df_mix_2 = SOX2_KI67_mask_file[SOX2_KI67_mask_file.OriginalImageName.isin(mix_2_names)]
SOX2_KI67_mask_file_df_mix_2


organoid_areas = pd.read_csv('/group/testa/Project/EndPoints/TPSSU/analysis/organoids_area.csv', index_col=0)
organoid_areas


organoid_areas['ImageName_ScanRegion'] = organoid_areas.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:5])).values
organoid_areas['Condition_Line'] = organoid_areas['ImageName_ScanRegion'].map(sample_dict)
organoid_areas['Line'] = organoid_areas['Condition_Line'].apply(lambda x: x.split('_')[-1] if pd.notnull(x) else x)
organoid_areas['Condition'] = organoid_areas['Condition_Line'].str.replace('_CTL08A', '', regex=True)
organoid_areas['Condition'] = organoid_areas['Condition'].str.replace('_CTL04E', '', regex=True)
organoid_areas = organoid_areas[organoid_areas['Condition'].isin(hormonal_conditions)]
organoid_areas


sample_sheet[~sample_sheet['ImageName_ScanRegion'].isin(organoid_areas['ImageName_ScanRegion'].tolist())]


img = aics.AICSImage('/group/testa/Project/EndPoints/TPSSU/Pictures/20240424_manuel_lessi_0134.czi')
px_size = img.physical_pixel_sizes.X
px_size

0.325


organoid_areas['Area_um2'] = organoid_areas['area'] * (px_size ** 2)

/tmp/ipykernel_359582/3605050963.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas['Area_um2'] = organoid_areas['area'] * (px_size ** 2)


to_plot = organoid_areas.loc[[i for i in good_tissue_to_keep_limit if i in organoid_areas.index]]
to_plot = to_plot[['Condition', 'Line']].value_counts().reset_index()
plt.figure(figsize = (5, 7))
sns.barplot(to_plot, x='count', y='Condition', hue='Line', order = hormonal_conditions, palette=line_palette)
plt.title('Number of organoids per condition')
plt.legend(title='Line', bbox_to_anchor=(1.05, 1), loc='upper left')

plt.savefig('../../../../endpoints_figures/organoid_count_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/organoid_count_per_condition.png', dpi=300, bbox_inches='tight')


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
organoid_areas = organoid_areas[organoid_areas['Condition'].isin(hormonal_conditions)]
for i, cond in enumerate(hormonal_conditions):
    data = organoid_areas[(organoid_areas['Line'] == 'CTL08A') & 
                                 (organoid_areas['Condition'] == cond)]['Area_um2']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = organoid_areas[(organoid_areas['Condition'] == 'DMSO') & 
                                       (organoid_areas['Line'] == 'CTL08A')]['Area_um2'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=organoid_areas[(organoid_areas['Line'] == 'CTL08A')],
    y='Area_um2', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = organoid_areas[(organoid_areas['Line'] == 'CTL04E') & 
                                 (organoid_areas['Condition'] == cond)]['Area_um2']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = organoid_areas[(organoid_areas['Condition'] == 'DMSO') & 
                                       (organoid_areas['Line'] == 'CTL04E')]['Area_um2'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=organoid_areas[organoid_areas['Line'] == 'CTL04E'],
    y='Area_um2', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('Area (um²)')
ax[1].set_ylabel('Area (um²)')

plt.savefig('../../../../endpoints_figures/endpoints_organoids_area_grouped.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_area_grouped.png', dpi=300, bbox_inches='tight')


organoid_areas_CTL08A = organoid_areas[organoid_areas['Line'] == 'CTL08A']
organoid_areas_CTL08A['Condition'] = organoid_areas_CTL08A['Condition'].astype('category')
organoid_areas_CTL08A["log_area"] = np.log(organoid_areas_CTL08A["Area_um2"])
organoid_areas_CTL08A['log_area'].hist(bins = 10)

model_CTL08A = smf.ols("log_area ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL08A,
                ).fit()

print(model_CTL08A.summary())

/tmp/ipykernel_359582/2873068395.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL08A['Condition'] = organoid_areas_CTL08A['Condition'].astype('category')
/tmp/ipykernel_359582/2873068395.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL08A["log_area"] = np.log(organoid_areas_CTL08A["Area_um2"])

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               log_area   R-squared:                       0.418
Model:                            OLS   Adj. R-squared:                  0.296
Method:                 Least Squares   F-statistic:                     3.431
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           0.000333
Time:                        11:17:32   Log-Likelihood:                -73.462
No. Observations:                  82   AIC:                             176.9
Df Residuals:                      67   BIC:                             213.0
Df Model:                          14                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                15.4856      0.268     57.849      0.000      14.951      16.020
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]     -0.2767      0.379     -0.731      0.467      -1.032       0.479
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]    -1.7082      0.464     -3.684      0.000      -2.634      -0.783
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -0.7963      0.346     -2.304      0.024      -1.486      -0.107
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -1.1674      0.379     -3.084      0.003      -1.923      -0.412
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -1.4736      0.423     -3.482      0.001      -2.318      -0.629
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]    -0.5383      0.423     -1.272      0.208      -1.383       0.306
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]       -0.6476      0.423     -1.530      0.131      -1.492       0.197
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.5371      0.379     -1.419      0.161      -1.293       0.219
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -1.1601      0.379     -3.065      0.003      -1.916      -0.405
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.8513      0.423     -2.011      0.048      -1.696      -0.006
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]      -1.6444      0.379     -4.344      0.000      -2.400      -0.889
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.4029      0.379     -1.064      0.291      -1.158       0.353
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -1.1685      0.379     -3.087      0.003      -1.924      -0.413
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -0.1595      0.379     -0.421      0.675      -0.915       0.596
==============================================================================
Omnibus:                       13.242   Durbin-Watson:                   1.918
Prob(Omnibus):                  0.001   Jarque-Bera (JB):               20.705
Skew:                          -0.637   Prob(JB):                     3.19e-05
Kurtosis:                       5.107   Cond. No.                         15.3
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.


organoid_areas_CTL04E = organoid_areas[organoid_areas['Line'] == 'CTL04E']
organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
organoid_areas_CTL04E["log_area"] = np.log(organoid_areas_CTL04E["Area_um2"])
organoid_areas_CTL04E['log_area'].hist(bins = 10)

model_CTL04E = smf.ols("log_area ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL04E,
                ).fit()

print(model_CTL04E.summary())

/tmp/ipykernel_359582/1765289553.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
/tmp/ipykernel_359582/1765289553.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E["log_area"] = np.log(organoid_areas_CTL04E["Area_um2"])

                            OLS Regression Results                            
==============================================================================
Dep. Variable:               log_area   R-squared:                       0.528
Model:                            OLS   Adj. R-squared:                  0.416
Method:                 Least Squares   F-statistic:                     4.746
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           3.77e-05
Time:                        11:17:32   Log-Likelihood:                -41.911
No. Observations:                  64   AIC:                             109.8
Df Residuals:                      51   BIC:                             137.9
Df Model:                          12                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                14.7172      0.261     56.414      0.000      14.193      15.241
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.0188      0.369      0.051      0.959      -0.722       0.760
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]     0.2327      0.398      0.584      0.562      -0.567       1.033
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      1.0591      0.337      3.145      0.003       0.383       1.735
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.0609      0.337     -0.181      0.857      -0.737       0.615
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.5125      0.398      1.286      0.204      -0.287       1.313
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.5022      0.337      1.491      0.142      -0.174       1.178
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.5818      0.337      1.728      0.090      -0.094       1.258
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -0.3924      0.337     -1.165      0.249      -1.069       0.284
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.7487      0.337      2.223      0.031       0.073       1.425
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.6445      0.337      1.914      0.061      -0.032       1.321
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.4704      0.337      1.397      0.169      -0.206       1.147
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -1.2498      0.452     -2.766      0.008      -2.157      -0.343
==============================================================================
Omnibus:                        7.906   Durbin-Watson:                   1.913
Prob(Omnibus):                  0.019   Jarque-Bera (JB):                7.916
Skew:                          -0.605   Prob(JB):                       0.0191
Kurtosis:                       4.226   Cond. No.                         15.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100
intercepts


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_area_OLS_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_359582/1523563738.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


n_nuclei_mix1 = pd.read_csv('../tables/n_nuclei_mix1.csv')
n_nuclei_mix2 = pd.read_csv('../tables/n_nuclei_mix2.csv')
n_nuclei = pd.concat([n_nuclei_mix1, n_nuclei_mix2])


n_nuclei.ImageName = n_nuclei.ImageName.str.replace('_channel_1', '')


n_nuclei.set_index('ImageName', inplace = True)


organoid_areas['n_nuclei'] = n_nuclei['count']


organoid_areas['density'] = organoid_areas['n_nuclei'] / organoid_areas['Area_um2']


import matplotlib.pyplot as plt
import numpy as np
from matplotlib.patches import Rectangle

fig, axs = plt.subplots(1, 2, figsize=(15, 7))
bar_width = 0.6

for ax, line in zip(axs, ['CTL08A', 'CTL04E']):
    df = organoid_areas[organoid_areas['Line'] == line]
    means = df.groupby('Condition')['n_nuclei'].mean().reindex(hormonal_conditions)
    sems = df.groupby('Condition')['n_nuclei'].sem().reindex(hormonal_conditions)

    x = np.arange(len(hormonal_conditions))

    for i, cond in enumerate(hormonal_conditions):
        mean = means[cond]
        sem = sems[cond]

        # Add bar as a Rectangle
        bar = Rectangle(
            (i - bar_width / 2, 0),  # bottom-left x, y
            bar_width,
            mean,
            color=color_palette[cond],
            zorder=1
        )
        ax.add_patch(bar)

        # Add error bar
        ax.errorbar(
            i, mean, yerr=sem,
            fmt='none',
            ecolor='black',
            capsize=5,
            zorder=2
        )

        # Add strip dots
        y_vals = df[df['Condition'] == cond]['n_nuclei']
        jittered_x = i + np.random.uniform(-bar_width/3, bar_width/3, size=len(y_vals))
        ax.scatter(jittered_x, y_vals, color='black', alpha=0.3, s=10, linewidth=0.5, zorder=3)

    # Format
    ax.set_title(line)
    ax.set_xticks(x)
    ax.set_xticklabels(hormonal_conditions, rotation=90)
    ax.set_xlim(-0.5, len(hormonal_conditions) - 0.5)
    ax.set_ylabel("Total number of nuclei")

plt.tight_layout(rect=[0, 0.03, 1, 0.95])

plt.savefig('../../../../endpoints_figures/number_of_nuclei_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/number_of_nuclei_per_condition.png', dpi=300, bbox_inches='tight')
plt.show()


sns.scatterplot(x = organoid_areas['Area_um2'], y = organoid_areas['n_nuclei'], s=50, hue = organoid_areas['Condition'], palette=color_palette)
plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')

plt.savefig('../../../../endpoints_figures/scatterplot_area_n_nuclei.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/scatterplot_area_n_nuclei.png', dpi=300, bbox_inches='tight')


sns.scatterplot(x = np.log10(organoid_areas['Area_um2']), y = np.log10(organoid_areas['n_nuclei']), s=50, hue = organoid_areas['Condition'], palette=color_palette)
plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')


plt.savefig('../../../../endpoints_figures/scatterplot_area_n_nuclei.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/scatterplot_area_n_nuclei.png', dpi=300, bbox_inches='tight')


sns.scatterplot(x = np.log10(organoid_areas['Area_um2']), y = np.log10(organoid_areas['n_nuclei']), s=50, hue = organoid_areas['Line'], palette=line_palette)
plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')

<matplotlib.legend.Legend at 0x15551b74ef50>


organoid_areas_CTL08A = organoid_areas[organoid_areas['Line'] == 'CTL08A']
organoid_areas_CTL08A['n_nuclei'].hist(bins = 10)

<Axes: >


organoid_areas_CTL08A["log_n_nuclei"] = np.log(organoid_areas_CTL08A["n_nuclei"])
organoid_areas_CTL08A['log_n_nuclei'].hist(bins = 10)

/tmp/ipykernel_359582/1482013400.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL08A["log_n_nuclei"] = np.log(organoid_areas_CTL08A["n_nuclei"])

<Axes: >


model_CTL08A = smf.ols("log_n_nuclei  ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL08A,
                ).fit()

print(model_CTL08A.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:           log_n_nuclei   R-squared:                       0.522
Model:                            OLS   Adj. R-squared:                  0.422
Method:                 Least Squares   F-statistic:                     5.232
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           1.52e-06
Time:                        11:17:42   Log-Likelihood:                -90.432
No. Observations:                  82   AIC:                             210.9
Df Residuals:                      67   BIC:                             247.0
Df Model:                          14                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                10.9638      0.329     33.301      0.000      10.307      11.621
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]     -0.4239      0.466     -0.910      0.366      -1.353       0.506
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]    -2.4438      0.570     -4.285      0.000      -3.582      -1.306
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -1.0388      0.425     -2.444      0.017      -1.887      -0.190
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -1.5445      0.466     -3.317      0.001      -2.474      -0.615
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -1.8597      0.521     -3.572      0.001      -2.899      -0.821
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]    -0.7584      0.521     -1.457      0.150      -1.797       0.281
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]       -0.7253      0.521     -1.393      0.168      -1.764       0.314
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.6386      0.466     -1.371      0.175      -1.568       0.291
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -1.4937      0.466     -3.208      0.002      -2.423      -0.564
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.7846      0.521     -1.507      0.136      -1.824       0.254
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]      -2.7544      0.466     -5.916      0.000      -3.684      -1.825
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.4159      0.466     -0.893      0.375      -1.345       0.513
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -1.1299      0.466     -2.427      0.018      -2.059      -0.201
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -0.0765      0.466     -0.164      0.870      -1.006       0.853
==============================================================================
Omnibus:                        6.800   Durbin-Watson:                   1.928
Prob(Omnibus):                  0.033   Jarque-Bera (JB):                8.262
Skew:                          -0.367   Prob(JB):                       0.0161
Kurtosis:                       4.371   Cond. No.                         15.3
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.


organoid_areas_CTL04E = organoid_areas[organoid_areas['Line'] == 'CTL04E']
organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
organoid_areas_CTL04E["log_n_nuclei"] = np.log(organoid_areas_CTL04E["n_nuclei"])
organoid_areas_CTL04E['log_n_nuclei'].hist(bins = 10)

model_CTL04E = smf.ols("log_n_nuclei ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL04E,
                ).fit()

print(model_CTL04E.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:           log_n_nuclei   R-squared:                       0.490
Model:                            OLS   Adj. R-squared:                  0.370
Method:                 Least Squares   F-statistic:                     4.083
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           0.000189
Time:                        11:17:42   Log-Likelihood:                -62.617
No. Observations:                  64   AIC:                             151.2
Df Residuals:                      51   BIC:                             179.3
Df Model:                          12                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                10.2373      0.361     28.395      0.000       9.513      10.961
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]     -0.3964      0.510     -0.777      0.441      -1.420       0.627
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]    -0.1566      0.551     -0.284      0.777      -1.262       0.949
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.8781      0.465      1.887      0.065      -0.056       1.812
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.1838      0.465     -0.395      0.695      -1.118       0.751
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.1943      0.551      0.353      0.726      -0.911       1.300
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.2342      0.465      0.503      0.617      -0.700       1.169
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.6839      0.465      1.469      0.148      -0.250       1.618
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -1.1444      0.465     -2.459      0.017      -2.079      -0.210
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.6637      0.465      1.426      0.160      -0.271       1.598
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.4658      0.465      1.001      0.322      -0.469       1.400
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.3717      0.465      0.799      0.428      -0.563       1.306
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -1.5616      0.624     -2.501      0.016      -2.815      -0.308
==============================================================================
Omnibus:                       17.531   Durbin-Watson:                   1.783
Prob(Omnibus):                  0.000   Jarque-Bera (JB):               33.590
Skew:                          -0.863   Prob(JB):                     5.08e-08
Kurtosis:                       6.101   Cond. No.                         15.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_359582/3888406708.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
/tmp/ipykernel_359582/3888406708.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E["log_n_nuclei"] = np.log(organoid_areas_CTL04E["n_nuclei"])


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_n_nuclei_OLS_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_359582/1529930461.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
organoid_areas = organoid_areas[organoid_areas['Condition'].isin(hormonal_conditions)]
for i, cond in enumerate(hormonal_conditions):
    data = organoid_areas[(organoid_areas['Line'] == 'CTL08A') & 
                                 (organoid_areas['Condition'] == cond)]['density']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = organoid_areas[(organoid_areas['Condition'] == 'DMSO') & 
                                       (organoid_areas['Line'] == 'CTL08A')]['density'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=organoid_areas[(organoid_areas['Line'] == 'CTL08A')],
    y='density', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = organoid_areas[(organoid_areas['Line'] == 'CTL04E') & 
                                 (organoid_areas['Condition'] == cond)]['density']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = organoid_areas[(organoid_areas['Condition'] == 'DMSO') & 
                                       (organoid_areas['Line'] == 'CTL04E')]['density'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=organoid_areas[organoid_areas['Line'] == 'CTL04E'],
    y='density', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('Density (nuclei/um²)')
ax[1].set_ylabel('Density (nuclei/um²)')

plt.savefig('../../../../endpoints_figures/endpoints_organoids_density_grouped.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_density_grouped.png', dpi=300, bbox_inches='tight')


density_dict = {i:j for i, j in zip(organoid_areas.index, organoid_areas['density'])}
area_dict = {i:j for i, j in zip(organoid_areas.index, organoid_areas['Area_um2'])}


organoid_areas_CTL08A = organoid_areas[organoid_areas['Line'] == 'CTL08A']
organoid_areas_CTL08A['density'].hist(bins = 10)

