From 9efe1e46cc2704a9b51d4cdf54214d2df2cc49f6 Mon Sep 17 00:00:00 2001
From: Anil Thanki <thanki.anil@gmail.com>
Date: Fri, 3 Nov 2023 10:37:53 +0000
Subject: [PATCH] code refactoring

---
 .../decoupler/decoupler_pathway_inference.py  | 63 +++++--------------
 1 file changed, 16 insertions(+), 47 deletions(-)

diff --git a/tools/tertiary-analysis/decoupler/decoupler_pathway_inference.py b/tools/tertiary-analysis/decoupler/decoupler_pathway_inference.py
index 7e24e502..5caca6f9 100644
--- a/tools/tertiary-analysis/decoupler/decoupler_pathway_inference.py
+++ b/tools/tertiary-analysis/decoupler/decoupler_pathway_inference.py
@@ -5,7 +5,6 @@
 import decoupler as dc
 import pandas as pd
 import hdf5plugin
-# import scanpy as sc
 
 # define arguments for the script
 parser = argparse.ArgumentParser()
@@ -16,17 +15,10 @@
 # add network input file option
 parser.add_argument("-n", "--input_network", help="Network input file", required=True)
 
-# optional network formatted output file option
+# output file prefix
 parser.add_argument(
-    "--output_network",
-    help="network formatted output files prefix",
-    default=None,
-)
-
-# optional network formatted output file option
-parser.add_argument(
-    "--output_anndata",
-    help="anndata formatted output files prefix",
+    "--output",
+    help="output files prefix",
     default=None,
 )
 
@@ -64,38 +56,18 @@
 )
 
 
-
 args = parser.parse_args()
-# read the input file
 
-# check that either -o or -on is specified
-if args.output_anndata is None and args.output_network is None:
-    raise ValueError("Please specify either -o or -on")
+# 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)
 
-# network = dc.load_network(args.input_network)
+# read in the input file network input file
 network = pd.read_csv(args.input_network, sep='\t')
 
-# d = dc.Decoupler(network)
-
-# pathway_activity = d.infer_pathway_activity(adata)
-
-# # Save the pathway activity to a file
-# pathway_activity.to_csv(args.output_network, index=False)
-
-# # read in the network and check that source, target, and weight columns are present
-# network = pd.read_csv(args.input_network, index_col=0)
-
-print(network.columns)
-
-print(args.source)
-
-print(args.target)
-
-print(args.weight)
-
 if (
     args.source not in network.columns
     or args.target not in network.columns
@@ -109,18 +81,15 @@
 
 dc.run_mlm(
     mat=adata,
-    net=network
+    net=network,
+    source=args.source,
+    target=args.target,
+    weight=args.weight,
+    verbose=True
 )
-# ,
-#     source=args.source,
-#     target=args.target,
-#     weight=args.weight,
-#     verbose=True
-# )
 
 mlm_key = "mlm_estimate"
 if args.mlm_key is not None and args.mlm_p_key is not mlm_key:
-    print("here mlm_key")
     adata.obsm[args.mlm_key] = adata.obsm[mlm_key].copy()
     # delete adata.obsm[mlm_key]
     del adata.obsm[mlm_key]
@@ -128,15 +97,15 @@
 
 mlm_pvals_key = "mlm_pvals"
 if args.mlm_p_key is not None and args.mlm_p_key is not mlm_pvals_key:
-    print("here mlm_pvals_key")
     adata.obsm[args.mlm_p_key] = adata.obsm[mlm_pvals_key].copy()
+    # delete adata.obsm[mlm_pvals_key]
     del adata.obsm[mlm_pvals_key]
     mlm_pvals_key = args.mlm_p_key
 
-if args.output_network is not None:
+if args.output is not None:
     # write adata.obsm[ulm_key] and adata.obsm[ulm_pvals_key] to the output network files
-    adata.obsm[mlm_key].to_csv(args.output_network + "_mlm.tsv", sep="\t")
-    adata.obsm[mlm_pvals_key].to_csv(args.output_network + "_mlm_pvals.tsv", sep="\t")
+    adata.obsm[mlm_key].to_csv(args.output + "_mlm.tsv", sep="\t")
+    adata.obsm[mlm_pvals_key].to_csv(args.output + "_mlm_pvals.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: