1 Load environment

Code

import warnings

warnings.filterwarnings("ignore")

import matplotlib.pyplot as plt
import seaborn as sns
import scanpy as sc
import pandas as pd
import numpy as np
import random
import itertools

from tqdm import tqdm

import decoupler as dc
import sys

sys.setrecursionlimit(20000)

sys.path.append("./../../../../utilities_folder")
from utilities import load_object, intTable, plotGenesInTerm, getAnnGenes, run_ora_catchErrors

Set R environment with rpy2:

Code

import rpy2.rinterface_lib.callbacks
import anndata2ri
import logging

from rpy2.robjects import pandas2ri
import rpy2.robjects as ro

sc.settings.verbosity = 0
rpy2.rinterface_lib.callbacks.logger.setLevel(logging.ERROR)

pandas2ri.activate()
anndata2ri.activate()

%load_ext rpy2.ipython

Set up of graphical parameters for Python plots:

Code

%matplotlib inline
sc.set_figure_params(dpi = 300, fontsize = 20)

plt.rcParams['svg.fonttype'] = 'none'

cmap_up = sns.light_palette("red", as_cmap=True)
cmap_down = sns.light_palette("blue", as_cmap=True)
cmap_all = sns.light_palette("seagreen", as_cmap=True)

Set up of graphical parameters for R plots:

Code

default_units = 'in' 
default_res = 300
default_width = 10
default_height = 9

import rpy2
old_setup_graphics = rpy2.ipython.rmagic.RMagics.setup_graphics

def new_setup_graphics(self, args):
    if getattr(args, 'units') is not None:
        if args.units != default_units:
            return old_setup_graphics(self, args)
    args.units = default_units
    if getattr(args, 'res') is None:
        args.res = default_res
    if getattr(args, 'width') is None:
        args.width = default_width
    if getattr(args, 'height') is None:
        args.height = default_height        
    return old_setup_graphics(self, args)


rpy2.ipython.rmagic.RMagics.setup_graphics = new_setup_graphics

Here the cell were we inject the parameters using Quarto renderer:

Code

# Injected Parameters
N = 3

Code

# Injected Parameters
N = 3

Import R libraries:

Code

%%R
source('./../../../../utilities_folder/GO_helper.r')
loc <- './../../../../R_loc' # pointing to the renv environment

.libPaths(loc)

library('topGO')
library('org.Hs.eg.db')
library(dplyr)
library(ggplot2)

Set output folders:

Code

output_folder = './'
folder = './tables/cluster_' + str(N) + '/'

2 Load data

Here we load the dataframe:

Code

markers = pd.read_excel(folder + 'genes_in_cluster_' + str(N) + '.xlsx', index_col = 0)
markers

	logFC.celltypes_leveledhEGCLC	logFC.celltypes_leveledhPGCLC	logFC.celltypes_levelediMeLC	logCPM	LR	PValue	FDR	clusters
COL23A1	-1.101485	3.621170	-13.228880	6.909245	2060.346734	0.000000e+00	0.000000e+00	3
GABRA3	0.564958	4.849473	-11.613345	6.484270	1905.606420	0.000000e+00	0.000000e+00	3
TAC3	-0.518513	4.650158	-12.176420	6.839040	2391.724594	0.000000e+00	0.000000e+00	3
YPEL2	-0.564026	4.597989	-10.983524	5.487823	1476.482635	7.459403e-320	7.718555e-318	3
GSTM3	-0.510083	4.140315	-11.488468	5.594719	1352.959750	4.747077e-293	4.069940e-291	3
...	...	...	...	...	...	...	...	...
DNAJC6	0.139028	-0.118234	-10.921683	2.344544	126.423458	3.189659e-27	1.202811e-26	3
PRKCH	-0.385489	-0.141925	-11.125183	2.316191	126.202522	3.559147e-27	1.340039e-26	3
C1QTNF12	-0.409803	-0.083718	-11.090250	2.260476	124.659127	7.653491e-27	2.868088e-26	3
AFAP1L2	0.076226	-0.000737	-10.836541	2.266568	121.977292	2.894441e-26	1.073941e-25	3
SLC6A11	-0.506352	-0.472412	-11.002013	2.080230	116.297619	4.838444e-25	1.764687e-24	3

