refactor so merge fasta and merge results use same function; new version

Author: apsteinberg

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tcdo_pg_tools"
-version = "0.0.4-beta"
+version = "0.0.5-beta"
 description = "Commandline tools to support proteogenomics analyses at MSK TCDO and beyond"
 readme = "README.rst"
 authors = [

src/tcdo_pg_tools/cli.py

@@ -1,8 +1,7 @@
 import click
 from tcdo_pg_tools.fusion_merge import fusion_merge
 from tcdo_pg_tools.coverage_calculator import coverage_calculator
-from tcdo_pg_tools.merge_pg_results import merge_pg_results
-from tcdo_pg_tools.merge_fasta import merge_fasta
+from tcdo_pg_tools.merge_proteome import merge_pg_results, merge_fasta
 
 @click.group()
 def cli():

src/tcdo_pg_tools/merge_fasta.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 """
 author: Asher Preska Steinberg
-merge proteomegenerator results across multiple samples on AA seq identity
+merge proteomegenerator fasta and results across multiple samples on AA seq identity
 """
 import os
 import pandas as pd
@@ -48,24 +48,9 @@ def plot_upset(countdat, upset_path):
     plt.savefig(upset_path, dpi=300, bbox_inches="tight")
     return
 
-@click.command()
-@click.option('-i', '--input_csv', required=True, type=click.Path(exists=True),
-              help='four column csv (fasta: fasta path, '
-                   'protein_table: protein.tsv path, '
-                   'name: sample name, condition: condition)')
-@click.option('-t', '--info_table', required=False,
-              default='info_table.tsv',
-              type=click.Path(), help="Path to index tsv for merged protein IDs")
-@click.option('-fa','--merged_fasta', required=False,
-              type=click.Path(), default='merged.fasta',
-              help="Path to merged fasta file")
-@click.option('--upset', is_flag=True, default=False, help="plot upset")
-@click.option('--upset_path', required=False,
-              type=click.Path(), default='upset_plot.svg',
-              help="Path to upset plot")
-def merge_pg_results(input_csv, info_table, merged_fasta, upset, upset_path, unique_proteins=True):
+def merge_proteome(input_csv, info_table, merged_fasta, upset, upset_path, unique_proteins=True):
     """
-    merge proteomegenerator results across multiple samples on AA seq identity
+    merge proteomegenerator fasta/results across multiple samples on AA seq identity
     """
     # read in metadata
     metadata = pd.read_csv(input_csv)
@@ -130,5 +115,45 @@ def merge_pg_results(input_csv, info_table, merged_fasta, upset, upset_path, uni
     # plot upset plot:
     if upset:
         plot_upset(countdat, upset_path)
-if __name__ == '__main__':
-    merge_pg_results()
+    return
+
+@click.command()
+@click.option('-i', '--input_csv', required=True, type=click.Path(exists=True),
+              help='four column csv (fasta: fasta path, '
+                   'protein_table: protein.tsv path, '
+                   'name: sample name, condition: condition)')
+@click.option('-t', '--info_table', required=False,
+              default='info_table.tsv',
+              type=click.Path(), help="Path to index tsv for merged protein IDs")
+@click.option('-fa','--merged_fasta', required=False,
+              type=click.Path(), default='merged.fasta',
+              help="Path to merged fasta file")
+@click.option('--upset', is_flag=True, default=False, help="plot upset")
+@click.option('--upset_path', required=False,
+              type=click.Path(), default='upset_plot.svg',
+              help="Path to upset plot")
+def merge_pg_results(input_csv, info_table, merged_fasta, upset, upset_path):
+    """
+    merge proteomegenerator results across multiple samples on AA seq identity
+    """
+    return merge_proteome(input_csv, info_table, merged_fasta, upset, upset_path, unique_proteins=True)
+
+@click.command()
+@click.option('-i', '--input_csv', required=True, type=click.Path(exists=True),
+              help='three column csv (fasta: fasta path, '
+                   'name: sample name, condition: condition)')
+@click.option('-t', '--info_table', required=False,
+              default='info_table.tsv',
+              type=click.Path(), help="Path to index tsv for merged protein IDs")
+@click.option('-fa','--merged_fasta', required=False,
+              type=click.Path(), default='merged.fasta',
+              help="Path to merged fasta file")
+@click.option('--upset', is_flag=True, default=False, help="plot upset")
+@click.option('--upset_path', required=False,
+              type=click.Path(), default='upset_plot.svg',
+              help="Path to upset plot")
+def merge_fasta(input_csv, info_table, merged_fasta, upset, upset_path):
+    """
+    merge multiple fasta on sequence identity
+    """
+    return merge_proteome(input_csv, info_table, merged_fasta, upset, upset_path, unique_proteins=False)

src/tcdo_pg_tools/merge_pg_results.py src/tcdo_pg_tools/merge_proteome.pysrc/tcdo_pg_tools/merge_pg_results.py renamed to src/tcdo_pg_tools/merge_proteome.py

@@ -0,0 +1,4 @@
+fasta,sample,condition
+/Volumes/kentsis/proteomics/data/Laura/Multi-protease_fractionation/fasta_files/AML_Celllines/Fasta/Celllines/PROTEOMEGENERATOR_47038_proteome_CD34_comb_fasta.fa,CD34+,control
+/Volumes/kentsis/proteomics/data/Laura/Multi-protease_fractionation/fasta_files/AML_Celllines/Fasta/Celllines/PROTEOMEGENERATOR_45382_proteome_MV4-11_fasta.fa,MV4-11,AML
+/Volumes/kentsis/proteomics/data/Laura/Multi-protease_fractionation/fasta_files/AML_Celllines/Fasta/Celllines/PROTEOMEGENERATOR_45642_proteome_Kasumi_1_fasta.fa,Kasumi-1,AML