<Axes: >


organoid_areas_CTL08A["log_density"] = np.log(organoid_areas_CTL08A["density"])
organoid_areas_CTL08A['log_density'].hist(bins = 10)

/tmp/ipykernel_359582/3272618323.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL08A["log_density"] = np.log(organoid_areas_CTL08A["density"])

<Axes: >


model_CTL08A = smf.ols("log_density ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL08A,
                ).fit()

print(model_CTL08A.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:            log_density   R-squared:                       0.684
Model:                            OLS   Adj. R-squared:                  0.618
Method:                 Least Squares   F-statistic:                     10.37
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           6.74e-12
Time:                        11:18:52   Log-Likelihood:                 11.210
No. Observations:                  82   AIC:                             7.580
Df Residuals:                      67   BIC:                             43.68
Df Model:                          14                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -4.5218      0.095    -47.438      0.000      -4.712      -4.332
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]     -0.1472      0.135     -1.092      0.279      -0.416       0.122
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]    -0.7356      0.165     -4.455      0.000      -1.065      -0.406
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -0.2425      0.123     -1.971      0.053      -0.488       0.003
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.3771      0.135     -2.798      0.007      -0.646      -0.108
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -0.3862      0.151     -2.562      0.013      -0.687      -0.085
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]    -0.2201      0.151     -1.460      0.149      -0.521       0.081
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]       -0.0776      0.151     -0.515      0.608      -0.378       0.223
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.1014      0.135     -0.753      0.454      -0.371       0.168
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -0.3335      0.135     -2.474      0.016      -0.603      -0.064
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.0667      0.151      0.443      0.660      -0.234       0.368
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]      -1.1100      0.135     -8.234      0.000      -1.379      -0.841
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.0131      0.135     -0.097      0.923      -0.282       0.256
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.0386      0.135      0.286      0.775      -0.230       0.308
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.0829      0.135      0.615      0.540      -0.186       0.352
==============================================================================
Omnibus:                        2.586   Durbin-Watson:                   1.869
Prob(Omnibus):                  0.274   Jarque-Bera (JB):                1.962
Skew:                           0.215   Prob(JB):                        0.375
Kurtosis:                       3.624   Cond. No.                         15.3
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.


organoid_areas_CTL04E = organoid_areas[organoid_areas['Line'] == 'CTL04E']
organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
organoid_areas_CTL04E["log_density"] = np.log(organoid_areas_CTL04E["density"])
organoid_areas_CTL04E['log_density'].hist(bins = 10)

model_CTL04E = smf.ols("log_density ~ C(Condition, Treatment(reference='DMSO'))",
                data=organoid_areas_CTL04E,
                ).fit()

print(model_CTL04E.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:            log_density   R-squared:                       0.452
Model:                            OLS   Adj. R-squared:                  0.323
Method:                 Least Squares   F-statistic:                     3.505
Date:                Thu, 05 Mar 2026   Prob (F-statistic):           0.000817
Time:                        11:18:52   Log-Likelihood:               0.057152
No. Observations:                  64   AIC:                             25.89
Df Residuals:                      51   BIC:                             53.95
Df Model:                          12                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -4.4799      0.135    -33.084      0.000      -4.752      -4.208
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]     -0.4152      0.191     -2.168      0.035      -0.800      -0.031
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]    -0.3893      0.207     -1.882      0.066      -0.805       0.026
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -0.1811      0.175     -1.036      0.305      -0.532       0.170
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.1229      0.175     -0.703      0.485      -0.474       0.228
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -0.3182      0.207     -1.538      0.130      -0.733       0.097
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]    -0.2680      0.175     -1.533      0.132      -0.619       0.083
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.1021      0.175      0.584      0.562      -0.249       0.453
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -0.7520      0.175     -4.302      0.000      -1.103      -0.401
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.0850      0.175     -0.486      0.629      -0.436       0.266
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.1787      0.175     -1.022      0.312      -0.530       0.172
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -0.0987      0.175     -0.565      0.575      -0.450       0.252
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -0.3118      0.235     -1.329      0.190      -0.783       0.159
==============================================================================
Omnibus:                       33.100   Durbin-Watson:                   1.679
Prob(Omnibus):                  0.000   Jarque-Bera (JB):              171.463
Skew:                          -1.206   Prob(JB):                     5.85e-38
Kurtosis:                      10.647   Cond. No.                         15.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_359582/4082485772.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E['Condition'] = organoid_areas_CTL04E['Condition'].astype('category')
/tmp/ipykernel_359582/4082485772.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  organoid_areas_CTL04E["log_density"] = np.log(organoid_areas_CTL04E["density"])


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100
intercepts


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax, fmt='')
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_density_OLS_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_359582/2873717824.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


tot_df_mix1_ch2 = pd.DataFrame()
measurements_files_mix_1_ch2 = [f for f in measurements_files_mix_1 if 'channel_2' in f]

for file in measurements_files_mix_1_ch2:
    print(file)
    df = pd.read_csv(file, index_col=0)
    df['ImageName'] = file.split("/")[-1].split(".")[0]
    print(df.shape)
    tot_df_mix1_ch2 = pd.concat([tot_df_mix1_ch2, df], axis=0)

/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion3_rep_1_channel_2_measures.csv
(14032, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion2_rep_0_channel_2_measures.csv
(36257, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion3_rep_1_channel_2_measures.csv
(29165, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion2_rep_0_channel_2_measures.csv
(28234, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion1_rep_2_channel_2_measures.csv
(5186, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion2_rep_1_channel_2_measures.csv
(30598, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion0_rep_0_channel_2_measures.csv
(4420, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion4_rep_0_channel_2_measures.csv
(5637, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion5_rep_2_channel_2_measures.csv
(44878, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion2_rep_1_channel_2_measures.csv
(25453, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion5_rep_0_channel_2_measures.csv
(14547, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion2_rep_0_channel_2_measures.csv
(65200, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion4_rep_1_channel_2_measures.csv
(18423, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion0_rep_2_channel_2_measures.csv
(12038, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion0_rep_1_channel_2_measures.csv
(52451, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion0_rep_0_channel_2_measures.csv
(69681, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion3_rep_0_channel_2_measures.csv
(60277, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion7_rep_0_channel_2_measures.csv
(36423, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion2_rep_1_channel_2_measures.csv
(54724, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion3_rep_2_channel_2_measures.csv
(48396, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion1_rep_0_channel_2_measures.csv
(18479, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion5_rep_0_channel_2_measures.csv
(61473, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion3_rep_2_channel_2_measures.csv
(62393, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion5_rep_2_channel_2_measures.csv
(27998, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion4_rep_0_channel_2_measures.csv
(16418, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion0_rep_0_channel_2_measures.csv
(54097, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion0_rep_1_channel_2_measures.csv
(19128, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion2_rep_2_channel_2_measures.csv
(7446, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion0_rep_0_channel_2_measures.csv
(6943, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion3_rep_2_channel_2_measures.csv
(44660, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion2_rep_0_channel_2_measures.csv
(6134, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion2_rep_0_channel_2_measures.csv
(43655, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion5_rep_0_channel_2_measures.csv
(55824, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion4_rep_0_channel_2_measures.csv
(43161, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion4_rep_2_channel_2_measures.csv
(26186, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion5_rep_2_channel_2_measures.csv
(42766, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion1_rep_0_channel_2_measures.csv
(32479, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion0_rep_2_channel_2_measures.csv
(46684, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion1_rep_1_channel_2_measures.csv
(7889, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion7_rep_1_channel_2_measures.csv
(1, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion3_rep_1_channel_2_measures.csv
(4878, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion5_rep_1_channel_2_measures.csv
(24682, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion3_rep_1_channel_2_measures.csv
(31993, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion3_rep_2_channel_2_measures.csv
(48939, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion4_rep_2_channel_2_measures.csv
(1405, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion0_rep_2_channel_2_measures.csv
(50003, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion4_rep_1_channel_2_measures.csv
(26358, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion1_rep_1_channel_2_measures.csv
(4685, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion0_rep_1_channel_2_measures.csv
(42864, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion4_rep_1_channel_2_measures.csv
(12551, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion1_rep_0_channel_2_measures.csv
(128250, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion2_rep_2_channel_2_measures.csv
(68825, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion0_rep_1_channel_2_measures.csv
(10615, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion2_rep_2_channel_2_measures.csv
(54944, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion2_rep_1_channel_2_measures.csv
(32605, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion2_rep_0_channel_2_measures.csv
(23699, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion3_rep_1_channel_2_measures.csv
(20919, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion4_rep_2_channel_2_measures.csv
(33055, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion3_rep_0_channel_2_measures.csv
(70503, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion1_rep_0_channel_2_measures.csv
(12349, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion1_rep_1_channel_2_measures.csv
(30782, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion6_rep_0_channel_2_measures.csv
(22787, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion4_rep_0_channel_2_measures.csv
(42538, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion5_rep_1_channel_2_measures.csv
(31370, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion3_rep_0_channel_2_measures.csv
(4465, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion0_rep_1_channel_2_measures.csv
(24746, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion1_rep_1_channel_2_measures.csv
(5061, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion5_rep_2_channel_2_measures.csv
(45127, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion1_rep_1_channel_2_measures.csv
(12207, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion5_rep_0_channel_2_measures.csv
(36668, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion4_rep_0_channel_2_measures.csv
(22478, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion0_rep_0_channel_2_measures.csv
(75915, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion4_rep_0_channel_2_measures.csv
(881, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion1_rep_2_channel_2_measures.csv
(25173, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion0_rep_1_channel_2_measures.csv
(9836, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion7_rep_2_channel_2_measures.csv
(27770, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion5_rep_0_channel_2_measures.csv
(52956, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion2_rep_2_channel_2_measures.csv
(55563, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion1_rep_1_channel_2_measures.csv
(92340, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion2_rep_1_channel_2_measures.csv
(2185, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion2_rep_2_channel_2_measures.csv
(13307, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion3_rep_0_channel_2_measures.csv
(47582, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion0_rep_2_channel_2_measures.csv
(1122, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion1_rep_0_channel_2_measures.csv
(5646, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion6_rep_1_channel_2_measures.csv
(22272, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion5_rep_1_channel_2_measures.csv
(59825, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion3_rep_0_channel_2_measures.csv
(11258, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion4_rep_2_channel_2_measures.csv
(6712, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion1_rep_0_channel_2_measures.csv
(26007, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion7_rep_3_channel_2_measures.csv
(72679, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion2_rep_1_channel_2_measures.csv
(17407, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion6_rep_2_channel_2_measures.csv
(4246, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion5_rep_1_channel_2_measures.csv
(79266, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion4_rep_1_channel_2_measures.csv
(10935, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion2_rep_0_channel_2_measures.csv
(24890, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion0_rep_1_channel_2_measures.csv
(24601, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion5_rep_2_channel_2_measures.csv
(58504, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion2_rep_2_channel_2_measures.csv
(7832, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion2_rep_1_channel_2_measures.csv
(194410, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion1_rep_0_channel_2_measures.csv
(2649, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion0_rep_2_channel_2_measures.csv
(35739, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion5_rep_1_channel_2_measures.csv
(72165, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion4_rep_0_channel_2_measures.csv
(79123, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion4_rep_1_channel_2_measures.csv
(17120, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion3_rep_0_channel_2_measures.csv
(43389, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion3_rep_2_channel_2_measures.csv
(19504, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0131_ScanRegion4_rep_1_channel_2_measures.csv
(38346, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0128_ScanRegion0_rep_0_channel_2_measures.csv
(70479, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0134_ScanRegion3_rep_0_channel_2_measures.csv
(50144, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion3_rep_2_channel_2_measures.csv
(1195, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion3_rep_1_channel_2_measures.csv
(54110, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0133_ScanRegion4_rep_1_channel_2_measures.csv
(4832, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0132_ScanRegion3_rep_1_channel_2_measures.csv
(39112, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0130_ScanRegion0_rep_0_channel_2_measures.csv
(41176, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion3_rep_3_channel_2_measures.csv
(9818, 19)
/group/testa/Project/EndPoints/TPSSU/analysis/measurements/20240424_manuel_lessi_0129_ScanRegion3_rep_4_channel_2_measures.csv
(23465, 19)


#tot_df_mix1_ch2.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/measurements_mix_1_ch2_SOX2.csv")


tot_pos_SOX2 = {}
density_SOX2 = {}
n_nuclei = {}
n_nuclei_tot_pos_SOX2 = {}

for file in measurements_files_mix_1_ch2:
    #print(file)
    df = pd.read_csv(file, index_col=0)
    
    imageName_scanRegion_rep = file.split('/')[-1].split('.')[0].replace('_channel_2_measures', '')
    imageName_scanRegion = '_'.join(imageName_scanRegion_rep.split('_')[:5])
    
    if imageName_scanRegion_rep in good_tissue_to_keep_limit and imageName_scanRegion in sample_sheet['ImageName_ScanRegion'].values:
        area = area_dict[imageName_scanRegion_rep]
        
        df['ImageName'] = file.split("/")[-1].split(".")[0]
        tot_pos_SOX2[file.split("/")[-1].split(".")[0]] = {}
        density_SOX2[imageName_scanRegion_rep] = {}
        n_nuclei_tot_pos_SOX2[imageName_scanRegion_rep] = {}

        min_quantile = np.quantile(df['area'], 0.01)

        max_quantile = np.quantile(df['area'], 0.99)

        df = df[(df['area'] > min_quantile) & (df['area'] < max_quantile)]

        n_nuclei[file.split("/")[-1].split(".")[0]] = df.shape[0]

        otsu_thrs = filters.threshold_multiotsu(np.array(df['intensity_mean']), classes = 4)

        for i, thr in enumerate(otsu_thrs):
            tot_pos_SOX2[file.split("/")[-1].split(".")[0]][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr) / df.shape[0] * 100
            n_nuclei_tot_pos_SOX2[imageName_scanRegion_rep][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr)
            density_SOX2[imageName_scanRegion_rep][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr) / area * 100


df_percentages = pd.DataFrame.from_dict(tot_pos_SOX2, orient='index')
df_percentages['ImageName_ScanRegion'] = df_percentages.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:5])).values
df_percentages['ImageName_ScanRegion_rep'] = df_percentages.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:7])).values
df_percentages['Condition_Line'] = df_percentages['ImageName_ScanRegion'].map(sample_dict)
df_percentages = df_percentages[~df_percentages.Condition_Line.isna()]
df_percentages['Line'] = df_percentages['Condition_Line'].apply(lambda x: x.split('_')[-1])
df_percentages['Condition'] = df_percentages['Condition_Line'].str.replace('_CTL08A', '', regex=True)
df_percentages['Condition'] = df_percentages['Condition'].str.replace('_CTL04E', '', regex=True)

#df_percentages = pd.read_csv("/group/testa/Project/EndPoints/TPSSU/analysis/percentages_mix_1_ch2_SOX2_percentages.csv")


sox2_pos_cells = pd.DataFrame.from_dict(n_nuclei_tot_pos_SOX2, orient='index')
sox2_pos_cells['ImageName_ScanRegion'] = sox2_pos_cells.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:5])).values
sox2_pos_cells['ImageName_ScanRegion_rep'] = sox2_pos_cells.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:7])).values
sox2_pos_cells['Condition_Line'] = sox2_pos_cells['ImageName_ScanRegion'].map(sample_dict)
sox2_pos_cells = sox2_pos_cells[~sox2_pos_cells.Condition_Line.isna()]
sox2_pos_cells['Line'] = sox2_pos_cells['Condition_Line'].apply(lambda x: x.split('_')[-1])
sox2_pos_cells['Condition'] = sox2_pos_cells['Condition_Line'].str.replace('_CTL08A', '', regex=True)
sox2_pos_cells['Condition'] = sox2_pos_cells['Condition'].str.replace('_CTL04E', '', regex=True)
sox2_pos_cells


density_SOX2 = pd.DataFrame.from_dict(density_SOX2, orient='index').reset_index()
density_SOX2['ImageName_ScanRegion'] = density_SOX2['index'].apply(lambda x: '_'.join(x.split('_')[0:5]))
density_SOX2['ImageName_ScanRegion_rep'] = density_SOX2['index'].apply(lambda x: '_'.join(x.split('_')[0:7]))
density_SOX2['Condition_Line'] = density_SOX2['ImageName_ScanRegion'].map(sample_dict)
density_SOX2 = density_SOX2[~density_SOX2.Condition_Line.isna()]
density_SOX2['Line'] = density_SOX2['Condition_Line'].apply(lambda x: x.split('_')[-1])
density_SOX2['Condition'] = density_SOX2['Condition_Line'].str.replace('_CTL08A', '', regex=True)
density_SOX2['Condition'] = density_SOX2['Condition'].str.replace('_CTL04E', '', regex=True)

print(len(density_SOX2))
#density_SOX2.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/SOX2_pos_over_area_mix_1_ch2.csv")