224 rows × 8 columns

Code

allGenes_series = pd.read_csv('./tables/all_bkg_genes.csv')
allGenes = allGenes_series['0'].tolist()

Here we load the dictionary that associates to each GO term its genes:

Code

GO2gene = load_object('./../../../../data/GO2gene_complete.pickle')

3 Markers of cluster

We filter genes for the cluster under investigation based on the p-value adjusted that we then convert in -log(p-value adjusted):

Code

markers = markers[markers.FDR < 0.01]
markers['-log10(FDR)'] = -np.log10(markers.FDR)
markers = markers.replace(np.inf, markers[markers['-log10(FDR)'] != np.inf]['-log10(FDR)'].max())
markers

	logFC.celltypes_leveledhEGCLC	logFC.celltypes_leveledhPGCLC	logFC.celltypes_levelediMeLC	logCPM	LR	PValue	FDR	clusters	-log10(FDR)
COL23A1	-1.101485	3.621170	-13.228880	6.909245	2060.346734	0.000000e+00	0.000000e+00	3	317.112464
GABRA3	0.564958	4.849473	-11.613345	6.484270	1905.606420	0.000000e+00	0.000000e+00	3	317.112464
TAC3	-0.518513	4.650158	-12.176420	6.839040	2391.724594	0.000000e+00	0.000000e+00	3	317.112464
YPEL2	-0.564026	4.597989	-10.983524	5.487823	1476.482635	7.459403e-320	7.718555e-318	3	317.112464
GSTM3	-0.510083	4.140315	-11.488468	5.594719	1352.959750	4.747077e-293	4.069940e-291	3	290.390412
...	...	...	...	...	...	...	...	...	...
DNAJC6	0.139028	-0.118234	-10.921683	2.344544	126.423458	3.189659e-27	1.202811e-26	3	25.919803
PRKCH	-0.385489	-0.141925	-11.125183	2.316191	126.202522	3.559147e-27	1.340039e-26	3	25.872883
C1QTNF12	-0.409803	-0.083718	-11.090250	2.260476	124.659127	7.653491e-27	2.868088e-26	3	25.542408
AFAP1L2	0.076226	-0.000737	-10.836541	2.266568	121.977292	2.894441e-26	1.073941e-25	3	24.969020
SLC6A11	-0.506352	-0.472412	-11.002013	2.080230	116.297619	4.838444e-25	1.764687e-24	3	23.753332

224 rows × 9 columns

3.0.1 All regulated

Code

all_sign = markers.index.tolist()
allSelected = allGenes_series['0'].isin(all_sign).astype('int').tolist()

4 topGO

4.1 All significant

Code

%%R -i allSelected -i allGenes

allGenes_v <- c(allSelected)
#print(allGenes_v)
names(allGenes_v) <- allGenes
allGenes_v <- unlist(allGenes_v)

geneNames <- c(allGenes)

ann_org_BP <- topGO::annFUN.org(whichOnto='BP', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_MF <- topGO::annFUN.org(whichOnto='MF', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

ann_org_CC <- topGO::annFUN.org(whichOnto='CC', feasibleGenes=names(allGenes_v), 
                           mapping='org.Hs.eg', ID='symbol')

selection <- function(allScores){return (as.logical(allScores))}

Biological Process

Code

%%R
#print(lapply(ann_org_BP, count_genes))

GOdata <- new("topGOdata",
  ontology="BP",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_BP,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([10903,   197,    10,  3187], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py

