From 65770098da493bf08dd131cb8336612c46a0d6fc Mon Sep 17 00:00:00 2001
From: Joshua Orvis <jorvis@gmail.com>
Date: Tue, 14 Nov 2023 22:40:11 -0600
Subject: [PATCH] First version of h5ad_add_metadata_columns.py, tested

---
 bin/h5ad_add_metadata_columns.py | 48 ++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100755 bin/h5ad_add_metadata_columns.py

diff --git a/bin/h5ad_add_metadata_columns.py b/bin/h5ad_add_metadata_columns.py
new file mode 100755
index 00000000..e7285b4c
--- /dev/null
+++ b/bin/h5ad_add_metadata_columns.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+
+"""
+
+"""
+
+import argparse
+import os
+import pandas as pd
+import scanpy as sc
+
+def main():
+    parser = argparse.ArgumentParser( description='Rename a colum in an H5AD file')
+    parser.add_argument('-im', '--input_matrix', type=str, required=True, help='Path to an input h5ad file to be read' )
+    parser.add_argument('-mf', '--metadata_file', type=str, required=True, help='Path to input file of new metadata columns to be added. Index should correspond to adata.obs.index')
+    parser.add_argument('-o', '--output_file', type=str, required=True, help='Path to an output file to be created' )
+    args = parser.parse_args()
+
+    adata = sc.read_h5ad(args.input_matrix)
+
+    # read a tab-delimited input file, set index to first column
+    metadata = pd.read_csv(args.metadata_file, sep='\t')
+    metadata = metadata.set_index(metadata.columns[0])
+
+    # make sure indexes match. If they don't, show where they disagree
+    assert (adata.obs.index == metadata.index).all()
+
+    # See where the indexes disagree
+    #print(adata.obs.index.difference(metadata.index))
+
+    # add metadata columns to adata
+    adata.obs = adata.obs.join(metadata)
+
+    # remove column of a certain name
+    adata.obs.drop('Unnamed..0', axis=1, inplace=True)
+
+    adata.write(args.output_file)
+
+
+if __name__ == '__main__':
+    main()
+
+
+
+
+
+
+