65


n_nuclei = pd.DataFrame.from_dict(n_nuclei, orient='index').reset_index()
n_nuclei['ImageName_ScanRegion'] = n_nuclei['index'].apply(lambda x: '_'.join(x.split('_')[0:5]))
n_nuclei['ImageName_ScanRegion_rep'] = n_nuclei['index'].apply(lambda x: '_'.join(x.split('_')[0:7]))
n_nuclei['Condition_Line'] = n_nuclei['ImageName_ScanRegion'].map(sample_dict)
n_nuclei = n_nuclei[~n_nuclei.Condition_Line.isna()]
n_nuclei['Line'] = n_nuclei['Condition_Line'].apply(lambda x: x.split('_')[-1])
n_nuclei['Condition'] = n_nuclei['Condition_Line'].str.replace('_CTL08A', '', regex=True)
n_nuclei['Condition'] = n_nuclei['Condition'].str.replace('_CTL04E', '', regex=True)


mix1_img_names = tot_df_mix1_ch2['ImageName'].apply(lambda x: '_'.join(x.split('_')[0:4])).value_counts().index.tolist()


check_qc_ch2['ImageName_ScanRegion'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:5]))
check_qc_ch2['ImageName_ScanRegion_rep'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:7]))
check_qc_ch2['ImageName'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:4]))
check_qc_ch2_mix1 = check_qc_ch2[check_qc_ch2['ImageName'].isin(mix1_img_names)]


check_qc_ch2_mix1['general QC (keep or not)'].value_counts()

general QC (keep or not)
YES      86
NO       15
LIMIT     6
Name: count, dtype: int64


check_qc_ch2_mix1


to_remove = check_qc_ch2_mix1[check_qc_ch2_mix1['general QC (keep or not)'] == 'NO']['ImageName_ScanRegion_rep'].tolist()
len(to_remove)

15


df_percentages = df_percentages[~df_percentages['ImageName_ScanRegion_rep'].isin(to_remove)]
len(df_percentages)

65


sox2_pos_cells = sox2_pos_cells[~sox2_pos_cells['ImageName_ScanRegion_rep'].isin(to_remove)]
len(sox2_pos_cells)

65


n_nuclei = n_nuclei[~n_nuclei['ImageName_ScanRegion_rep'].isin(to_remove)]
len(n_nuclei)

65


order = df_percentages['Condition'].tolist()
order = list(dict.fromkeys(order))  # Remove duplicates while preserving order
order.remove('DMSO')
order.sort()
order = ['DMSO'] + order


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df_percentages[(df_percentages['Line'] == 'CTL08A') & 
                                 (df_percentages['Condition'] == cond)]['otsu_1']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df_percentages[(df_percentages['Condition'] == 'DMSO') & 
                                       (df_percentages['Line'] == 'CTL08A')]['otsu_1'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df_percentages[(df_percentages['Line'] == 'CTL08A')],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df_percentages[(df_percentages['Line'] == 'CTL04E') & 
                                 (df_percentages['Condition'] == cond)]['otsu_1']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df_percentages[(df_percentages['Condition'] == 'DMSO') & 
                                       (df_percentages['Line'] == 'CTL04E')]['otsu_1'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df_percentages[df_percentages['Line'] == 'CTL04E'],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('SOX2+ nuclei (%)')
ax[1].set_ylabel('SOX2+ nuclei (%)')

plt.savefig('../../../../endpoints_figures/SOX2_pos_otsu_1_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/SOX2_pos_otsu_1_per_condition.png', dpi=300, bbox_inches='tight')


df_percentages[df_percentages.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False)


sox2_pos_cells[sox2_pos_cells.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False)


df_percentages[df_percentages.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


sox2_pos_cells[sox2_pos_cells.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


sox2_pos_cells


check_area_df = organoid_areas.loc[sox2_pos_cells.ImageName_ScanRegion_rep.tolist()]
check_area_df


check_area_df[check_area_df.Condition.isin(['RET_AG', 'DMSO'])][['area', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


n_nuclei[n_nuclei.Condition.isin(['RET_AG', 'DMSO'])][[0, 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


sox2_pos_cells['total'] = sox2_pos_cells['ImageName_ScanRegion_rep'].map({i:j for i, j in zip(n_nuclei['ImageName_ScanRegion_rep'], n_nuclei[0])})


sox2_pos_cells_CTL08A = sox2_pos_cells[sox2_pos_cells['Line'] == 'CTL08A']

sox2_pos_cells_CTL08A["prop"] = sox2_pos_cells_CTL08A["otsu_1"] / sox2_pos_cells_CTL08A["total"]
sox2_pos_cells_CTL08A["logit_prop"] = np.log(sox2_pos_cells_CTL08A["prop"] / (1 - sox2_pos_cells_CTL08A["prop"]))

model_CTL08A = smf.ols(
    "logit_prop ~ C(Condition, Treatment(reference='DMSO'))",
    data=sox2_pos_cells_CTL08A
).fit()


print(model_CTL08A.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:             logit_prop   R-squared:                       0.565
Model:                            OLS   Adj. R-squared:                  0.309
Method:                 Least Squares   F-statistic:                     2.201
Date:                Mon, 02 Mar 2026   Prob (F-statistic):             0.0496
Time:                        15:07:52   Log-Likelihood:                -14.374
No. Observations:                  36   AIC:                             56.75
Df Residuals:                      22   BIC:                             78.92
Df Model:                          13                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -2.1951      0.266     -8.240      0.000      -2.748      -1.643
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.2963      0.377      0.786      0.440      -0.485       1.078
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.2565      0.337      0.761      0.455      -0.442       0.955
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.1645      0.377     -0.437      0.667      -0.946       0.617
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.4915      0.421      1.167      0.256      -0.382       1.365
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.5876      0.421      1.395      0.177      -0.286       1.461
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]        0.7627      0.421      1.811      0.084      -0.111       1.636
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.8711      0.421      2.068      0.051      -0.002       1.745
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.2757      0.377      0.732      0.472      -0.506       1.057
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.8440      0.533      1.584      0.127      -0.261       1.949
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]       1.3298      0.377      3.529      0.002       0.548       2.111
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.0072      0.377      0.019      0.985      -0.774       0.789
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -0.0771      0.421     -0.183      0.856      -0.951       0.796
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.3515      0.421      0.835      0.413      -0.522       1.225
==============================================================================
Omnibus:                        7.041   Durbin-Watson:                   1.978
Prob(Omnibus):                  0.030   Jarque-Bera (JB):                6.343
Skew:                          -0.638   Prob(JB):                       0.0419
Kurtosis:                       4.613   Cond. No.                         14.0
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/2300495477.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  sox2_pos_cells_CTL08A["prop"] = sox2_pos_cells_CTL08A["otsu_1"] / sox2_pos_cells_CTL08A["total"]
/tmp/ipykernel_3702104/2300495477.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  sox2_pos_cells_CTL08A["logit_prop"] = np.log(sox2_pos_cells_CTL08A["prop"] / (1 - sox2_pos_cells_CTL08A["prop"]))


sox2_pos_cells_CTL04E = sox2_pos_cells[sox2_pos_cells['Line'] == 'CTL04E']

sox2_pos_cells_CTL04E["prop"] = sox2_pos_cells_CTL04E["otsu_1"] / sox2_pos_cells_CTL04E["total"]
sox2_pos_cells_CTL04E["logit_prop"] = np.log(sox2_pos_cells_CTL04E["prop"] / (1 - sox2_pos_cells_CTL04E["prop"]))

model_CTL04E = smf.ols(
    "logit_prop ~ C(Condition, Treatment(reference='DMSO'))",
    data=sox2_pos_cells_CTL04E,
    freq_weights=sox2_pos_cells_CTL04E["total"]
).fit()


print(model_CTL04E.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:             logit_prop   R-squared:                       0.379
Model:                            OLS   Adj. R-squared:                 -0.023
Method:                 Least Squares   F-statistic:                    0.9439
Date:                Mon, 02 Mar 2026   Prob (F-statistic):              0.525
Time:                        15:07:53   Log-Likelihood:                -9.7081
No. Observations:                  29   AIC:                             43.42
Df Residuals:                      17   BIC:                             59.82
Df Model:                          11                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -1.5235      0.312     -4.878      0.000      -2.182      -0.865
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.4697      0.442      1.063      0.302      -0.462       1.402
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -0.2268      0.403     -0.563      0.581      -1.078       0.624
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]    -0.0049      0.403     -0.012      0.991      -0.856       0.846
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -0.1204      0.442     -0.273      0.788      -1.052       0.811
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.0034      0.403      0.008      0.993      -0.847       0.854
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.2240      0.403     -0.555      0.586      -1.075       0.627
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -0.3528      0.442     -0.799      0.436      -1.285       0.579
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.2639      0.403      0.655      0.522      -0.587       1.115
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.3037      0.442     -0.688      0.501      -1.236       0.628
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.3429      0.403      0.850      0.407      -0.508       1.194
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.5097      0.541      0.942      0.359      -0.632       1.651
==============================================================================
Omnibus:                        4.068   Durbin-Watson:                   1.955
Prob(Omnibus):                  0.131   Jarque-Bera (JB):                2.536
Skew:                          -0.471   Prob(JB):                        0.281
Kurtosis:                       4.100   Cond. No.                         14.2
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/4102023209.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  sox2_pos_cells_CTL04E["prop"] = sox2_pos_cells_CTL04E["otsu_1"] / sox2_pos_cells_CTL04E["total"]
/tmp/ipykernel_3702104/4102023209.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  sox2_pos_cells_CTL04E["logit_prop"] = np.log(sox2_pos_cells_CTL04E["prop"] / (1 - sox2_pos_cells_CTL04E["prop"]))
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100 # The odds of being SOX2-positive are increased/decreased by this percentage compared to DMSO.
intercepts


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_SOX2pos_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_3702104/2823708458.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = density_SOX2[(density_SOX2['Line'] == 'CTL08A') & 
                                 (density_SOX2['Condition'] == cond)]['otsu_1']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = density_SOX2[(density_SOX2['Condition'] == 'DMSO') & 
                                       (density_SOX2['Line'] == 'CTL08A')]['otsu_1'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=density_SOX2[(density_SOX2['Line'] == 'CTL08A')],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = density_SOX2[(density_SOX2['Line'] == 'CTL04E') & 
                                 (density_SOX2['Condition'] == cond)]['otsu_1']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = density_SOX2[(density_SOX2['Condition'] == 'DMSO') & 
                                       (density_SOX2['Line'] == 'CTL04E')]['otsu_1'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=density_SOX2[density_SOX2['Line'] == 'CTL04E'],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('SOX2+ nuclei / organoid area (um²)')
ax[1].set_ylabel('SOX2+ nuclei / organoid area (um²)')

plt.savefig('../../../../endpoints_figures/SOX2_density_otsu_1_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/SOX2_density_otsu_1_per_condition.png', dpi=300, bbox_inches='tight')


density_SOX2[density_SOX2.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


mask_file_df_mix_1 = mask_file_df_mix_1.merge(sample_sheet, left_on='ImageName_ScanRegion', right_on='ImageName_ScanRegion', how='left')
mask_file_df_mix_1


mask_file_df_mix_1.set_index('level_1', inplace=True)


mask_file_df_mix_1['Line'] = mask_file_df_mix_1['Condition_Line'].apply(lambda x: x.split('_')[-1] if pd.notnull(x) else x)


mask_file_df_mix_1['organoid_area'] = mask_file_df_mix_1['ImageName_ScanRegion_Rep'].map({i:j for i, j in zip(organoid_areas.index, organoid_areas['area'])})


mask_file_df_mix_1['organoid_area_um2'] = mask_file_df_mix_1['organoid_area'] * (px_size ** 2)
mask_file_df_mix_1['area_um2'] = mask_file_df_mix_1['area'] * (px_size ** 2)


n_nuclei = pd.read_csv('../tables/n_nuclei_mix1.csv')
n_nuclei['ImageName'] = n_nuclei['ImageName'].str.replace('_channel_1', '')


mask_file_df_mix_1['n_nuclei'] = mask_file_df_mix_1['ImageName_ScanRegion_Rep'].map({i:j for i, j in zip(n_nuclei['ImageName'], n_nuclei['count'])})


mask_file_df_mix_1['pos_area_over_nuclei'] = mask_file_df_mix_1['area_um2'] / mask_file_df_mix_1['n_nuclei']
mask_file_df_mix_1['pos_area_over_tot'] = mask_file_df_mix_1['area_um2'] / mask_file_df_mix_1['organoid_area_um2']


mask_file_df_mix_1.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/measurements_mix_1_ch0_TUJ1.csv")


mask_file_df_mix_1


df = mask_file_df_mix_1[mask_file_df_mix_1.ImageName_ScanRegion_Rep.isin(good_tissue_to_keep_limit)]

fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_nuclei']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_nuclei'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_nuclei']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_nuclei'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('TUJ1+ area (um2) / # nuclei')
ax[1].set_ylabel('TUJ1+ area (um2) / # nuclei')

plt.savefig('../../../../endpoints_figures/TUJ1_pos_area_over_nuclei_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/TUJ1_pos_area_over_nuclei_per_condition.png', dpi=300, bbox_inches='tight')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_nuclei', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


mask_file_df_mix_1_CTL04E = mask_file_df_mix_1[mask_file_df_mix_1['Line'] == 'CTL04E']
mask_file_df_mix_1_CTL04E['Condition'] = mask_file_df_mix_1_CTL04E['Condition'].astype('category')
mask_file_df_mix_1_CTL04E["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_1_CTL04E["area_um2"] / mask_file_df_mix_1_CTL04E["n_nuclei"])
mask_file_df_mix_1_CTL04E['log_area_over_n_nuclei'].hist(bins = 10)

model_CTL04E = smf.ols("log_area_over_n_nuclei ~ C(Condition, Treatment(reference='DMSO'))",
                data=mask_file_df_mix_1_CTL04E,
                freq_weights=mask_file_df_mix_1_CTL04E["n_nuclei"]
                ).fit()

print(model_CTL04E.summary())

/tmp/ipykernel_3702104/58368655.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_1_CTL04E['Condition'] = mask_file_df_mix_1_CTL04E['Condition'].astype('category')
/tmp/ipykernel_3702104/58368655.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_1_CTL04E["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_1_CTL04E["area_um2"] / mask_file_df_mix_1_CTL04E["n_nuclei"])
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)

                              OLS Regression Results                              
==================================================================================
Dep. Variable:     log_area_over_n_nuclei   R-squared:                       0.346
Model:                                OLS   Adj. R-squared:                 -0.032
Method:                     Least Squares   F-statistic:                    0.9149
Date:                    Mon, 02 Mar 2026   Prob (F-statistic):              0.546
Time:                            15:08:00   Log-Likelihood:                -9.9467
No. Observations:                      31   AIC:                             43.89
Df Residuals:                          19   BIC:                             61.10
Df Model:                              11                                         
Covariance Type:                nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                 4.0803      0.301     13.545      0.000       3.450       4.711
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.6328      0.426      1.486      0.154      -0.259       1.524
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.2016      0.389      0.518      0.610      -0.612       1.016
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]     0.1546      0.389      0.397      0.695      -0.659       0.969
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -0.0232      0.426     -0.054      0.957      -0.915       0.868
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.2824      0.389      0.726      0.477      -0.532       1.096
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.0640      0.389     -0.164      0.871      -0.878       0.750
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.7773      0.389      1.999      0.060      -0.037       1.591
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.0914      0.389      0.235      0.817      -0.723       0.905
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.3163      0.389      0.813      0.426      -0.498       1.130
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.2027      0.389      0.521      0.608      -0.611       1.017
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.2782      0.522      0.533      0.600      -0.814       1.370
==============================================================================
Omnibus:                       18.900   Durbin-Watson:                   2.640
Prob(Omnibus):                  0.000   Jarque-Bera (JB):               36.693
Skew:                           1.242   Prob(JB):                     1.08e-08
Kurtosis:                       7.716   Cond. No.                         14.7
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.


mask_file_df_mix_1_CTL08A = mask_file_df_mix_1[mask_file_df_mix_1['Line'] == 'CTL08A']
mask_file_df_mix_1_CTL08A['Condition'] = mask_file_df_mix_1_CTL08A['Condition'].astype('category')
mask_file_df_mix_1_CTL08A["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_1_CTL08A["area_um2"] / mask_file_df_mix_1_CTL08A["n_nuclei"])
mask_file_df_mix_1_CTL08A['log_area_over_n_nuclei'].hist(bins = 10)

model_CTL08A = smf.ols("log_area_over_n_nuclei ~ C(Condition, Treatment(reference='DMSO'))",
                data=mask_file_df_mix_1_CTL08A,
                freq_weights=mask_file_df_mix_1_CTL08A["n_nuclei"]
                ).fit()

print(model_CTL08A.summary())

