v27.0.0

phasing/utils/convert_group_to_read_stat_file.py

@@ -1,9 +1,27 @@
+"""
+Converting collapsed group.txt file into a .read_stat file that could be used to run IsoPhase later
+"""
+
 import os, sys
 
-f = open('dedup.5merge.collapsed.read_stat.txt', 'w')
-f.write("id\tpbid\tis_fl\tstat\n")
-for line in open('dedup.5merge.collapsed.group.txt'):
-    a,b=line.strip().split()
-    for x in set(b.split(',')): f.write(f"{x}\t{a}\tY\tunique\n")
-
-f.close()
+def main(group_filename, output_filename):
+    f = open(output_filename, 'w')
+    f.write("id\tpbid\tis_fl\tstat\n")
+    for line in open(group_filename):
+        a,b=line.strip().split()
+        for x in set(b.split(',')): f.write(f"{x}\t{a}\tY\tunique\n")
+    f.close()
+    print(f"Output written to: {output_filename}")
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser
+    parser = ArgumentParser()
+    parser.add_argument("group_txt", help="Collapsed .group.txt to convert")
+    parser.add_argument("output_txt", help="Output filename")
+
+    args = parser.parse_args()
+    if not os.path.exists(args.group_txt):
+        print("Input .group.txt file {0} does not exist! Abort!".format(args.group_txt))
+        sys.exit(-1)
+
+    main(args.group_txt, args.output_txt)

singlecell/link_molecule_to_celltype.py

@@ -0,0 +1,44 @@
+from csv import DictReader, DictWriter
+import gzip
+import os, sys
+
+def main(bc_info_csv, input_csv, output_csv):
+    bc_info = {}  # BC --> cell type
+    reader = DictReader(open(bc_info_csv), delimiter=',')
+    if 'BCrev' not in reader.fieldnames or 'Celltype' not in reader.fieldnames:
+        print(f"ERROR: Expected 'BCrev' and 'Celltype' columns in {bc_info_csv}. Abort!")
+        sys.exit(-1)
+    for r in reader:
+        bc_info[r['BCrev']] = r['Celltype']
+
+    reader = DictReader(gzip.open(input_csv, 'rt'), delimiter='\t')
+    if 'BCrev' not in reader.fieldnames or 'id' not in reader.fieldnames:
+        print(f"ERROR: Expected 'id' and 'BCrev' columns in {input_csv}. Abort!")
+        sys.exit(-1)
+
+    f = open(output_csv, 'w')
+    writer = DictWriter(f, fieldnames=reader.fieldnames+['Celltype'], delimiter=',')
+    writer.writeheader()
+    for r in reader:
+        if r['BCrev'] in bc_info:
+            r['Celltype'] = bc_info[r['BCrev']]
+            writer.writerow(r)
+    f.close()
+    print(f"Output written to: {output_csv}")
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser
+    parser = ArgumentParser()
+    parser.add_argument("bc_csv", help="Comma-delimited barcode to cell type information, must have 'BCrev' and 'Celltype' columns")
+    parser.add_argument("annotated_csv", help="Tab-delimited annotated CSV file, gzipped, must have 'id' and 'BCrev' columns")
+    parser.add_argument("output_csv", help="Output CSV filename")
+
+    args = parser.parse_args()
+    if not os.path.exists(args.bc_csv):
+        print("Input file {0} does not exist! Abort!".format(args.bc_csv))
+        sys.exit(-1)
+    if not os.path.exists(args.annotated_csv):
+        print("Input file {0} does not exist! Abort!".format(args.annotated_csv))
+        sys.exit(-1)
+
+    main(args.bc_csv, args.annotated_csv, args.output_csv)