	GO.ID	Term	Annotated	Significant	Expected	weight	Scores
0	GO:0061098	positive regulation of protein tyrosine ...	33	6	0.60	2.4e-05	0.000024
1	GO:0030502	negative regulation of bone mineralizati...	10	3	0.18	0.00063	0.000635
2	GO:0001974	blood vessel remodeling	24	4	0.43	0.00083	0.000827
3	GO:0086091	regulation of heart rate by cardiac cond...	26	4	0.47	0.00113	0.001132
4	GO:0086014	atrial cardiac muscle cell action potent...	12	3	0.22	0.00113	0.001133
...	...	...	...	...	...	...	...
5697	GO:2001244	positive regulation of intrinsic apoptot...	42	0	0.76	1.00000	1.000000
5698	GO:2001251	negative regulation of chromosome organi...	88	0	1.59	1.00000	1.000000
5699	GO:2001252	positive regulation of chromosome organi...	93	0	1.68	1.00000	1.000000
5700	GO:2001256	regulation of store-operated calcium ent...	11	0	0.20	1.00000	1.000000
5701	GO:2001267	regulation of cysteine-type endopeptidas...	13	0	0.23	1.00000	1.000000

5702 rows × 7 columns

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

Code

results_table_py['-log10(pvalue)'] = - np.log10(results_table_py.Scores)
results_table_py['Significant/Annotated'] = results_table_py['Significant'] / results_table_py['Annotated']

Code

intTable(results_table_py, folder = folder, fileName = 'GO_BP_all.xlsx', save = True)

Code

%%R -i folder
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected

image = bubbleplot(Res, Ont = 'BP', fillCol = 'forestgreen')
ggsave(file=paste0(folder, "TopGO_results_BP.pdf"), plot=image, width=12, height=4)

bubbleplot(Res, Ont = 'BP', fillCol = 'forestgreen')

Code

%%R -i markers
image = plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

ggsave(file=paste0(folder, "Genes_in_Term_results_BP.pdf"), plot=image, width=12, height=4)

plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_BP_genesInTerm_all.xlsx'), SE = markers)

Molecular Function

Code

%%R

GOdata <- new("topGOdata",
  ontology="MF",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_MF,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([11203,   207,    10,   505], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')
results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_MF_all.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected

image = bubbleplot(Res, Ont = 'MF', fillCol = 'forestgreen')

ggsave(file=paste0(folder, "TopGO_results_MF.pdf"), plot=image, width=12, height=4)

bubbleplot(Res, Ont = 'MF', fillCol = 'forestgreen')

Code

%%R -i markers
image = plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

ggsave(file=paste0(folder, "Genes_in_Term_results_MF.pdf"), plot=image, width=12, height=4)

plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=15, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_MF_genesInTerm_all.xlsx'), SE = markers)

Cellular Compartment

Code

%%R

GOdata <- new("topGOdata",
  ontology="CC",
  allGenes=allGenes_v,
  annot=annFUN.GO2genes,
  GO2genes=ann_org_CC,
  geneSel = selection,
  nodeSize=10)

Code

%%R -o results

results <- runTest(GOdata, algorithm="weight01",statistic="fisher")

Code

scores = ro.r.score(results)
score_names = ro.r(
'''
names(results@score)
'''
)
go_data = ro.r.GOdata

genesData = ro.r(
'''
geneData(results)
'''
)
genesData

array([11323,   207,    10,   367], dtype=int32)

Code

#num_summarize = min(100, len(score_names))
results_table = ro.r.GenTable(go_data, weight=results,
        orderBy="weight", topNodes=len(scores))

Code

results_table_py = ro.conversion.rpy2py(results_table)

Code

scores_py = ro.conversion.rpy2py(scores)
score_names = [i for i in score_names]

Code

scores_df = pd.DataFrame({'Scores': scores_py, 'GO.ID': score_names})
results_table_py = results_table_py.merge(scores_df, left_on = 'GO.ID', right_on = 'GO.ID')