                              OLS Regression Results                              
==================================================================================
Dep. Variable:     log_area_over_n_nuclei   R-squared:                       0.526
Model:                                OLS   Adj. R-squared:                  0.289
Method:                     Least Squares   F-statistic:                     2.219
Date:                    Mon, 02 Mar 2026   Prob (F-statistic):             0.0406
Time:                            15:08:01   Log-Likelihood:                0.32798
No. Observations:                      40   AIC:                             27.34
Df Residuals:                          26   BIC:                             50.99
Df Model:                              13                                         
Covariance Type:                nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                 4.0439      0.172     23.530      0.000       3.691       4.397
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.3981      0.243      1.638      0.114      -0.102       0.898
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.4010      0.217      1.845      0.077      -0.046       0.848
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]     0.6730      0.243      2.769      0.010       0.173       1.173
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.6589      0.272      2.425      0.023       0.100       1.217
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.4310      0.272      1.586      0.125      -0.128       0.990
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]        0.3515      0.272      1.293      0.207      -0.207       0.910
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.5384      0.243      2.215      0.036       0.039       1.038
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.4979      0.243      2.048      0.051      -0.002       0.997
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.2920      0.272      1.074      0.292      -0.267       0.851
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]       0.8220      0.243      3.382      0.002       0.322       1.322
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.0887      0.243      0.365      0.718      -0.411       0.588
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.1299      0.243      0.534      0.598      -0.370       0.629
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -0.0455      0.243     -0.187      0.853      -0.545       0.454
==============================================================================
Omnibus:                        1.470   Durbin-Watson:                   2.601
Prob(Omnibus):                  0.479   Jarque-Bera (JB):                0.617
Skew:                          -0.193   Prob(JB):                        0.734
Kurtosis:                       3.470   Cond. No.                         14.7
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/4221072985.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_1_CTL08A['Condition'] = mask_file_df_mix_1_CTL08A['Condition'].astype('category')
/tmp/ipykernel_3702104/4221072985.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_1_CTL08A["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_1_CTL08A["area_um2"] / mask_file_df_mix_1_CTL08A["n_nuclei"])
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100
intercepts


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_TUJ_n_nuclei_OLS_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_3702104/584137039.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


df = mask_file_df_mix_1[mask_file_df_mix_1.ImageName_ScanRegion_Rep.isin(good_tissue_to_keep_limit)]

fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_tot'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_tot'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('TUJ1+ area (um2) / organoid area (um2)', fontsize=15)
ax[1].set_ylabel('TUJ1+ area (um2) / organoid area (um2)', fontsize=15)

plt.savefig('../../../../endpoints_figures/TUJ1_pos_area_over_tot_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/TUJ1_pos_area_over_tot_per_condition.png', dpi=300, bbox_inches='tight')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_tot', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


SOX2_KI67_mask_file_df_mix_1 = SOX2_KI67_mask_file_df_mix_1.merge(sample_sheet, left_on='ImageName_ScanRegion', right_on='ImageName_ScanRegion', how='left')
SOX2_KI67_mask_file_df_mix_1


SOX2_KI67_mask_file_df_mix_1.set_index('level_1', inplace=True)


SOX2_KI67_mask_file_df_mix_1['Line'] = SOX2_KI67_mask_file_df_mix_1['Condition_Line'].apply(lambda x: x.split('_')[-1] if pd.notnull(x) else x)


SOX2_KI67_mask_file_df_mix_1['organoid_area_um2'] = SOX2_KI67_mask_file_df_mix_1['ImageName_ScanRegion_Rep'].map({i:j for i, j in zip(organoid_areas.index, organoid_areas['area'])}) * (px_size ** 2)
SOX2_KI67_mask_file_df_mix_1['area_um2'] = SOX2_KI67_mask_file_df_mix_1['area'] * (px_size ** 2)


SOX2_KI67_mask_file_df_mix_1['n_nuclei'] = SOX2_KI67_mask_file_df_mix_1['ImageName_ScanRegion_Rep'].map({i:j for i, j in zip(n_nuclei['ImageName'], n_nuclei['count'])})


SOX2_KI67_mask_file_df_mix_1['pos_area_over_nuclei'] = SOX2_KI67_mask_file_df_mix_1['area_um2'] / SOX2_KI67_mask_file_df_mix_1['n_nuclei']
SOX2_KI67_mask_file_df_mix_1['pos_area_over_tot'] = SOX2_KI67_mask_file_df_mix_1['area_um2'] / SOX2_KI67_mask_file_df_mix_1['organoid_area_um2']


mask_file_df_mix_1.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/measurements_mix_1_ch0_TUJ1.csv")


df = SOX2_KI67_mask_file_df_mix_1[SOX2_KI67_mask_file_df_mix_1.ImageName_ScanRegion_Rep.isin(good_tissue_to_keep_limit)]

fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_nuclei']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_nuclei'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_nuclei']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_nuclei'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('SOX2+ area (um2) / # nuclei')
ax[1].set_ylabel('SOX2+ area (um2) / # nuclei')

Text(0, 0.5, 'SOX2+ area (um2) / # nuclei')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_nuclei', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


df = SOX2_KI67_mask_file_df_mix_1[SOX2_KI67_mask_file_df_mix_1.ImageName_ScanRegion_Rep.isin(good_tissue_to_keep_limit)]

fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_tot'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_tot'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('SOX2+ area (um2) / organoid area (um2)', fontsize=15)
ax[1].set_ylabel('SOX2+ area (um2) / organoid area (um2)', fontsize=15)

Text(0, 0.5, 'SOX2+ area (um2) / organoid area (um2)')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_tot', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


n_nuclei_tot_pos_SOX2_otsu1 = {k: v['otsu_1'] for k, v in n_nuclei_tot_pos_SOX2.items() if 'otsu_1' in v}


df['SOX2+'] = df['ImageName_ScanRegion_Rep'].map(n_nuclei_tot_pos_SOX2_otsu1)

/tmp/ipykernel_3702104/1000197899.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['SOX2+'] = df['ImageName_ScanRegion_Rep'].map(n_nuclei_tot_pos_SOX2_otsu1)


df["SOX2+_TUJ1_ratio"] = df['SOX2+'] / df['area_um2']

/tmp/ipykernel_3702104/3857021914.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df["SOX2+_TUJ1_ratio"] = df['SOX2+'] / df['area_um2']


fig, ax = plt.subplots(1, 2, figsize=(25, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['SOX2+_TUJ1_ratio']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['SOX2+_TUJ1_ratio'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='SOX2+_TUJ1_ratio', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['SOX2+_TUJ1_ratio']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['SOX2+_TUJ1_ratio'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='SOX2+_TUJ1_ratio', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('SOX2+_TUJ1_ratio')
ax[1].set_ylabel('SOX2+_TUJ1_ratio')

plt.savefig('../../../../endpoints_figures/SOX2+_TUJ1_ratio_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/SOX2+_TUJ1_ratio_per_condition.png', dpi=300, bbox_inches='tight')


tot_df_mix2_ch2 = pd.DataFrame()
measurements_files_mix_2_ch2 = [f for f in measurements_files_mix_2 if 'channel_2' in f]

for file in measurements_files_mix_2_ch2:
    df = pd.read_csv(file, index_col=0)
    df['ImageName'] = file.split("/")[-1].split(".")[0]
    tot_df_mix2_ch2 = pd.concat([tot_df_mix2_ch2, df], axis=0)


# tot_df_mix2_ch2.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/measurements_mix_2_ch2_MKI67.csv")


tot_pos_MKI67 = {}
dens_norm_MKI67 = {}
density_MKI67 = {}
n_nuclei = {}
n_nuclei_tot_pos_MKI67 = {}

for file in measurements_files_mix_2_ch2:
    #print(file)
    imageName_scanRegion_rep = file.split('/')[-1].split('.')[0].replace('_channel_2_measures', '')
    imageName_scanRegion = '_'.join(imageName_scanRegion_rep.split('_')[:5])
    
    if imageName_scanRegion_rep in good_tissue_to_keep_limit and imageName_scanRegion in sample_sheet['ImageName_ScanRegion'].values:
        df = pd.read_csv(file, index_col=0)
        
        imageName_scanRegion_rep = file.split('/')[-1].split('.')[0].replace('_channel_2_measures', '')
        density = density_dict[imageName_scanRegion_rep]
        area = area_dict[imageName_scanRegion_rep]
        
        df['ImageName'] = file.split("/")[-1].split(".")[0]
        tot_pos_MKI67[file.split("/")[-1].split(".")[0]] = {}
        dens_norm_MKI67[imageName_scanRegion_rep] = {}
        density_MKI67[imageName_scanRegion_rep] = {}
        n_nuclei_tot_pos_MKI67[imageName_scanRegion_rep] = {}

        min_quantile = np.quantile(df['area'], 0.01)

        max_quantile = np.quantile(df['area'], 0.99)

        df = df[(df['area'] > min_quantile) & (df['area'] < max_quantile)]

        n_nuclei[file.split("/")[-1].split(".")[0]] = df.shape[0]

        otsu_thrs = filters.threshold_multiotsu(np.array(df['intensity_mean']), classes = 4)

        for i, thr in enumerate(otsu_thrs):
            tot_pos_MKI67[file.split("/")[-1].split(".")[0]][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr) / df.shape[0] * 100
            n_nuclei_tot_pos_MKI67[imageName_scanRegion_rep][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr)
            dens_norm_MKI67[imageName_scanRegion_rep][f'otsu_{i}'] = tot_pos_MKI67[file.split("/")[-1].split(".")[0]][f'otsu_{i}'] * density
            density_MKI67[imageName_scanRegion_rep][f'otsu_{i}'] = np.sum(df['intensity_mean'] > thr) / area * 100


df_percentages = pd.DataFrame.from_dict(tot_pos_MKI67, orient='index')
df_percentages['ImageName_ScanRegion'] = df_percentages.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:5])).values
df_percentages['ImageName_ScanRegion_rep'] = df_percentages.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:7])).values
df_percentages['Condition_Line'] = df_percentages['ImageName_ScanRegion'].map(sample_dict)
df_percentages = df_percentages[~df_percentages.Condition_Line.isna()]
df_percentages['Line'] = df_percentages['Condition_Line'].apply(lambda x: x.split('_')[-1])
df_percentages['Condition'] = df_percentages['Condition_Line'].str.replace('_CTL08A', '', regex=True)
df_percentages['Condition'] = df_percentages['Condition'].str.replace('_CTL04E', '', regex=True)

#df_percentages.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/percentages_mix_2_ch2_MKI67_percentages.csv")


KI67_pos = pd.DataFrame.from_dict(n_nuclei_tot_pos_MKI67, orient='index')
KI67_pos['ImageName_ScanRegion'] = KI67_pos.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:5])).values
KI67_pos['ImageName_ScanRegion_rep'] = KI67_pos.reset_index()['index'].apply(lambda x: '_'.join(x.split('_')[0:7])).values
KI67_pos['Condition_Line'] = KI67_pos['ImageName_ScanRegion'].map(sample_dict)
KI67_pos = KI67_pos[~KI67_pos.Condition_Line.isna()]
KI67_pos['Line'] = KI67_pos['Condition_Line'].apply(lambda x: x.split('_')[-1])
KI67_pos['Condition'] = KI67_pos['Condition_Line'].str.replace('_CTL08A', '', regex=True)
KI67_pos['Condition'] = KI67_pos['Condition'].str.replace('_CTL04E', '', regex=True)


density_MKI67 = pd.DataFrame.from_dict(density_MKI67, orient='index').reset_index()
density_MKI67['ImageName_ScanRegion'] = density_MKI67['index'].apply(lambda x: '_'.join(x.split('_')[0:5]))
density_MKI67['ImageName_ScanRegion_rep'] = density_MKI67['index'].apply(lambda x: '_'.join(x.split('_')[0:7]))
density_MKI67['Condition_Line'] = density_MKI67['ImageName_ScanRegion'].map(sample_dict)
density_MKI67 = density_MKI67[~density_MKI67.Condition_Line.isna()]
density_MKI67['Line'] = density_MKI67['Condition_Line'].apply(lambda x: x.split('_')[-1])
density_MKI67['Condition'] = density_MKI67['Condition_Line'].str.replace('_CTL08A', '', regex=True)
density_MKI67['Condition'] = density_MKI67['Condition'].str.replace('_CTL04E', '', regex=True)

print(len(density_MKI67))
#density_MKI67.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/MKI67_pos_over_area_mix_1_ch2.csv")

74


n_nuclei_df = pd.DataFrame.from_dict(n_nuclei, orient='index').reset_index()
n_nuclei_df['ImageName_ScanRegion'] = n_nuclei_df['index'].apply(lambda x: '_'.join(x.split('_')[0:5]))
n_nuclei_df['ImageName_ScanRegion_rep'] = n_nuclei_df['index'].apply(lambda x: '_'.join(x.split('_')[0:7]))
n_nuclei_df['Condition_Line'] = n_nuclei_df['ImageName_ScanRegion'].map(sample_dict)
n_nuclei_df = n_nuclei_df[~n_nuclei_df.Condition_Line.isna()]
n_nuclei_df['Line'] = n_nuclei_df['Condition_Line'].apply(lambda x: x.split('_')[-1])
n_nuclei_df['Condition'] = n_nuclei_df['Condition_Line'].str.replace('_CTL08A', '', regex=True)
n_nuclei_df['Condition'] = n_nuclei_df['Condition'].str.replace('_CTL04E', '', regex=True)


check_area_df = organoid_areas.loc[KI67_pos.ImageName_ScanRegion_rep.tolist()]
check_area_df


check_area_df[check_area_df.Condition.isin(['RET_AG', 'DMSO'])][['area', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


mix2_img_names = tot_df_mix2_ch2['ImageName'].apply(lambda x: '_'.join(x.split('_')[0:4])).value_counts().index.tolist()
mix2_img_names

['20240424_manuel_lessi_0141',
 '20240424_manuel_lessi_0143',
 '20240424_manuel_lessi_0140',
 '20240424_manuel_lessi_0138',
 '20240424_manuel_lessi_0137',
 '20240424_manuel_lessi_0139',
 '20240424_manuel_lessi_0142']


check_qc_ch2['ImageName_ScanRegion'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:5]))
check_qc_ch2['ImageName_ScanRegion_Rep'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:7]))
check_qc_ch2['ImageName'] = check_qc_ch2['Reference Image Report'].apply(lambda x: '_'.join(x.split('_')[0:4]))
check_qc_ch2_mix2 = check_qc_ch2[check_qc_ch2['ImageName'].isin(mix2_img_names)]
check_qc_ch2_mix2


check_qc_ch2_mix2['general QC (keep or not)'].value_counts()

general QC (keep or not)
YES      60
NO       35
LIMIT    14
Name: count, dtype: int64


to_remove = check_qc_ch2_mix2[check_qc_ch2_mix2['general QC (keep or not)'] == 'NO']['ImageName_ScanRegion_Rep'].tolist()
len(to_remove)

35


df_percentages = df_percentages[~df_percentages['ImageName_ScanRegion_rep'].isin(to_remove)]
len(df_percentages)

49


KI67_pos = KI67_pos[~KI67_pos['ImageName_ScanRegion_rep'].isin(to_remove)]
len(KI67_pos)

49


n_nuclei_df = n_nuclei_df[~n_nuclei_df['ImageName_ScanRegion_rep'].isin(to_remove)]
len(n_nuclei_df)

49


order = df_percentages['Condition'].tolist()
order = list(dict.fromkeys(order))  # Remove duplicates while preserving order
order.remove('DMSO')
order.sort()
order = ['DMSO'] + order


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df_percentages[(df_percentages['Line'] == 'CTL08A') & 
                                 (df_percentages['Condition'] == cond)]['otsu_1']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df_percentages[(df_percentages['Condition'] == 'DMSO') & 
                                       (df_percentages['Line'] == 'CTL08A')]['otsu_1'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df_percentages[(df_percentages['Line'] == 'CTL08A')],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df_percentages[(df_percentages['Line'] == 'CTL04E') & 
                                 (df_percentages['Condition'] == cond)]['otsu_1']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df_percentages[(df_percentages['Condition'] == 'DMSO') & 
                                       (df_percentages['Line'] == 'CTL04E')]['otsu_1'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df_percentages[df_percentages['Line'] == 'CTL04E'],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('KI67+ nuclei (%)', fontsize=15)
ax[1].set_ylabel('KI67+ nuclei (%)', fontsize=15)

plt.savefig('../../../../endpoints_figures/MKI67_pos_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/MKI67_pos_per_condition.png', dpi=300, bbox_inches='tight')


df_percentages[df_percentages.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


KI67_pos[KI67_pos.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


n_nuclei_df[n_nuclei_df.Condition.isin(['RET_AG', 'DMSO'])][[0, 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


KI67_pos['total'] = KI67_pos['ImageName_ScanRegion_rep'].map({i:j for i, j in zip(n_nuclei_df['ImageName_ScanRegion_rep'], n_nuclei_df[0])})


KI67_pos_CTL08A = KI67_pos[KI67_pos['Line'] == 'CTL08A']

KI67_pos_CTL08A["prop"] = KI67_pos_CTL08A["otsu_1"] / KI67_pos_CTL08A["total"]
KI67_pos_CTL08A["logit_prop"] = np.log(KI67_pos_CTL08A["prop"] / (1 - KI67_pos_CTL08A["prop"]))

model_CTL08A = smf.ols(
    "logit_prop ~ C(Condition, Treatment(reference='DMSO'))",
    data=KI67_pos_CTL08A,
    freq_weights=KI67_pos_CTL08A["total"]
).fit()


print(model_CTL08A.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:             logit_prop   R-squared:                       0.568
Model:                            OLS   Adj. R-squared:                  0.167
Method:                 Least Squares   F-statistic:                     1.417
Date:                Mon, 02 Mar 2026   Prob (F-statistic):              0.263
Time:                        15:08:52   Log-Likelihood:                -7.4512
No. Observations:                  28   AIC:                             42.90
Df Residuals:                      14   BIC:                             61.55
Df Model:                          13                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -4.1452      0.447     -9.283      0.000      -5.103      -3.188
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.5951      0.631      0.942      0.362      -0.759       1.950
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]     1.3577      0.631      2.150      0.050       0.003       2.712
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.7473      0.499      1.497      0.157      -0.323       1.818
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.7175      0.547      1.312      0.211      -0.455       1.890
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.8569      0.547      1.567      0.139      -0.316       2.030
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]        0.3481      0.547      0.637      0.535      -0.825       1.521
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       1.1186      0.516      2.170      0.048       0.013       2.224
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.3820      0.516      0.741      0.471      -0.724       1.488
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]       0.9965      0.547      1.822      0.090      -0.176       2.169
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]       1.0435      0.547      1.908      0.077      -0.129       2.216
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]      0.1727      0.547      0.316      0.757      -1.000       1.346
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.3073      0.547      0.562      0.583      -0.866       1.480
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.0865      0.631      0.137      0.893      -1.268       1.441
==============================================================================
Omnibus:                        0.516   Durbin-Watson:                   2.415
Prob(Omnibus):                  0.773   Jarque-Bera (JB):                0.087
Skew:                          -0.130   Prob(JB):                        0.957
Kurtosis:                       3.085   Cond. No.                         21.0
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/2826624957.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  KI67_pos_CTL08A["prop"] = KI67_pos_CTL08A["otsu_1"] / KI67_pos_CTL08A["total"]
/tmp/ipykernel_3702104/2826624957.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  KI67_pos_CTL08A["logit_prop"] = np.log(KI67_pos_CTL08A["prop"] / (1 - KI67_pos_CTL08A["prop"]))
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


