Mercurial > repos > ebi-gxa > decoupler_pseudobulk

changeset 5:893ff9213a34 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ebi-gene-expression-group/container-galaxy-sc-tertiary/ commit 1034a450c97dcbb77871050cf0c6d3da90dac823
author ebi-gxa
date Fri, 15 Mar 2024 12:18:11 +0000
parents f321c60167d4
children ed2a77422e00
files decoupler_pathway_inference.py get_test_data.sh test-data/progeny_test.tsv test-data/progeny_test_2.tsv
diffstat 4 files changed, 290 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/decoupler_pathway_inference.py	Fri Mar 15 12:18:11 2024 +0000
@@ -0,0 +1,132 @@
+# import the necessary packages
+import argparse
+
+import anndata as ad
+import decoupler as dc
+import pandas as pd
+
+# define arguments for the script
+parser = argparse.ArgumentParser()
+
+# add AnnData input file option
+parser.add_argument(
+    "-i", "--input_anndata", help="AnnData input file", required=True
+)
+
+# add network input file option
+parser.add_argument(
+    "-n", "--input_network", help="Network input file", required=True
+)
+
+# output file prefix
+parser.add_argument(
+    "-o", "--output",
+    help="output files prefix",
+    default=None,
+)
+
+# path to save Activities AnnData file
+parser.add_argument(
+    "-a", "--activities_path", help="Path to save Activities AnnData file", default=None
+)
+
+# Column name in net with source nodes
+parser.add_argument(
+    "-s", "--source", help="Column name in net with source nodes.", default="source"
+)
+
+# Column name in net with target nodes
+parser.add_argument(
+    "-t", "--target", help="Column name in net with target nodes.", default="target"
+)
+
+# Column name in net with weights.
+parser.add_argument(
+    "-w", "--weight", help="Column name in net with weights.", default="weight"
+)
+
+# add boolean argument for use_raw
+parser.add_argument(
+    "--use_raw", action="store_true", default=False, help="Whether to use the raw part of the AnnData object"
+)
+
+# add argument for min_cells
+parser.add_argument(
+    "--min_n", help="Minimum of targets per source. If less, sources are removed.", default=5, type=int
+)
+
+# add activity inference method option
+parser.add_argument(
+    "-m", "--method", help="Activity inference method", default="mlm", required=True
+)
+args = parser.parse_args()
+
+# check that either -o or --output is specified
+if args.output is None:
+    raise ValueError("Please specify either -o or --output")
+
+# read in the AnnData input file
+adata = ad.read_h5ad(args.input_anndata)
+
+# read in the input file network input file
+network = pd.read_csv(args.input_network, sep='\t')
+
+if (
+    args.source not in network.columns
+    or args.target not in network.columns
+    or args.weight not in network.columns
+):
+    raise ValueError(
+        "Source, target, and weight columns are not present in the network"
+    )
+
+
+print(type(args.min_n))
+
+if args.method == "mlm":
+    dc.run_mlm(
+        mat=adata,
+        net=network,
+        source=args.source,
+        target=args.target,
+        weight=args.weight,
+        verbose=True,
+        min_n=args.min_n,
+        use_raw=args.use_raw 
+    )
+
+    if args.output is not None:
+        # write adata.obsm[mlm_key] and adata.obsm[mlm_pvals_key] to the output network files
+        combined_df = pd.concat([adata.obsm["mlm_estimate"], adata.obsm["mlm_pvals"]], axis=1)
+
+        # Save the combined dataframe to a file