Code

results_table_py = results_table_py[results_table_py['Scores'] < 0.05]
results_table_py = results_table_py[results_table_py['Annotated'] < 200]
results_table_py = results_table_py[results_table_py['Annotated'] > 15]

intTable(results_table_py, folder = folder, fileName = 'GO_CC_all.xlsx', save = True)

Code

%%R
Res <- GenTable(GOdata, weight=results,
        orderBy="weight", topNodes=length(score(results)))
#print(Res[0:10,])
colnames(Res) <- c("GO.ID", "Term", "Annotated", "Significant", "Expected", "Statistics")
Res$ER <- Res$Significant / Res$Expected
image = bubbleplot(Res, Ont = 'CC', fillCol = 'forestgreen')

ggsave(file=paste0(folder, "TopGO_results_CC.pdf"), plot=image, width=12, height=4)

bubbleplot(Res, Ont = 'CC', fillCol = 'forestgreen')

Code

%%R -i markers
image = plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=12, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

ggsave(file=paste0(folder, "Genes:_in_Term_results_CC.pdf"), plot=image, width=12, height=4)

plotGenesInTerm_v1(Res, GOdata, SE = markers, nterms=12, ngenes=12,
                             fillCol='forestgreen', log = TRUE)

Code

%%R -i markers -i folder
saveGenesInTerm(Res, GOdata, nterms = 20, path = paste0(folder,'GO_CC_genesInTerm_all.xlsx'), SE = markers)

Pathway annotation

4.1.0.1 Reactome

Code

curated = msigdb[msigdb['collection'].isin(['reactome_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

rank = pd.DataFrame(markers['-log10(FDR)'])

rank_copy = rank.copy()
rank_copy['pval'] = markers.loc[rank.index].FDR

Code

rank_copy

	-log10(FDR)	pval
COL23A1	317.112464	0.000000e+00
GABRA3	317.112464	0.000000e+00
TAC3	317.112464	0.000000e+00
YPEL2	317.112464	7.718555e-318
GSTM3	290.390412	4.069940e-291
...	...	...
DNAJC6	25.919803	1.202811e-26
PRKCH	25.872883	1.340039e-26
C1QTNF12	25.542408	2.868088e-26
AFAP1L2	24.969020	1.073941e-25
SLC6A11	23.753332	1.764687e-24

224 rows × 2 columns

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)
len(results_table_py)

6

Code

intTable(results_table_py, folder = folder, fileName = 'Reactome_all.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['reactome_pathways'], rank_copy)
    _, df = plotGenesInTerm(results = results_table_py, GO2gene = GO2gene['reactome_pathways'], DEGs = rank_copy, n_top_terms = 10, cmap = cmap_all)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_Reactome_all.xlsx', save = True)

4.1.0.2 KEGG

Code

curated = msigdb[msigdb['collection'].isin(['kegg_pathways'])]
curated = curated[~curated.duplicated(['geneset', 'genesymbol'])]

aggregated = curated[["geneset", "genesymbol"]].groupby("geneset").count().rename(columns={"genesymbol": "gene_count"})
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count > 200].index.tolist())].copy()
curated = curated[~curated.geneset.isin(aggregated[aggregated.gene_count < 15].index.tolist())].copy()

Code

results_table_py = run_ora_catchErrors(mat=rank.T, net=curated, source='geneset', target='genesymbol', verbose=False, n_up=len(rank), n_bottom=0)

Code

intTable(results_table_py, folder = folder, fileName = 'KEGG_all.xlsx', save = True)

Code

if len(results_table_py) > 0:
    results_table_py = getAnnGenes(results_table_py, GO2gene['kegg_pathways'], rank_copy)
    _, df = plotGenesInTerm(results_table_py, GO2gene['kegg_pathways'], rank_copy, n_top_terms = 10, n_top_genes = 15, cmap = cmap_all)

Code

if len(results_table_py) > 0:
    intTable(df, folder = folder, fileName = 'genesInTerm_KEGG_all.xlsx', save = True)