KI67_pos_CTL04E = KI67_pos[KI67_pos['Line'] == 'CTL04E']

KI67_pos_CTL04E["prop"] = KI67_pos_CTL04E["otsu_1"] / KI67_pos_CTL04E["total"]
KI67_pos_CTL04E["logit_prop"] = np.log(KI67_pos_CTL04E["prop"] / (1 - KI67_pos_CTL04E["prop"]))

model_CTL04E = smf.ols(
    "logit_prop ~ C(Condition, Treatment(reference='DMSO'))",
    data=KI67_pos_CTL04E,
    freq_weights=KI67_pos_CTL04E["total"]
).fit()


print(model_CTL04E.summary())

                            OLS Regression Results                            
==============================================================================
Dep. Variable:             logit_prop   R-squared:                       0.910
Model:                            OLS   Adj. R-squared:                  0.821
Method:                 Least Squares   F-statistic:                     10.14
Date:                Mon, 02 Mar 2026   Prob (F-statistic):           0.000538
Time:                        15:08:52   Log-Likelihood:                 1.4378
No. Observations:                  21   AIC:                             19.12
Df Residuals:                      10   BIC:                             30.61
Df Model:                          10                                         
Covariance Type:            nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                -3.3823      0.232    -14.608      0.000      -3.898      -2.866
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.1183      0.401      0.295      0.774      -0.775       1.012
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]     0.0422      0.327      0.129      0.900      -0.687       0.772
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]     0.7196      0.299      2.407      0.037       0.054       1.386
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]     -0.9889      0.401     -2.466      0.033      -1.883      -0.095
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -1.9767      0.327     -6.037      0.000      -2.706      -1.247
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]       -0.6295      0.299     -2.106      0.061      -1.296       0.037
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.6248      0.299     -2.090      0.063      -1.291       0.041
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.3268      0.327     -0.998      0.342      -1.056       0.403
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -0.7444      0.401     -1.856      0.093      -1.638       0.149
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.2459      0.401      0.613      0.553      -0.648       1.140
==============================================================================
Omnibus:                        2.967   Durbin-Watson:                   2.076
Prob(Omnibus):                  0.227   Jarque-Bera (JB):                1.304
Skew:                           0.230   Prob(JB):                        0.521
Kurtosis:                       4.131   Cond. No.                         11.9
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/2466720807.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  KI67_pos_CTL04E["prop"] = KI67_pos_CTL04E["otsu_1"] / KI67_pos_CTL04E["total"]
/tmp/ipykernel_3702104/2466720807.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  KI67_pos_CTL04E["logit_prop"] = np.log(KI67_pos_CTL04E["prop"] / (1 - KI67_pos_CTL04E["prop"]))
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100 # The odds of being KI67-positive are increased/decreased by this percentage compared to DMSO.


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_KI67pos_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_3702104/4000860394.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


df = density_MKI67[density_MKI67.ImageName_ScanRegion_rep.isin(good_tissue_to_keep_limit)]
df = df[~df['ImageName_ScanRegion_rep'].isin(to_remove)]


fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['otsu_1']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['otsu_1'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['otsu_1']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['otsu_1'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='otsu_1', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('KI67+ area (um2) / organoid area (um2)', fontsize=15)
ax[1].set_ylabel('KI67+ area (um2) / organoid area (um2)', fontsize=15)

plt.savefig('../../../../endpoints_figures/MKI67_density_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/MKI67_density_per_condition.png', dpi=300, bbox_inches='tight')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['otsu_1', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


mask_file_df_mix_2 = mask_file_df_mix_2.merge(sample_sheet, left_on='ImageName_ScanRegion', right_on='ImageName_ScanRegion', how='left')


#n_nuclei.reset_index(inplace=True)
#n_nuclei.rename(columns={'index': 'ImageName'}, inplace=True)
n_nuclei = {i.replace('_channel_2_measures', ''):j for i, j in zip(n_nuclei.keys(), n_nuclei.values())}


mask_file_df_mix_2['organoid_area_um2'] = mask_file_df_mix_2['ImageName_ScanRegion_Rep'].map({i:j for i, j in zip(organoid_areas.index, organoid_areas['area'])}) * (px_size ** 2)
mask_file_df_mix_2.set_index('ImageName_ScanRegion_Rep', inplace=True)
mask_file_df_mix_2['n_nuclei'] = n_nuclei
mask_file_df_mix_2['area_um2'] = mask_file_df_mix_2['area'] * (px_size ** 2)


mask_file_df_mix_2['pos_area_over_n_nuclei'] = mask_file_df_mix_2['area_um2'] / mask_file_df_mix_2['n_nuclei']
mask_file_df_mix_2['pos_area_over_tot'] = mask_file_df_mix_2['area_um2'] / mask_file_df_mix_2['organoid_area_um2']


mask_file_df_mix_2['Line'] = mask_file_df_mix_2['Condition_Line'].apply(lambda x: x.split('_')[-1] if pd.notnull(x) else x)


#mask_file_df_mix_2.to_csv("/group/testa/Project/EndPoints/TPSSU/analysis/measurements_mix_2_ch0_MAP2.csv")


df = mask_file_df_mix_2.loc[[i for i in good_tissue_to_keep_limit if i in mask_file_df_mix_2.index]]
fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_n_nuclei']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_n_nuclei'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_n_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_n_nuclei']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_n_nuclei'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_n_nuclei', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('MAP2+ area (um2) / # nuclei')
ax[1].set_ylabel('MAP2+ area (um2) / # nuclei')

plt.savefig('../../../../endpoints_figures/MAP2_pos_area_over_n_nuclei_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/MAP2_pos_area_over_n_nuclei_per_condition.png', dpi=300, bbox_inches='tight')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_n_nuclei', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


mask_file_df_mix_2_CTL04E = mask_file_df_mix_2[mask_file_df_mix_2['Line'] == 'CTL04E']
mask_file_df_mix_2_CTL04E['Condition'] = mask_file_df_mix_2_CTL04E['Condition'].astype('category')
mask_file_df_mix_2_CTL04E["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_2_CTL04E["area_um2"] / mask_file_df_mix_2_CTL04E["n_nuclei"])
mask_file_df_mix_2_CTL04E['log_area_over_n_nuclei'].hist(bins = 10)

model_CTL04E = smf.ols("log_area_over_n_nuclei ~ C(Condition, Treatment(reference='DMSO'))",
                data=mask_file_df_mix_2_CTL04E,
                freq_weights=mask_file_df_mix_2_CTL04E["n_nuclei"]
                ).fit()

print(model_CTL04E.summary())

                              OLS Regression Results                              
==================================================================================
Dep. Variable:     log_area_over_n_nuclei   R-squared:                       0.437
Model:                                OLS   Adj. R-squared:                  0.081
Method:                     Least Squares   F-statistic:                     1.229
Date:                    Mon, 02 Mar 2026   Prob (F-statistic):              0.333
Time:                            15:08:59   Log-Likelihood:                -7.4707
No. Observations:                      32   AIC:                             40.94
Df Residuals:                          19   BIC:                             60.00
Df Model:                              12                                         
Covariance Type:                nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                 4.2615      0.280     15.196      0.000       3.675       4.849
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.3638      0.397      0.917      0.371      -0.466       1.194
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]     0.2776      0.362      0.767      0.453      -0.480       1.035
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]     -0.0173      0.362     -0.048      0.962      -0.775       0.740
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]     0.2152      0.362      0.594      0.559      -0.543       0.973
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.0009      0.486      0.002      0.999      -1.016       1.018
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]    -0.1143      0.362     -0.316      0.756      -0.872       0.643
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]      -0.4969      0.362     -1.372      0.186      -1.255       0.261
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.4489      0.362      1.240      0.230      -0.309       1.207
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.2118      0.362     -0.585      0.565      -0.970       0.546
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.1283      0.397     -0.323      0.750      -0.958       0.702
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]      0.0087      0.362      0.024      0.981      -0.749       0.766
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]     0.4233      0.486      0.872      0.394      -0.593       1.440
==============================================================================
Omnibus:                       26.781   Durbin-Watson:                   2.471
Prob(Omnibus):                  0.000   Jarque-Bera (JB):               85.509
Skew:                           1.559   Prob(JB):                     2.70e-19
Kurtosis:                      10.376   Cond. No.                         15.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/tmp/ipykernel_3702104/64246595.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_2_CTL04E['Condition'] = mask_file_df_mix_2_CTL04E['Condition'].astype('category')
/tmp/ipykernel_3702104/64246595.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_2_CTL04E["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_2_CTL04E["area_um2"] / mask_file_df_mix_2_CTL04E["n_nuclei"])
/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


mask_file_df_mix_2_CTL08A = mask_file_df_mix_2[mask_file_df_mix_2['Line'] == 'CTL08A']
mask_file_df_mix_2_CTL08A['Condition'] = mask_file_df_mix_2_CTL08A['Condition'].astype('category')
mask_file_df_mix_2_CTL08A["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_2_CTL08A["area_um2"] / mask_file_df_mix_2_CTL08A["n_nuclei"])
mask_file_df_mix_2_CTL08A['log_area_over_n_nuclei'].hist(bins = 10)

model_CTL08A = smf.ols("log_area_over_n_nuclei ~ C(Condition, Treatment(reference='DMSO'))",
                data=mask_file_df_mix_2_CTL08A,
                freq_weights=mask_file_df_mix_2_CTL08A["n_nuclei"]
                ).fit()

print(model_CTL08A.summary())

/tmp/ipykernel_3702104/4202280779.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_2_CTL08A['Condition'] = mask_file_df_mix_2_CTL08A['Condition'].astype('category')
/tmp/ipykernel_3702104/4202280779.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  mask_file_df_mix_2_CTL08A["log_area_over_n_nuclei"] = np.log(mask_file_df_mix_2_CTL08A["area_um2"] / mask_file_df_mix_2_CTL08A["n_nuclei"])

                              OLS Regression Results                              
==================================================================================
Dep. Variable:     log_area_over_n_nuclei   R-squared:                       0.856
Model:                                OLS   Adj. R-squared:                  0.782
Method:                     Least Squares   F-statistic:                     11.48
Date:                    Mon, 02 Mar 2026   Prob (F-statistic):           5.90e-08
Time:                            15:09:00   Log-Likelihood:                 14.263
No. Observations:                      42   AIC:                             1.474
Df Residuals:                          27   BIC:                             27.54
Df Model:                              14                                         
Covariance Type:                nonrobust                                         
=========================================================================================================================
                                                            coef    std err          t      P>|t|      [0.025      0.975]
-------------------------------------------------------------------------------------------------------------------------
Intercept                                                 4.2056      0.124     33.897      0.000       3.951       4.460
C(Condition, Treatment(reference='DMSO'))[T.ANDR_AG]      0.1453      0.175      0.828      0.415      -0.215       0.505
C(Condition, Treatment(reference='DMSO'))[T.ANDR_INH]     0.6053      0.175      3.450      0.002       0.245       0.965
C(Condition, Treatment(reference='DMSO'))[T.ARYL_AG]      0.2968      0.164      1.808      0.082      -0.040       0.634
C(Condition, Treatment(reference='DMSO'))[T.ARYL_INH]     0.3291      0.175      1.876      0.072      -0.031       0.689
C(Condition, Treatment(reference='DMSO'))[T.ESTR_AG]      0.5082      0.196      2.590      0.015       0.106       0.911
C(Condition, Treatment(reference='DMSO'))[T.ESTR_INH]     0.3283      0.196      1.674      0.106      -0.074       0.731
C(Condition, Treatment(reference='DMSO'))[T.GC_AG]       -0.0797      0.196     -0.406      0.688      -0.482       0.323
C(Condition, Treatment(reference='DMSO'))[T.GC_INH]       0.0141      0.175      0.080      0.937      -0.346       0.374
C(Condition, Treatment(reference='DMSO'))[T.LX_AG]        0.4626      0.175      2.636      0.014       0.103       0.823
C(Condition, Treatment(reference='DMSO'))[T.LX_INH]      -0.0925      0.196     -0.472      0.641      -0.495       0.310
C(Condition, Treatment(reference='DMSO'))[T.RET_AG]       1.4620      0.175      8.332      0.000       1.102       1.822
C(Condition, Treatment(reference='DMSO'))[T.RET_INH]     -0.0196      0.175     -0.112      0.912      -0.380       0.340
C(Condition, Treatment(reference='DMSO'))[T.THYR_AG]     -0.1537      0.175     -0.876      0.389      -0.514       0.206
C(Condition, Treatment(reference='DMSO'))[T.THYR_INH]    -0.2600      0.175     -1.482      0.150      -0.620       0.100
==============================================================================
Omnibus:                        4.498   Durbin-Watson:                   2.461
Prob(Omnibus):                  0.106   Jarque-Bera (JB):                3.653
Skew:                          -0.718   Prob(JB):                        0.161
Kurtosis:                       3.164   Cond. No.                         15.5
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.

/group/testa/Users/alessia.valenti/NewImageAnalysis/.local/lib/python3.10/site-packages/statsmodels/base/model.py:130: ValueWarning: unknown kwargs ['freq_weights']
  warnings.warn(msg, ValueWarning)


resid_CTL08A = model_CTL08A.resid

stats.probplot(resid_CTL08A, dist="norm", plot=plt)
plt.show()


resid_CTL04E = model_CTL04E.resid

stats.probplot(resid_CTL04E, dist="norm", plot=plt)
plt.show()


pvals_CTL08A = model_CTL08A.pvalues[1:]  # exclude intercept
corrected_pvals_CTL08A = multipletests(pvals_CTL08A, method='fdr_bh')[1]

df_results_CTL08A = pd.concat([model_CTL08A.params, pd.Series(corrected_pvals_CTL08A, index=model_CTL08A.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL08A.columns = ['intercept', 'pvalue']


pvals_CTL04E = model_CTL04E.pvalues[1:]  # exclude intercept
corrected_pvals_CTL04E = multipletests(pvals_CTL04E, method='fdr_bh')[1]

df_results_CTL04E = pd.concat([model_CTL04E.params, pd.Series(corrected_pvals_CTL04E, index=model_CTL04E.params.index[1:])], axis = 1).iloc[1:]
df_results_CTL04E.columns = ['intercept', 'pvalue']


pvals = pd.concat([df_results_CTL08A['pvalue'], df_results_CTL04E['pvalue']], axis = 1)
pvals.columns = ['CTL08A', 'CTL04E']
pvals.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in pvals.index]
pvals


intercepts = pd.concat([df_results_CTL08A['intercept'], df_results_CTL04E['intercept']], axis = 1)
intercepts.columns = ['CTL08A', 'CTL04E']
intercepts.index = [i.split('C(Condition, Treatment(reference=\'DMSO\'))[T.')[1].replace(']', '') for i in intercepts.index]
intercepts = (np.exp(intercepts) - 1) * 100 # The percentage increase/decrease in MAP2+ area per nuclei compared to DMSO.
intercepts


fig, ax = plt.subplots(figsize = (4,7))
intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")
intercepts = intercepts[pvals < 0.05].fillna('')
sns.heatmap(pvals, annot=intercepts, fmt='', cmap='Greens_r', cbar_kws={'label': 'p-value'}, vmin=0, vmax=0.05, ax = ax)
plt.title('Condition vs DMSO\n')
plt.savefig('../../../../endpoints_figures/endpoints_organoids_MAP2_n_nuclei_OLS_test.png', dpi=300, bbox_inches='tight')

