update merge_pg_results.py to allow for reference proteomes

Author: apsteinberg

requirements.txt

@@ -1,9 +1,9 @@
 sphinx
 sphinx-click
-pandas
-numpy
-click
-tqdm
-numba
-marsilea
-matplotlib
+pandas>=2.2.3
+numpy>=2.2.6
+click>=8.2.1
+tqdm>=4.67.1
+numba>=0.61.2
+marsilea>=0.5.3
+matplotlib>=3.10.3

src/tcdo_pg_tools/merge_pg_results.py

@@ -112,7 +112,7 @@ def merge_pg_results(input_csv, info_table, merged_fasta, upset, upset_path, uni
             "unique_protein_id": f"PG{i}", # give protein a unique identifier
             "samples": samples,
             "conditions": conditions,
-            "sample_count": len(group)
+            "sample_count": len(set(group["sample"]))
         })
         i = i+1
     # write dataframe to tsv
@@ -130,4 +130,5 @@ def merge_pg_results(input_csv, info_table, merged_fasta, upset, upset_path, uni
     # plot upset plot:
     if upset:
         plot_upset(countdat, upset_path)
-    return
+if __name__ == '__main__':
+    merge_pg_results()