+        combined_df.to_csv(args.output + ".tsv", sep="\t")
+
+    # if args.activities_path is specified, generate the activities AnnData and save the AnnData object to the specified path
+    if args.activities_path is not None:
+        acts = dc.get_acts(adata, obsm_key="mlm_estimate")
+        acts.write_h5ad(args.activities_path)
+
+elif args.method == "ulm":
+    dc.run_ulm(
+        mat=adata,
+        net=network,
+        source=args.source,
+        target=args.target,
+        weight=args.weight,
+        verbose=True,
+        min_n=args.min_n,
+        use_raw=args.use_raw 
+    )
+
+    if args.output is not None:
+        # write adata.obsm[mlm_key] and adata.obsm[mlm_pvals_key] to the output network files
+        combined_df = pd.concat([adata.obsm["ulm_estimate"], adata.obsm["ulm_pvals"]], axis=1)
+
+        # Save the combined dataframe to a file
+        combined_df.to_csv(args.output + ".tsv", sep="\t")
+
+    # if args.activities_path is specified, generate the activities AnnData and save the AnnData object to the specified path
+    if args.activities_path is not None:
+        acts = dc.get_acts(adata, obsm_key="ulm_estimate")
+        acts.write_h5ad(args.activities_path)
--- a/get_test_data.sh	Thu Nov 16 20:05:16 2023 +0000
+++ b/get_test_data.sh	Fri Mar 15 12:18:11 2024 +0000
@@ -19,3 +19,19 @@
 mkdir -p test-data
 pushd test-data
 get_data $MTX_LINK $BASENAME_FILE
+
+
+# Download input anndata for decoupler-pathway_inference
+BASENAME_FILE='pbmc3k_processed.h5ad'
+
+MTX_LINK='https://zenodo.org/records/3752813/files/pbmc3k_processed.h5ad'
+
+get_data $MTX_LINK $BASENAME_FILE
+
+# Download output anndata for decoupler-pathway_inference
+BASENAME_FILE='test.h5ad'
+
+MTX_LINK='https://zenodo.org/records/10401958/files/test.h5ad'
+
+get_data $MTX_LINK $BASENAME_FILE
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/progeny_test.tsv	Fri Mar 15 12:18:11 2024 +0000
@@ -0,0 +1,71 @@
+	source	target	weight	p_value
+0	Androgen	TMPRSS2	11.490631	0.0
+1	Androgen	NKX3-1	10.622551	2.2e-44
+2	Androgen	MBOAT2	10.472733	4.6e-44
+3	Androgen	KLK2	10.176186	1.94441e-40
+4	Androgen	SARG	11.386852	2.79021e-40
+5	EGFR	LZTFL1	-1.8738769	2.0809955e-18
+6	EGFR	PHLDA2	3.5051384	2.0530624e-17
+7	EGFR	DUSP6	12.6293125	6.537324e-17
+8	EGFR	DUSP5	7.9430394	6.86669e-17
+9	EGFR	PHLDA1	6.619626	3.4106933e-16
+10	Estrogen	GREB1	17.240173	0.0
+11	Estrogen	RET	10.718027	0.0
+12	Estrogen	TFF1	14.430255	0.0
+13	Estrogen	HEY2	11.482369	3.1e-44
+14	Estrogen	RAPGEFL1	10.544896	5.2e-43
+15	Hypoxia	FAM162A	8.335551	0.0
+16	Hypoxia	NDRG1	22.08712	0.0
+17	Hypoxia	ENO2	14.32694	0.0
+18	Hypoxia	PDK1	13.120449	0.0
+19	Hypoxia	ANKRD37	8.484976	0.0
+20	JAK-STAT	OAS1	15.028714	1.058e-41
+21	JAK-STAT	HERC6	8.769676	1.3450407e-38
+22	JAK-STAT	OAS3	10.618842	1.2143582e-37
+23	JAK-STAT	PLSCR1	8.481604	8.955206e-37
+24	JAK-STAT	DDX60	12.198234	9.150971e-36
+25	MAPK	DUSP6	16.859016	0.0
+26	MAPK	SPRED2	3.5018346	0.0
+27	MAPK	SPRY2	9.481585	9.19e-43
+28	MAPK	ETV5	5.9887094	6.7425e-41
+29	MAPK	EPHA2	6.3140125	3.7492e-40
+30	NFkB	NFKB1	9.513637	0.0
+31	NFkB	CXCL3	22.946114	0.0
+32	NFkB	NFKB2	5.5155754	0.0
+33	NFkB	NFKBIA	11.444533	0.0
+34	NFkB	BCL2A1	14.416924	0.0
+35	PI3K	MLANA	-9.985743	1.84e-43
+36	PI3K	PMEL	-6.5903482	6.8747866e-36
+37	PI3K	FAXDC2	-12.421274	3.297515e-34
+38	PI3K	HSD17B8	-8.601571	9.948224e-34
+39	PI3K	CTSF	-9.172143	1.0235212e-31
+40	TGFb	LINC00312	4.428987	2.0074443e-17
+41	TGFb	TSPAN2	5.502326	3.1451768e-16
+42	TGFb	SMAD7	7.6311436	7.3087106e-16