/tmp/ipykernel_3702104/293039614.py:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.
  intercepts = intercepts.applymap(lambda x: f"{x:+.1f}%" if pd.notnull(x) else "")


df = mask_file_df_mix_2.loc[[i for i in good_tissue_to_keep_limit if i in mask_file_df_mix_2.index]]
fig, ax = plt.subplots(1, 2, figsize=(20, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['pos_area_over_tot'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['pos_area_over_tot']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['pos_area_over_tot'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='pos_area_over_tot', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('MAP2+ area (um2) / organoid area (um2)', fontsize=15)
ax[1].set_ylabel('MAP2+ area (um2) / organoid area (um2)', fontsize=15)

plt.savefig('../../../../endpoints_figures/MAP2_pos_area_over_tot_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/MAP2_pos_area_over_tot_per_condition.png', dpi=300, bbox_inches='tight')


df[df.Condition.isin(['RET_AG', 'DMSO'])][['pos_area_over_tot', 'Condition']].sort_values(by='Condition', ascending=False).groupby('Condition').median()


n_nuclei_tot_pos_MKI67_otsu1 = {k: v['otsu_1'] for k, v in n_nuclei_tot_pos_MKI67.items() if 'otsu_1' in v}


n_nuclei_tot_pos_MKI67_otsu1

{'20240424_manuel_lessi_0142_ScanRegion2_rep_0': 157,
 '20240424_manuel_lessi_0142_ScanRegion2_rep_2': 64,
 '20240424_manuel_lessi_0138_ScanRegion1_rep_2': 908,
 '20240424_manuel_lessi_0140_ScanRegion4_rep_1': 755,
 '20240424_manuel_lessi_0140_ScanRegion5_rep_2': 1063,
 '20240424_manuel_lessi_0139_ScanRegion3_rep_1': 1135,
 '20240424_manuel_lessi_0140_ScanRegion4_rep_2': 701,
 '20240424_manuel_lessi_0138_ScanRegion2_rep_0': 1373,
 '20240424_manuel_lessi_0143_ScanRegion0_rep_2': 499,
 '20240424_manuel_lessi_0139_ScanRegion4_rep_1': 693,
 '20240424_manuel_lessi_0139_ScanRegion4_rep_0': 509,
 '20240424_manuel_lessi_0137_ScanRegion4_rep_0': 607,
 '20240424_manuel_lessi_0140_ScanRegion1_rep_0': 210,
 '20240424_manuel_lessi_0137_ScanRegion0_rep_0': 688,
 '20240424_manuel_lessi_0140_ScanRegion5_rep_0': 376,
 '20240424_manuel_lessi_0138_ScanRegion2_rep_1': 1570,
 '20240424_manuel_lessi_0138_ScanRegion3_rep_2': 2686,
 '20240424_manuel_lessi_0137_ScanRegion5_rep_1': 760,
 '20240424_manuel_lessi_0139_ScanRegion3_rep_2': 812,
 '20240424_manuel_lessi_0137_ScanRegion2_rep_1': 108,
 '20240424_manuel_lessi_0138_ScanRegion4_rep_0': 756,
 '20240424_manuel_lessi_0137_ScanRegion1_rep_1': 892,
 '20240424_manuel_lessi_0139_ScanRegion2_rep_2': 22,
 '20240424_manuel_lessi_0137_ScanRegion4_rep_1': 1168,
 '20240424_manuel_lessi_0139_ScanRegion3_rep_0': 1014,
 '20240424_manuel_lessi_0138_ScanRegion4_rep_2': 107,
 '20240424_manuel_lessi_0137_ScanRegion3_rep_0': 159,
 '20240424_manuel_lessi_0143_ScanRegion1_rep_1': 985,
 '20240424_manuel_lessi_0137_ScanRegion5_rep_0': 1199,
 '20240424_manuel_lessi_0139_ScanRegion0_rep_0': 155,
 '20240424_manuel_lessi_0138_ScanRegion0_rep_2': 212,
 '20240424_manuel_lessi_0141_ScanRegion3_rep_0': 2127,
 '20240424_manuel_lessi_0143_ScanRegion0_rep_0': 388,
 '20240424_manuel_lessi_0138_ScanRegion3_rep_0': 1025,
 '20240424_manuel_lessi_0141_ScanRegion2_rep_1': 660,
 '20240424_manuel_lessi_0141_ScanRegion2_rep_2': 1279,
 '20240424_manuel_lessi_0139_ScanRegion1_rep_1': 1216,
 '20240424_manuel_lessi_0139_ScanRegion1_rep_0': 1086,
 '20240424_manuel_lessi_0140_ScanRegion3_rep_0': 618,
 '20240424_manuel_lessi_0140_ScanRegion1_rep_1': 1262,
 '20240424_manuel_lessi_0138_ScanRegion4_rep_1': 306,
 '20240424_manuel_lessi_0139_ScanRegion0_rep_1': 216,
 '20240424_manuel_lessi_0137_ScanRegion1_rep_0': 757,
 '20240424_manuel_lessi_0138_ScanRegion2_rep_2': 1845,
 '20240424_manuel_lessi_0138_ScanRegion5_rep_2': 634,
 '20240424_manuel_lessi_0140_ScanRegion0_rep_2': 1901,
 '20240424_manuel_lessi_0143_ScanRegion1_rep_0': 1273,
 '20240424_manuel_lessi_0139_ScanRegion0_rep_2': 617,
 '20240424_manuel_lessi_0138_ScanRegion0_rep_0': 1008,
 '20240424_manuel_lessi_0141_ScanRegion2_rep_0': 623,
 '20240424_manuel_lessi_0143_ScanRegion0_rep_1': 975,
 '20240424_manuel_lessi_0137_ScanRegion2_rep_0': 662,
 '20240424_manuel_lessi_0140_ScanRegion0_rep_1': 1066,
 '20240424_manuel_lessi_0138_ScanRegion0_rep_1': 29,
 '20240424_manuel_lessi_0140_ScanRegion1_rep_2': 336,
 '20240424_manuel_lessi_0137_ScanRegion3_rep_2': 270,
 '20240424_manuel_lessi_0138_ScanRegion1_rep_1': 651,
 '20240424_manuel_lessi_0140_ScanRegion3_rep_1': 257,
 '20240424_manuel_lessi_0137_ScanRegion1_rep_2': 845,
 '20240424_manuel_lessi_0137_ScanRegion3_rep_1': 321,
 '20240424_manuel_lessi_0140_ScanRegion4_rep_0': 899,
 '20240424_manuel_lessi_0140_ScanRegion0_rep_0': 2048,
 '20240424_manuel_lessi_0142_ScanRegion2_rep_1': 44,
 '20240424_manuel_lessi_0138_ScanRegion3_rep_3': 299,
 '20240424_manuel_lessi_0139_ScanRegion2_rep_1': 229,
 '20240424_manuel_lessi_0140_ScanRegion5_rep_1': 71,
 '20240424_manuel_lessi_0138_ScanRegion5_rep_0': 1362,
 '20240424_manuel_lessi_0139_ScanRegion2_rep_0': 584,
 '20240424_manuel_lessi_0140_ScanRegion3_rep_2': 551,
 '20240424_manuel_lessi_0141_ScanRegion3_rep_1': 342,
 '20240424_manuel_lessi_0138_ScanRegion5_rep_1': 845,
 '20240424_manuel_lessi_0138_ScanRegion3_rep_1': 840,
 '20240424_manuel_lessi_0138_ScanRegion1_rep_0': 999,
 '20240424_manuel_lessi_0140_ScanRegion2_rep_0': 248}


df['MKI67+'] = df.reset_index()['ImageName_ScanRegion_Rep'].map(n_nuclei_tot_pos_MKI67_otsu1).values


df["MKI67+_MAP2_ratio"] = df['MKI67+'] / df['area_um2']


fig, ax = plt.subplots(1, 2, figsize=(25, 5))
for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL08A') & 
                                 (df['Condition'] == cond)]['MKI67+_MAP2_ratio']
    box = ax[0].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
        # Add stripplot for CTL08A (single points per box)

    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL08A')]['MKI67+_MAP2_ratio'].median()
    ax[0].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[(df['Line'] == 'CTL08A')],
    y='MKI67+_MAP2_ratio', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[0], size=8
)

for i, cond in enumerate(hormonal_conditions):
    data = df[(df['Line'] == 'CTL04E') & 
                                 (df['Condition'] == cond)]['MKI67+_MAP2_ratio']
    box = ax[1].boxplot(data, positions=[i], patch_artist=True, widths=.8)
    for patch in box['boxes']:
        patch.set_facecolor(color_palette[cond])
        box['medians'][0].set_color('black')
    dmso_median = df[(df['Condition'] == 'DMSO') & 
                                       (df['Line'] == 'CTL04E')]['MKI67+_MAP2_ratio'].median()
    ax[1].axhline(dmso_median, color='red', linestyle='--', linewidth=.7, alpha=0.7)

sns.stripplot(
    data=df[df['Line'] == 'CTL04E'],
    y='MKI67+_MAP2_ratio', x='Condition', order=hormonal_conditions, color='black', alpha=0.5, jitter=False, ax=ax[1], size=8
)

_ = ax[0].set_xticks(range(len(hormonal_conditions)))
_ = ax[0].set_xticklabels(hormonal_conditions, rotation=90)

_ = ax[1].set_xticks(range(len(hormonal_conditions)))
_ = ax[1].set_xticklabels(hormonal_conditions, rotation=90)

ax[0].set_title('CTL08A')
ax[1].set_title('CTL04E')

ax[0].set_ylabel('MKI67+/MAP2 ratio (nuclei/um2)')
ax[1].set_ylabel('MKI67+/MAP2 ratio (nuclei/um2)')

plt.savefig('../../../../endpoints_figures/MKI67+_MAP2_ratio_per_condition.pdf', dpi=300, bbox_inches='tight')
plt.savefig('../../../../endpoints_figures/MKI67+_MAP2_ratio_per_condition.png', dpi=300, bbox_inches='tight')

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max
0	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_0_c...	41353242.0	1	2417.670006	1451.0	24120.0
1	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_1_c...	16657221.0	1	3091.305189	1683.0	18027.0
2	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_2_c...	44113333.0	1	3377.073590	1493.0	27952.0
3	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_0_c...	10098868.0	1	2645.539375	1110.0	27468.0
4	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_1_c...	7030992.0	1	3937.014572	1941.0	25144.0
...	...	...	...	...	...	...	...
275	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion2_rep_1_c...	23124873.0	1	4259.092122	2134.0	44177.0
276	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion2_rep_2_c...	3373772.0	1	5777.220379	2861.0	33473.0
277	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_0_c...	10606818.0	1	6209.021854	3028.0	52453.0
278	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_1_c...	27412715.0	1	3358.864704	1478.0	28030.0
279	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_2_c...	34550995.0	1	3780.418198	1524.0	49946.0

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max	OriginalImageName	ImageName_ScanRegion	ImageName_ScanRegion_Rep
0	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_0_c...	41353242.0	1	2417.670006	1451.0	24120.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_0
1	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_1_c...	16657221.0	1	3091.305189	1683.0	18027.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_1
2	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_2_c...	44113333.0	1	3377.073590	1493.0	27952.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_2
3	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_0_c...	10098868.0	1	2645.539375	1110.0	27468.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion1	20240424_manuel_lessi_0134_ScanRegion1_rep_0
4	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_1_c...	7030992.0	1	3937.014572	1941.0	25144.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion1	20240424_manuel_lessi_0134_ScanRegion1_rep_1
...	...	...	...	...	...	...	...	...	...	...
275	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion2_rep_1_c...	23124873.0	1	4259.092122	2134.0	44177.0	20240424_manuel_lessi_0144	20240424_manuel_lessi_0144_ScanRegion2	20240424_manuel_lessi_0144_ScanRegion2_rep_1
276	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion2_rep_2_c...	3373772.0	1	5777.220379	2861.0	33473.0	20240424_manuel_lessi_0144	20240424_manuel_lessi_0144_ScanRegion2	20240424_manuel_lessi_0144_ScanRegion2_rep_2
277	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_0_c...	10606818.0	1	6209.021854	3028.0	52453.0	20240424_manuel_lessi_0144	20240424_manuel_lessi_0144_ScanRegion3	20240424_manuel_lessi_0144_ScanRegion3_rep_0
278	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_1_c...	27412715.0	1	3358.864704	1478.0	28030.0	20240424_manuel_lessi_0144	20240424_manuel_lessi_0144_ScanRegion3	20240424_manuel_lessi_0144_ScanRegion3_rep_1
279	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0144_ScanRegion3_rep_2_c...	34550995.0	1	3780.418198	1524.0	49946.0	20240424_manuel_lessi_0144	20240424_manuel_lessi_0144_ScanRegion3	20240424_manuel_lessi_0144_ScanRegion3_rep_2

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max	OriginalImageName	ImageName_ScanRegion	ImageName_ScanRegion_Rep
0	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_0_c...	41353242.0	1	2417.670006	1451.0	24120.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_0
1	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_1_c...	16657221.0	1	3091.305189	1683.0	18027.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_1
2	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion0_rep_2_c...	44113333.0	1	3377.073590	1493.0	27952.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	20240424_manuel_lessi_0134_ScanRegion0_rep_2
3	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_0_c...	10098868.0	1	2645.539375	1110.0	27468.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion1	20240424_manuel_lessi_0134_ScanRegion1_rep_0
4	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0134_ScanRegion1_rep_1_c...	7030992.0	1	3937.014572	1941.0	25144.0	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion1	20240424_manuel_lessi_0134_ScanRegion1_rep_1
...	...	...	...	...	...	...	...	...	...	...
253	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion4_rep_0_c...	31563732.0	1	5826.471794	2338.0	65535.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion4	20240424_manuel_lessi_0128_ScanRegion4_rep_0
254	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion4_rep_1_c...	15937774.0	1	4450.546162	1907.0	34600.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion4	20240424_manuel_lessi_0128_ScanRegion4_rep_1
255	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_0_c...	27625720.0	1	8458.966141	3148.0	65535.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_0
256	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_1_c...	24213189.0	1	8076.440269	3291.0	64452.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_1
257	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_2_c...	40133175.0	1	4824.591142	1926.0	50550.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_2

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max	OriginalImageName	ImageName_ScanRegion	ImageName_ScanRegion_Rep
63	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_0_c...	25216880.0	1	2897.342427	1595.0	46841.0	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion0	20240424_manuel_lessi_0138_ScanRegion0_rep_0
64	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_1_c...	783450.0	1	5758.093586	2353.0	28128.0	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion0	20240424_manuel_lessi_0138_ScanRegion0_rep_1
65	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_2_c...	9406872.0	1	2427.271453	1434.0	22097.0	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion0	20240424_manuel_lessi_0138_ScanRegion0_rep_2
66	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion1_rep_0_c...	19764267.0	1	4312.851140	1931.0	46239.0	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion1	20240424_manuel_lessi_0138_ScanRegion1_rep_0
67	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion1_rep_1_c...	16905853.0	1	5440.278854	1960.0	53194.0	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion1	20240424_manuel_lessi_0138_ScanRegion1_rep_1
...	...	...	...	...	...	...	...	...	...	...
225	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0140_ScanRegion4_rep_1_c...	31837996.0	1	3904.760504	1749.0	59013.0	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion4	20240424_manuel_lessi_0140_ScanRegion4_rep_1
226	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0140_ScanRegion4_rep_2_c...	18872105.0	1	3218.488803	1461.0	31570.0	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion4	20240424_manuel_lessi_0140_ScanRegion4_rep_2
227	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0140_ScanRegion5_rep_0_c...	26246594.0	1	5094.892965	2251.0	65058.0	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion5	20240424_manuel_lessi_0140_ScanRegion5_rep_0
228	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0140_ScanRegion5_rep_1_c...	1893364.0	1	10712.595047	4554.0	42993.0	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion5	20240424_manuel_lessi_0140_ScanRegion5_rep_1
229	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0140_ScanRegion5_rep_2_c...	24276964.0	1	3060.892932	1587.0	48985.0	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion5	20240424_manuel_lessi_0140_ScanRegion5_rep_2

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max
0	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_0_c...	4101511.0	1	3193.621243	760.0	58222.0
1	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_1_c...	364102.0	1	1737.696456	799.0	32870.0
2	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion0_rep_2_c...	1211261.0	1	2790.889845	666.0	55530.0
3	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion1_rep_0_c...	5725447.0	1	2689.380828	667.0	65535.0
4	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0138_ScanRegion1_rep_1_c...	3492983.0	1	2311.704404	652.0	65535.0
...	...	...	...	...	...	...	...
275	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0147_ScanRegion0_rep_0_c...	28772264.0	1	2396.070626	1210.0	46386.0
276	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0147_ScanRegion0_rep_1_c...	65092576.0	1	1752.924324	920.0	65535.0
277	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0147_ScanRegion1_rep_0_c...	22241252.0	1	2317.127770	873.0	63830.0
278	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0147_ScanRegion1_rep_1_c...	21330335.0	1	2837.997036	1092.0	65535.0
279	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0147_ScanRegion1_rep_2_c...	28381819.0	1	1679.860053	669.0	57590.0

Load manual checks¶

Load sample sheet¶

Load measurements file names¶

Area organoids¶

Statistical test - Area¶

Compute density¶

Number of nuclei per condition and line¶

Statistical test - Number of nuclei¶

Plot of density¶

Statistical test - Density¶

MIX 1¶

Channel 2 - SOX2¶

Thresholding¶

Plots¶

Percentages¶

Statistical testing for SOX2+ proportions¶

SOX2+ / organoid area¶

Channel 0 - TUJ1¶

Plot positive area/number of nuclei¶

Statistical testing for TUJ1 area / number of nuclei¶

Plot positive area/total area¶

Channel 2 - SOX2 - Area¶

Plot positive area/number of nuclei¶

Plot positive area/total area¶

SOX2 / TUJ1 ratio¶

MIX 2¶

Channel 2 - MKI67¶

Thresholding¶

Plots¶

Percentages¶

Statistical testing for KI67+ proportions¶

MKI67+ / organoid area¶

Channel 0 - MAP2¶

Plot positive area/number of nuclei¶

Statistical testing for MAP2 area / number of nuclei¶

Plot positive area/total area¶

MKI67 / MAP2 ratio¶

	ImageName_ScanRegion_Rep	ImageName_ScanRegion
0	20240424_manuel_lessi_0147_ScanRegion1_rep_1	20240424_manuel_lessi_0147_ScanRegion1
1	20240424_manuel_lessi_0139_ScanRegion4_rep_1	20240424_manuel_lessi_0139_ScanRegion4
2	20240424_manuel_lessi_0132_ScanRegion3_rep_2	20240424_manuel_lessi_0132_ScanRegion3
3	20240424_manuel_lessi_0138_ScanRegion0_rep_1	20240424_manuel_lessi_0138_ScanRegion0
4	20240424_manuel_lessi_0129_ScanRegion1_rep_2	20240424_manuel_lessi_0129_ScanRegion1
...	...	...
240	20240424_manuel_lessi_0132_ScanRegion4_rep_1	20240424_manuel_lessi_0132_ScanRegion4
241	20240424_manuel_lessi_0135_ScanRegion0_rep_2	20240424_manuel_lessi_0135_ScanRegion0
242	20240424_manuel_lessi_0141_ScanRegion4_rep_1	20240424_manuel_lessi_0141_ScanRegion4
243	20240424_manuel_lessi_0129_ScanRegion2_rep_0	20240424_manuel_lessi_0129_ScanRegion2
244	20240424_manuel_lessi_0132_ScanRegion1_rep_0	20240424_manuel_lessi_0132_ScanRegion1

	Path	Scan Area	Condition	Line	OPA	Paraffin Block ID	MIX	ImageName	ImageName_ScanRegion	Condition_Line
0	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	ESTR_AG	CTL04E	12	29	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion0	ESTR_AG_CTL04E
1	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	ESTR_AG	CTL08A	12	30	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion1	ESTR_AG_CTL08A
2	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	ESTR_INH	CTL04E	12	31	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion2	ESTR_INH_CTL04E
3	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	ANDR_AG	CTL04E	12	33	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion3	ANDR_AG_CTL04E
4	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	ESTR_INH	CTL08A	12	32	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion4	ESTR_INH_CTL08A
5	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	ANDR_AG	CTL08A	12	34	1	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	ANDR_AG_CTL08A
7	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	ARYL_INH	CTL08A	13	40	1	20240424_manuel_lessi_0129	20240424_manuel_lessi_0129_ScanRegion1	ARYL_INH_CTL08A
8	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	ARYL_INH	CTL04E	13	39	1	20240424_manuel_lessi_0129	20240424_manuel_lessi_0129_ScanRegion2	ARYL_INH_CTL04E
9	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	ARYL_AG	CTL08A	13	38	1	20240424_manuel_lessi_0129	20240424_manuel_lessi_0129_ScanRegion3	ARYL_AG_CTL08A
11	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	ARYL_AG	CTL04E	13	37	1	20240424_manuel_lessi_0129	20240424_manuel_lessi_0129_ScanRegion5	ARYL_AG_CTL04E
12	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	LX_AG	CTL04E	14	41	1	20240424_manuel_lessi_0130	20240424_manuel_lessi_0130_ScanRegion0	LX_AG_CTL04E
13	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	GC_AG	CTL08A	14	46	1	20240424_manuel_lessi_0130	20240424_manuel_lessi_0130_ScanRegion1	GC_AG_CTL08A
14	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	LX_AG	CTL08A	14	42	1	20240424_manuel_lessi_0130	20240424_manuel_lessi_0130_ScanRegion2	LX_AG_CTL08A
15	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	LX_INH	CTL04E	14	43	1	20240424_manuel_lessi_0130	20240424_manuel_lessi_0130_ScanRegion3	LX_INH_CTL04E
16	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	LX_INH	CTL08A	14	44	1	20240424_manuel_lessi_0130	20240424_manuel_lessi_0130_ScanRegion4	LX_INH_CTL08A
17	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	GC_INH	CTL04E	15	47	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion0	GC_INH_CTL04E
18	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	THYR_INH	CTL04E	15	51	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion1	THYR_INH_CTL04E
19	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	THYR_AG	CTL08A	15	50	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion2	THYR_AG_CTL08A
20	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	GC_INH	CTL08A	15	48	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion3	GC_INH_CTL08A
21	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	THYR_AG	CTL04E	15	49	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion4	THYR_AG_CTL04E
22	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	THYR_INH	CTL08A	15	52	1	20240424_manuel_lessi_0131	20240424_manuel_lessi_0131_ScanRegion5	THYR_INH_CTL08A
23	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	DMSO	CTL04E	16	57	1	20240424_manuel_lessi_0132	20240424_manuel_lessi_0132_ScanRegion4	DMSO_CTL04E
24	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	DMSO	CTL08A	16	58	1	20240424_manuel_lessi_0132	20240424_manuel_lessi_0132_ScanRegion5	DMSO_CTL08A
25	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	RET_AG	CTL08A	17	64	1	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion4	RET_AG_CTL08A
26	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	RET_INH	CTL04E	18	65	1	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion0	RET_INH_CTL04E
27	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	RET_INH	CTL08A	18	66	1	20240424_manuel_lessi_0134	20240424_manuel_lessi_0134_ScanRegion2	RET_INH_CTL08A
28	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	ESTR_AG	CTL04E	12	29	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion0	ESTR_AG_CTL04E
29	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	ANDR_AG	CTL08A	12	34	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion1	ANDR_AG_CTL08A
30	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	ESTR_AG	CTL08A	12	30	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion2	ESTR_AG_CTL08A
31	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	ESTR_INH	CTL04E	12	31	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion3	ESTR_INH_CTL04E
32	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	ANDR_AG	CTL04E	12	33	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion4	ANDR_AG_CTL04E
33	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	ESTR_INH	CTL08A	12	32	2	20240424_manuel_lessi_0137	20240424_manuel_lessi_0137_ScanRegion5	ESTR_INH_CTL08A
34	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	ANDR_INH	CTL08A	13	36	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion0	ANDR_INH_CTL08A
35	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	ANDR_INH	CTL04E	13	35	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion1	ANDR_INH_CTL04E
36	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	ARYL_INH	CTL04E	13	39	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion2	ARYL_INH_CTL04E
37	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	ARYL_AG	CTL08A	13	38	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion3	ARYL_AG_CTL08A
38	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	ARYL_INH	CTL08A	13	40	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion4	ARYL_INH_CTL08A
39	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	ARYL_AG	CTL04E	13	37	2	20240424_manuel_lessi_0138	20240424_manuel_lessi_0138_ScanRegion5	ARYL_AG_CTL04E
40	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	LX_AG	CTL08A	14	42	2	20240424_manuel_lessi_0139	20240424_manuel_lessi_0139_ScanRegion0	LX_AG_CTL08A
41	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	LX_INH	CTL08A	14	44	2	20240424_manuel_lessi_0139	20240424_manuel_lessi_0139_ScanRegion1	LX_INH_CTL08A
42	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	LX_AG	CTL04E	14	41	2	20240424_manuel_lessi_0139	20240424_manuel_lessi_0139_ScanRegion2	LX_AG_CTL04E
43	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	LX_INH	CTL04E	14	43	2	20240424_manuel_lessi_0139	20240424_manuel_lessi_0139_ScanRegion3	LX_INH_CTL04E
44	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	GC_AG	CTL08A	14	46	2	20240424_manuel_lessi_0139	20240424_manuel_lessi_0139_ScanRegion4	GC_AG_CTL08A
45	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	GC_INH	CTL08A	15	48	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion0	GC_INH_CTL08A
46	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	GC_INH	CTL04E	15	47	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion1	GC_INH_CTL04E
47	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	THYR_INH	CTL04E	15	51	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion2	THYR_INH_CTL04E
48	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	THYR_AG	CTL04E	15	49	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion3	THYR_AG_CTL04E
49	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion4	THYR_INH	CTL08A	15	52	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion4	THYR_INH_CTL08A
50	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion5	THYR_AG	CTL08A	15	50	2	20240424_manuel_lessi_0140	20240424_manuel_lessi_0140_ScanRegion5	THYR_AG_CTL08A
51	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	DMSO	CTL08A	16	58	2	20240424_manuel_lessi_0141	20240424_manuel_lessi_0141_ScanRegion2	DMSO_CTL08A
52	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion3	DMSO	CTL04E	16	57	2	20240424_manuel_lessi_0141	20240424_manuel_lessi_0141_ScanRegion3	DMSO_CTL04E
53	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion2	RET_AG	CTL08A	17	64	2	20240424_manuel_lessi_0142	20240424_manuel_lessi_0142_ScanRegion2	RET_AG_CTL08A
54	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion0	RET_INH	CTL08A	18	66	2	20240424_manuel_lessi_0143	20240424_manuel_lessi_0143_ScanRegion0	RET_INH_CTL08A
55	T:\Project\EndPoints\TPSSU\Pictures\20240424_m...	ScanRegion1	RET_INH	CTL04E	18	65	2	20240424_manuel_lessi_0143	20240424_manuel_lessi_0143_ScanRegion1	RET_INH_CTL04E

	level_0	level_1	area	label	intensity_mean	intensity_min	intensity_max	OriginalImageName	ImageName_ScanRegion	ImageName_ScanRegion_Rep
19	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0133_ScanRegion0_rep_0_c...	21490093.0	1	3839.355973	1168.0	38274.0	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion0	20240424_manuel_lessi_0133_ScanRegion0_rep_0
20	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0133_ScanRegion0_rep_1_c...	14199055.0	1	4477.197476	1226.0	46860.0	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion0	20240424_manuel_lessi_0133_ScanRegion0_rep_1
21	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0133_ScanRegion0_rep_2_c...	15755642.0	1	3759.473544	1092.0	43784.0	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion0	20240424_manuel_lessi_0133_ScanRegion0_rep_2
22	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0133_ScanRegion1_rep_0_c...	1037489.0	1	2031.997964	957.0	21498.0	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion1	20240424_manuel_lessi_0133_ScanRegion1_rep_0
23	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0133_ScanRegion1_rep_1_c...	2023185.0	1	3780.785030	1512.0	38018.0	20240424_manuel_lessi_0133	20240424_manuel_lessi_0133_ScanRegion1	20240424_manuel_lessi_0133_ScanRegion1_rep_1
...	...	...	...	...	...	...	...	...	...	...
270	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion4_rep_0_c...	16244663.0	1	4090.208776	1313.0	48739.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion4	20240424_manuel_lessi_0128_ScanRegion4_rep_0
271	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion4_rep_1_c...	7057712.0	1	4113.493459	1235.0	42141.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion4	20240424_manuel_lessi_0128_ScanRegion4_rep_1
272	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_0_c...	12963431.0	1	5394.798945	1568.0	44306.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_0
273	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_1_c...	10831979.0	1	4610.981995	1604.0	40226.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_1
274	/group/testa/Project/EndPoints/TPSSU/analysis/...	20240424_manuel_lessi_0128_ScanRegion5_rep_2_c...	17819211.0	1	3234.373585	1320.0	37653.0	20240424_manuel_lessi_0128	20240424_manuel_lessi_0128_ScanRegion5	20240424_manuel_lessi_0128_ScanRegion5_rep_2

	area
20240424_manuel_lessi_0141_ScanRegion1_rep_0	48618374
20240424_manuel_lessi_0131_ScanRegion0_rep_2	36008220
20240424_manuel_lessi_0133_ScanRegion4_rep_0	8422522
20240424_manuel_lessi_0143_ScanRegion2_rep_1	61481135
20240424_manuel_lessi_0147_ScanRegion0_rep_1	162545379
...	...
20240424_manuel_lessi_0129_ScanRegion1_rep_0	26572184
20240424_manuel_lessi_0129_ScanRegion0_rep_0	9292198
20240424_manuel_lessi_0142_ScanRegion1_rep_2	38017446
20240424_manuel_lessi_0129_ScanRegion2_rep_1	29459387
20240424_manuel_lessi_0134_ScanRegion4_rep_1	22517768

	CTL08A	CTL04E
ANDR_AG	0.503368	0.959467
ANDR_INH	0.003224	0.674231
ARYL_AG	0.048640	0.033257
ARYL_INH	0.007327	0.935059
ESTR_AG	0.004118	0.306303
ESTR_INH	0.264495	0.284239
GC_AG	0.203314	NaN
GC_INH	0.224817	0.216278
LX_AG	0.007327	0.332531
LX_INH	0.084566	0.122681
RET_AG	0.000680	NaN
RET_INH	0.339600	0.183886
THYR_AG	0.007327	0.288888
THYR_INH	0.674887	0.047296

	CTL08A	CTL04E
ANDR_AG	-24.170411	1.902158
ANDR_INH	-81.880094	26.198362
ARYL_AG	-54.900314	188.387416
ARYL_INH	-68.882331	-5.911741
ESTR_AG	-77.089349	66.950283
ESTR_INH	-41.627377	65.228707
GC_AG	-47.670945	NaN
GC_INH	-41.557494	78.932108
LX_AG	-68.655867	-32.456484
LX_INH	-57.312929	111.427435
RET_AG	-80.687425	NaN
RET_INH	-33.158847	90.499384
THYR_AG	-68.917410	60.069424
THYR_INH	-14.742162	-71.345140

	CTL08A	CTL04E
ANDR_AG	0.403765	0.660794
ANDR_INH	0.000418	0.777295
ARYL_AG	0.035865	0.259707
ARYL_INH	0.005151	0.777295
ESTR_AG	0.003083	0.777295
ESTR_INH	0.222476	0.777295
GC_AG	0.222476	NaN
GC_INH	0.222476	0.383899
LX_AG	0.005744	0.104285
LX_INH	0.222476	0.383899
RET_AG	0.000002	NaN
RET_INH	0.403765	0.643285
THYR_AG	0.035865	0.660794
THYR_INH	0.869907	0.104285

	CTL08A	CTL04E
ANDR_AG	4.879720e-01	0.209006
ANDR_INH	2.281347e-04	0.262176
ARYL_AG	1.234503e-01	0.467429
ARYL_INH	3.132806e-02	0.626950
ESTR_AG	4.429340e-02	0.315606
ESTR_INH	2.977829e-01	0.315606
GC_AG	7.694695e-01	NaN
GC_INH	7.067643e-01	0.626950
LX_AG	4.450044e-02	0.000921
LX_INH	7.694695e-01	0.628969
RET_AG	1.276243e-10	NaN
RET_INH	9.231513e-01	0.467429
THYR_AG	8.350771e-01	0.626950
THYR_INH	7.566438e-01	0.379241

	CTL08A	CTL04E
ANDR_AG	-13.685767	-33.979428
ANDR_INH	-52.078278	-32.245714
ARYL_AG	-21.533218	-16.562041
ARYL_INH	-31.418007	-11.563816
ESTR_AG	-32.034081	-27.254041
ESTR_INH	-19.754827	-23.505846
GC_AG	-7.471028	NaN
GC_INH	-9.647208	10.750290
LX_AG	-28.360952	-52.856458
LX_INH	6.896722	-8.146840
RET_AG	-67.042535	NaN
RET_INH	-1.296808	-16.360442
THYR_AG	3.936766	-9.401252
THYR_INH	8.647752	-26.787315

	otsu_0	otsu_1	otsu_2	ImageName_ScanRegion	ImageName_ScanRegion_rep	Condition_Line	Line	Condition
20240424_manuel_lessi_0129_ScanRegion3_rep_1	2907	1209	365	20240424_manuel_lessi_0129_ScanRegion3	20240424_manuel_lessi_0129_ScanRegion3_rep_1	ARYL_AG_CTL08A	CTL08A	ARYL_AG
20240424_manuel_lessi_0134_ScanRegion2_rep_0	9181	3059	783	20240424_manuel_lessi_0134_ScanRegion2	20240424_manuel_lessi_0134_ScanRegion2_rep_0	RET_INH_CTL08A	CTL08A	RET_INH
20240424_manuel_lessi_0129_ScanRegion1_rep_2	301	144	36	20240424_manuel_lessi_0129_ScanRegion1	20240424_manuel_lessi_0129_ScanRegion1_rep_2	ARYL_INH_CTL08A	CTL08A	ARYL_INH
20240424_manuel_lessi_0134_ScanRegion2_rep_1	9830	3475	872	20240424_manuel_lessi_0134_ScanRegion2	20240424_manuel_lessi_0134_ScanRegion2_rep_1	RET_INH_CTL08A	CTL08A	RET_INH
20240424_manuel_lessi_0133_ScanRegion4_rep_0	3333	1923	522	20240424_manuel_lessi_0133_ScanRegion4	20240424_manuel_lessi_0133_ScanRegion4_rep_0	RET_AG_CTL08A	CTL08A	RET_AG
...	...	...	...	...	...	...	...	...
20240424_manuel_lessi_0130_ScanRegion3_rep_1	22897	12283	4331	20240424_manuel_lessi_0130_ScanRegion3	20240424_manuel_lessi_0130_ScanRegion3_rep_1	LX_INH_CTL04E	CTL04E	LX_INH
20240424_manuel_lessi_0133_ScanRegion4_rep_1	1685	884	260	20240424_manuel_lessi_0133_ScanRegion4	20240424_manuel_lessi_0133_ScanRegion4_rep_1	RET_AG_CTL08A	CTL08A	RET_AG
20240424_manuel_lessi_0130_ScanRegion0_rep_0	10199	5549	1924	20240424_manuel_lessi_0130_ScanRegion0	20240424_manuel_lessi_0130_ScanRegion0_rep_0	LX_AG_CTL04E	CTL04E	LX_AG
20240424_manuel_lessi_0129_ScanRegion3_rep_3	3898	2172	762	20240424_manuel_lessi_0129_ScanRegion3	20240424_manuel_lessi_0129_ScanRegion3_rep_3	ARYL_AG_CTL08A	CTL08A	ARYL_AG
20240424_manuel_lessi_0129_ScanRegion3_rep_4	4919	2353	819	20240424_manuel_lessi_0129_ScanRegion3	20240424_manuel_lessi_0129_ScanRegion3_rep_4	ARYL_AG_CTL08A	CTL08A	ARYL_AG