+43	TGFb	NOX4	5.913813	3.8292238e-15
+44	TGFb	COL4A1	6.3374896	9.052501e-15
+45	TNFa	CSF2	8.35548	0.0
+46	TNFa	CXCL5	10.0813675	0.0
+47	TNFa	NFKBIE	10.356205	0.0
+48	TNFa	TNFAIP3	35.40072	0.0
+49	TNFa	EFNA1	18.63111	0.0
+50	Trail	FRMPD1	-2.2346141	9.378505e-07
+51	Trail	WT1-AS	2.2251053	2.0316747e-06
+52	Trail	WNT8A	-1.8469616	3.795469e-05
+53	Trail	GPR18	3.240805	6.1090715e-05
+54	Trail	TEC	2.0513217	6.32898e-05
+55	VEGF	CRACD	-4.87119	6.7185365e-25
+56	VEGF	VWA8	-3.6068044	1.4495265e-18
+57	VEGF	NLGN1	-5.618075	2.6587072e-18
+58	VEGF	NRG3	-5.823747	1.0848074e-16
+59	VEGF	KCNK10	2.8833063	1.8129868e-16
+60	WNT	BMP4	5.936831	2.511717e-10
+61	WNT	SIGLEC6	2.0207362	2.347858e-09
+62	WNT	NPY2R	1.3872339	8.666917e-09
+63	WNT	CSF3R	1.9323153	3.0219417e-07
+64	WNT	KRT23	4.1216116	5.463989e-07
+65	p53	GLS2	6.452465	7.444302e-37
+66	p53	MDM2	8.193488	2.1194304e-35
+67	p53	ZNF79	4.020263	4.5987433e-34
+68	p53	FDXR	11.994496	5.589482e-32
+69	p53	LCE1B	11.813737	7.8095406e-30
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/progeny_test_2.tsv	Fri Mar 15 12:18:11 2024 +0000
@@ -0,0 +1,71 @@
+source	target	weight	p_value
+Androgen	TMPRSS2	11.490631	0.0
+Androgen	NKX3-1	10.622551	2.2e-44
+Androgen	MBOAT2	10.472733	4.6e-44
+Androgen	KLK2	10.176186	1.94441e-40
+Androgen	SARG	11.386852	2.79021e-40
+EGFR	LZTFL1	-1.8738769	2.0809955e-18
+EGFR	PHLDA2	3.5051384	2.0530624e-17
+EGFR	DUSP6	12.6293125	6.537324e-17
+EGFR	DUSP5	7.9430394	6.86669e-17
+EGFR	PHLDA1	6.619626	3.4106933e-16
+Estrogen	GREB1	17.240173	0.0
+Estrogen	RET	10.718027	0.0
+Estrogen	TFF1	14.430255	0.0
+Estrogen	HEY2	11.482369	3.1e-44
+Estrogen	RAPGEFL1	10.544896	5.2e-43
+Hypoxia	FAM162A	8.335551	0.0
+Hypoxia	NDRG1	22.08712	0.0
+Hypoxia	ENO2	14.32694	0.0
+Hypoxia	PDK1	13.120449	0.0
+Hypoxia	ANKRD37	8.484976	0.0
+JAK-STAT	OAS1	15.028714	1.058e-41
+JAK-STAT	HERC6	8.769676	1.3450407e-38
+JAK-STAT	OAS3	10.618842	1.2143582e-37
+JAK-STAT	PLSCR1	8.481604	8.955206e-37
+JAK-STAT	DDX60	12.198234	9.150971e-36
+MAPK	DUSP6	16.859016	0.0
+MAPK	SPRED2	3.5018346	0.0
+MAPK	SPRY2	9.481585	9.19e-43
+MAPK	ETV5	5.9887094	6.7425e-41
+MAPK	EPHA2	6.3140125	3.7492e-40
+NFkB	NFKB1	9.513637	0.0
+NFkB	CXCL3	22.946114	0.0
+NFkB	NFKB2	5.5155754	0.0
+NFkB	NFKBIA	11.444533	0.0
+NFkB	BCL2A1	14.416924	0.0
+PI3K	MLANA	-9.985743	1.84e-43
+PI3K	PMEL	-6.5903482	6.8747866e-36
+PI3K	FAXDC2	-12.421274	3.297515e-34
+PI3K	HSD17B8	-8.601571	9.948224e-34
+PI3K	CTSF	-9.172143	1.0235212e-31
+TGFb	LINC00312	4.428987	2.0074443e-17
+TGFb	TSPAN2	5.502326	3.1451768e-16
+TGFb	SMAD7	7.6311436	7.3087106e-16
+TGFb	NOX4	5.913813	3.8292238e-15
+TGFb	COL4A1	6.3374896	9.052501e-15
+TNFa	CSF2	8.35548	0.0
+TNFa	CXCL5	10.0813675	0.0
+TNFa	NFKBIE	10.356205	0.0
+TNFa	TNFAIP3	35.40072	0.0
+TNFa	EFNA1	18.63111	0.0
+Trail	FRMPD1	-2.2346141	9.378505e-07
+Trail	WT1-AS	2.2251053	2.0316747e-06
+Trail	WNT8A	-1.8469616	3.795469e-05
+Trail	GPR18	3.240805	6.1090715e-05
+Trail	TEC	2.0513217	6.32898e-05
+VEGF	CRACD	-4.87119	6.7185365e-25
+VEGF	VWA8	-3.6068044	1.4495265e-18
+VEGF	NLGN1	-5.618075	2.6587072e-18
+VEGF	NRG3	-5.823747	1.0848074e-16
+VEGF	KCNK10	2.8833063	1.8129868e-16
+WNT	BMP4	5.936831	2.511717e-10
+WNT	SIGLEC6	2.0207362	2.347858e-09
+WNT	NPY2R	1.3872339	8.666917e-09
+WNT	CSF3R	1.9323153	3.0219417e-07
+WNT	KRT23	4.1216116	5.463989e-07
+p53	GLS2	6.452465	7.444302e-37
+p53	MDM2	8.193488	2.1194304e-35
+p53	ZNF79	4.020263	4.5987433e-34
+p53	FDXR	11.994496	5.589482e-32
+p53	LCE1B	11.813737	7.8095406e-30