	Reference Image Report	general QC (keep or not)	ImageName_ScanRegion_Rep	ImageName_ScanRegion	ImageName_ScanRegion_rep	ImageName
0	20240424_manuel_lessi_0128_ScanRegion0_rep_0_c...	YES	20240424_manuel_lessi_0128_ScanRegion0_rep_0	20240424_manuel_lessi_0128_ScanRegion0	20240424_manuel_lessi_0128_ScanRegion0_rep_0	20240424_manuel_lessi_0128
1	20240424_manuel_lessi_0128_ScanRegion0_rep_1_c...	YES	20240424_manuel_lessi_0128_ScanRegion0_rep_1	20240424_manuel_lessi_0128_ScanRegion0	20240424_manuel_lessi_0128_ScanRegion0_rep_1	20240424_manuel_lessi_0128
2	20240424_manuel_lessi_0128_ScanRegion1_rep_0_c...	YES	20240424_manuel_lessi_0128_ScanRegion1_rep_0	20240424_manuel_lessi_0128_ScanRegion1	20240424_manuel_lessi_0128_ScanRegion1_rep_0	20240424_manuel_lessi_0128
3	20240424_manuel_lessi_0128_ScanRegion1_rep_1_c...	YES	20240424_manuel_lessi_0128_ScanRegion1_rep_1	20240424_manuel_lessi_0128_ScanRegion1	20240424_manuel_lessi_0128_ScanRegion1_rep_1	20240424_manuel_lessi_0128
4	20240424_manuel_lessi_0128_ScanRegion2_rep_0_c...	YES	20240424_manuel_lessi_0128_ScanRegion2_rep_0	20240424_manuel_lessi_0128_ScanRegion2	20240424_manuel_lessi_0128_ScanRegion2_rep_0	20240424_manuel_lessi_0128
...	...	...	...	...	...	...
102	20240424_manuel_lessi_0134_ScanRegion4_rep_2_c...	NO	20240424_manuel_lessi_0134_ScanRegion4_rep_2	20240424_manuel_lessi_0134_ScanRegion4	20240424_manuel_lessi_0134_ScanRegion4_rep_2	20240424_manuel_lessi_0134
103	20240424_manuel_lessi_0134_ScanRegion5_rep_0_c...	NO	20240424_manuel_lessi_0134_ScanRegion5_rep_0	20240424_manuel_lessi_0134_ScanRegion5	20240424_manuel_lessi_0134_ScanRegion5_rep_0	20240424_manuel_lessi_0134
104	20240424_manuel_lessi_0134_ScanRegion6_rep_0_c...	YES	20240424_manuel_lessi_0134_ScanRegion6_rep_0	20240424_manuel_lessi_0134_ScanRegion6	20240424_manuel_lessi_0134_ScanRegion6_rep_0	20240424_manuel_lessi_0134
105	20240424_manuel_lessi_0134_ScanRegion6_rep_2_c...	NO	20240424_manuel_lessi_0134_ScanRegion6_rep_2	20240424_manuel_lessi_0134_ScanRegion6	20240424_manuel_lessi_0134_ScanRegion6_rep_2	20240424_manuel_lessi_0134
106	20240424_manuel_lessi_0134_ScanRegion7_rep_3_c...	YES	20240424_manuel_lessi_0134_ScanRegion7_rep_3	20240424_manuel_lessi_0134_ScanRegion7	20240424_manuel_lessi_0134_ScanRegion7_rep_3	20240424_manuel_lessi_0134

	otsu_1	Condition
20240424_manuel_lessi_0133_ScanRegion4_rep_0_channel_2_measures	34.818034	RET_AG
20240424_manuel_lessi_0133_ScanRegion4_rep_2_channel_2_measures	37.808219	RET_AG
20240424_manuel_lessi_0133_ScanRegion4_rep_1_channel_2_measures	18.673426	RET_AG
20240424_manuel_lessi_0132_ScanRegion5_rep_0_channel_2_measures	11.246140	DMSO
20240424_manuel_lessi_0132_ScanRegion5_rep_2_channel_2_measures	12.400583	DMSO
20240424_manuel_lessi_0132_ScanRegion4_rep_1_channel_2_measures	26.132437	DMSO
20240424_manuel_lessi_0132_ScanRegion5_rep_1_channel_2_measures	7.145889	DMSO
20240424_manuel_lessi_0132_ScanRegion4_rep_0_channel_2_measures	11.837556	DMSO

	CTL08A	CTL04E
ANDR_AG	0.613721	0.805461
ARYL_AG	0.613721	0.805461
ARYL_INH	0.787909	0.993399
ESTR_AG	0.554127	0.963623
ESTR_INH	0.459976	0.993399
GC_AG	0.363385	NaN
GC_INH	0.328821	0.805461
LX_AG	0.613721	0.805461
LX_INH	0.414184	0.805461
RET_AG	0.024514	NaN
RET_INH	0.984871	0.805461
THYR_AG	0.927832	0.805461
THYR_INH	0.613721	0.805461

	CTL08A	CTL04E
ANDR_AG	34.488239	59.950465
ARYL_AG	29.237804	-20.293282
ARYL_INH	-15.165839	-0.484287
ESTR_AG	63.479583	-11.345261
ESTR_INH	79.974485	0.339119
GC_AG	114.412482	NaN
GC_INH	138.960827	-20.067131
LX_AG	31.739861	-29.725497
LX_INH	132.570815	30.203388
RET_AG	278.009841	NaN
RET_INH	0.725216	-26.194311
THYR_AG	-7.419489	40.904062
THYR_INH	42.123558	66.475574

	area	ImageName_ScanRegion	Condition_Line	Line	Condition	Area_um2	n_nuclei	density
20240424_manuel_lessi_0129_ScanRegion3_rep_1	18992894	20240424_manuel_lessi_0129_ScanRegion3	ARYL_AG_CTL08A	CTL08A	ARYL_AG	2.006124e+06	14032	0.006995
20240424_manuel_lessi_0134_ScanRegion2_rep_0	35827100	20240424_manuel_lessi_0134_ScanRegion2	RET_INH_CTL08A	CTL08A	RET_INH	3.784237e+06	36257	0.009581
20240424_manuel_lessi_0129_ScanRegion1_rep_2	9802711	20240424_manuel_lessi_0129_ScanRegion1	ARYL_INH_CTL08A	CTL08A	ARYL_INH	1.035411e+06	5186	0.005009
20240424_manuel_lessi_0134_ScanRegion2_rep_1	30831525	20240424_manuel_lessi_0134_ScanRegion2	RET_INH_CTL08A	CTL08A	RET_INH	3.256580e+06	30598	0.009396
20240424_manuel_lessi_0133_ScanRegion4_rep_0	8422522	20240424_manuel_lessi_0133_ScanRegion4	RET_AG_CTL08A	CTL08A	RET_AG	8.896289e+05	5637	0.006336
...	...	...	...	...	...	...	...	...
20240424_manuel_lessi_0130_ScanRegion3_rep_1	53795625	20240424_manuel_lessi_0130_ScanRegion3	LX_INH_CTL04E	CTL04E	LX_INH	5.682163e+06	54110	0.009523
20240424_manuel_lessi_0133_ScanRegion4_rep_1	11112634	20240424_manuel_lessi_0133_ScanRegion4	RET_AG_CTL08A	CTL08A	RET_AG	1.173772e+06	4832	0.004117
20240424_manuel_lessi_0130_ScanRegion0_rep_0	38195586	20240424_manuel_lessi_0130_ScanRegion0	LX_AG_CTL04E	CTL04E	LX_AG	4.034409e+06	41176	0.010206
20240424_manuel_lessi_0129_ScanRegion3_rep_3	12134498	20240424_manuel_lessi_0129_ScanRegion3	ARYL_AG_CTL08A	CTL08A	ARYL_AG	1.281706e+06	9818	0.007660
20240424_manuel_lessi_0129_ScanRegion3_rep_4	19790425	20240424_manuel_lessi_0129_ScanRegion3	ARYL_AG_CTL08A	CTL08A	ARYL_AG	2.090364e+06	23465	0.011225

	CTL08A	CTL04E
ANDR_AG	0.202776	0.845971
ARYL_AG	0.165762	0.956242
ARYL_INH	0.066489	0.956242
ESTR_AG	0.097848	0.957144
ESTR_INH	0.202776	0.956242
GC_AG	0.299312	NaN
GC_INH	0.116107	0.957144
LX_AG	0.131940	0.661754
LX_INH	0.380217	0.957144
RET_AG	0.029726	NaN
RET_INH	0.778107	0.956242
THYR_AG	0.706278	0.956242
THYR_INH	0.852862	0.956242

	CTL08A	CTL04E
ANDR_AG	48.892111	88.294004
ARYL_AG	49.334772	22.339423
ARYL_INH	96.018670	16.715867
ESTR_AG	93.257018	-2.292952
ESTR_INH	53.884421	32.630223
GC_AG	42.118838	NaN
GC_INH	71.321014	-6.196268
LX_AG	64.519630	117.548202
LX_INH	33.907897	9.572143
RET_AG	127.500496	NaN
RET_INH	9.270000	37.207111
THYR_AG	13.869399	22.465599
THYR_INH	-4.450827	32.070909

	area	ImageName_ScanRegion	Condition_Line	Line	Condition	Area_um2	n_nuclei	density
20240424_manuel_lessi_0142_ScanRegion2_rep_0	8024395	20240424_manuel_lessi_0142_ScanRegion2	RET_AG_CTL08A	CTL08A	RET_AG	8.475767e+05	2437	0.002875
20240424_manuel_lessi_0142_ScanRegion2_rep_2	9480571	20240424_manuel_lessi_0142_ScanRegion2	RET_AG_CTL08A	CTL08A	RET_AG	1.001385e+06	2340	0.002337
20240424_manuel_lessi_0138_ScanRegion1_rep_2	37281437	20240424_manuel_lessi_0138_ScanRegion1	ANDR_INH_CTL04E	CTL04E	ANDR_INH	3.937852e+06	30867	0.007839
20240424_manuel_lessi_0140_ScanRegion4_rep_1	55908114	20240424_manuel_lessi_0140_ScanRegion4	THYR_INH_CTL08A	CTL08A	THYR_INH	5.905295e+06	72472	0.012272
20240424_manuel_lessi_0140_ScanRegion5_rep_2	41670728	20240424_manuel_lessi_0140_ScanRegion5	THYR_AG_CTL08A	CTL08A	THYR_AG	4.401471e+06	58972	0.013398
...	...	...	...	...	...	...	...	...
20240424_manuel_lessi_0141_ScanRegion3_rep_1	8113209	20240424_manuel_lessi_0141_ScanRegion3	DMSO_CTL04E	CTL04E	DMSO	8.569577e+05	9105	0.010625
20240424_manuel_lessi_0138_ScanRegion5_rep_1	60950304	20240424_manuel_lessi_0138_ScanRegion5	ARYL_AG_CTL04E	CTL04E	ARYL_AG	6.437876e+06	63198	0.009817
20240424_manuel_lessi_0138_ScanRegion3_rep_1	16957648	20240424_manuel_lessi_0138_ScanRegion3	ARYL_AG_CTL08A	CTL08A	ARYL_AG	1.791152e+06	15879	0.008865
20240424_manuel_lessi_0138_ScanRegion1_rep_0	28072509	20240424_manuel_lessi_0138_ScanRegion1	ANDR_INH_CTL04E	CTL04E	ANDR_INH	2.965159e+06	26167	0.008825
20240424_manuel_lessi_0140_ScanRegion2_rep_0	7130564	20240424_manuel_lessi_0140_ScanRegion2	THYR_INH_CTL04E	CTL04E	THYR_INH	7.531658e+05	6079	0.008071

	Reference Image Report	general QC (keep or not)	ImageName_ScanRegion_Rep	ImageName_ScanRegion	ImageName_ScanRegion_rep	ImageName
131	20240424_manuel_lessi_0137_ScanRegion0_rep_0_c...	LIMIT	20240424_manuel_lessi_0137_ScanRegion0_rep_0	20240424_manuel_lessi_0137_ScanRegion0	20240424_manuel_lessi_0137_ScanRegion0_rep_0	20240424_manuel_lessi_0137
132	20240424_manuel_lessi_0137_ScanRegion1_rep_0_c...	NO	20240424_manuel_lessi_0137_ScanRegion1_rep_0	20240424_manuel_lessi_0137_ScanRegion1	20240424_manuel_lessi_0137_ScanRegion1_rep_0	20240424_manuel_lessi_0137
133	20240424_manuel_lessi_0137_ScanRegion1_rep_1_c...	YES	20240424_manuel_lessi_0137_ScanRegion1_rep_1	20240424_manuel_lessi_0137_ScanRegion1	20240424_manuel_lessi_0137_ScanRegion1_rep_1	20240424_manuel_lessi_0137
134	20240424_manuel_lessi_0137_ScanRegion1_rep_2_c...	NO	20240424_manuel_lessi_0137_ScanRegion1_rep_2	20240424_manuel_lessi_0137_ScanRegion1	20240424_manuel_lessi_0137_ScanRegion1_rep_2	20240424_manuel_lessi_0137
135	20240424_manuel_lessi_0137_ScanRegion2_rep_0_c...	YES	20240424_manuel_lessi_0137_ScanRegion2_rep_0	20240424_manuel_lessi_0137_ScanRegion2	20240424_manuel_lessi_0137_ScanRegion2_rep_0	20240424_manuel_lessi_0137
...	...	...	...	...	...	...
235	20240424_manuel_lessi_0143_ScanRegion4_rep_1_c...	YES	20240424_manuel_lessi_0143_ScanRegion4_rep_1	20240424_manuel_lessi_0143_ScanRegion4	20240424_manuel_lessi_0143_ScanRegion4_rep_1	20240424_manuel_lessi_0143
236	20240424_manuel_lessi_0143_ScanRegion4_rep_2_c...	YES	20240424_manuel_lessi_0143_ScanRegion4_rep_2	20240424_manuel_lessi_0143_ScanRegion4	20240424_manuel_lessi_0143_ScanRegion4_rep_2	20240424_manuel_lessi_0143
237	20240424_manuel_lessi_0143_ScanRegion5_rep_0_c...	YES	20240424_manuel_lessi_0143_ScanRegion5_rep_0	20240424_manuel_lessi_0143_ScanRegion5	20240424_manuel_lessi_0143_ScanRegion5_rep_0	20240424_manuel_lessi_0143
238	20240424_manuel_lessi_0143_ScanRegion5_rep_1_c...	YES	20240424_manuel_lessi_0143_ScanRegion5_rep_1	20240424_manuel_lessi_0143_ScanRegion5	20240424_manuel_lessi_0143_ScanRegion5_rep_1	20240424_manuel_lessi_0143
239	20240424_manuel_lessi_0143_ScanRegion5_rep_2_c...	YES	20240424_manuel_lessi_0143_ScanRegion5_rep_2	20240424_manuel_lessi_0143_ScanRegion5	20240424_manuel_lessi_0143_ScanRegion5_rep_2	20240424_manuel_lessi_0143

	CTL08A	CTL04E
ANDR_AG	0.588199	0.859964
ANDR_INH	0.292076	0.900052
ARYL_AG	0.339398	NaN
ESTR_AG	0.391179	0.122862
ESTR_INH	0.339398	NaN
GC_AG	0.689105	NaN
GC_INH	0.292076	0.001258
LX_AG	0.680433	0.126244
LX_INH	0.292076	0.126244
RET_AG	0.292076	NaN
RET_INH	0.819911	0.488274
THYR_AG	0.689105	0.155187
THYR_INH	0.892963	0.691742
ARYL_INH	NaN	0.122862

	CTL08A	CTL04E
ANDR_AG	5.807400e-01	0.969314
ANDR_INH	1.301555e-02	0.969314
ARYL_AG	1.907124e-01	0.998520
ARYL_INH	1.907124e-01	0.969314
ESTR_AG	5.343187e-02	0.998520
ESTR_INH	2.114632e-01	0.998520
GC_AG	8.024340e-01	NaN
GC_INH	9.367019e-01	0.969314
LX_AG	5.343187e-02	0.969314
LX_INH	8.024340e-01	0.969314
RET_AG	8.529133e-08	NaN
RET_INH	9.367019e-01	0.998520
THYR_AG	5.807400e-01	0.998520
THYR_INH	2.623755e-01	0.969314

	CTL08A	CTL04E
ANDR_AG	15.640588	43.875257
ANDR_INH	83.171575	31.989519
ARYL_AG	34.550373	-1.713245
ARYL_INH	38.975719	24.011350
ESTR_AG	66.225582	0.091310
ESTR_INH	38.865425	-10.800735
GC_AG	-7.659116	NaN
GC_INH	1.416405	-39.158859
LX_AG	58.813469	56.659567
LX_INH	-8.836966	-19.086892
RET_AG	331.439273	NaN
RET_INH	-1.939067	-12.040344
THYR_AG	-14.248588	0.876280
THYR_INH	-22.896690	52.702340