update use main

Author: ATPs

src/PrecisionProDB.py

@@ -12,7 +12,7 @@
 A VCF or /a tsv file can be used as the variant input. If the variant file is in tsv format, at least four columns are required in the header: chr, pos, ref, alt. Additional columns will be ignored. Try to Convert the file to proper format if you have a bed file or other types of variant file. The pos column is 1-based like in the vcf file.
 Additionally, a string like "chr1-788418-CAG-C" can used as variant input. It has to be combined with the --sqlite for quick check of the mutation effects
 '''
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-g','--genome', help = 'the reference genome sequence in fasta format. It can be a gzip file', default='')
@@ -173,3 +173,6 @@
 
 
     print('PrecisionProDB finished! Total seconds:', time.time() - time0)
+
+if __name__ == '__main__':
+    main()

src/PrecisionProDB_Sqlite.py

@@ -407,7 +407,7 @@ def main(file_genome, file_gtf, file_mutations, file_protein, threads, outprefix
 if datatype is gtf or not set, the gtf input is required
 '''
 
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     import argparse
@@ -447,4 +447,7 @@ def main(file_genome, file_gtf, file_mutations, file_protein, threads, outprefix
     print(description)
     print(f)
 
-    main(file_genome, file_gtf, file_mutations, file_protein, threads, outprefix, datatype, protein_keyword, filter_PASS, individual, chromosome_only, keep_all, file_sqlite)
+    main(file_genome, file_gtf, file_mutations, file_protein, threads, outprefix, datatype, protein_keyword, filter_PASS, individual, chromosome_only, keep_all, file_sqlite)
+
+if __name__ == '__main__':
+    main()

src/PrecisionProDB_core.py

@@ -615,7 +615,7 @@ def runPerChom(self):
 description = '''PrecisionProDB_core, personal proteogenomic tools which outputs a new reference protein based on the variants data
 '''
 
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-g','--genome', help = 'the reference genome sequence in fasta format. It can be a gzip file', required=True)
@@ -655,3 +655,6 @@ def runPerChom(self):
     pergeno.splitInputByChromosomes()
     #print(pergeno.__dict__)
     pergeno.runPerChom()
+
+if __name__ == '__main__':
+    main()

src/PrecisionProDB_test.py

@@ -79,7 +79,8 @@ def main(dc_variant, dc_inputs, dc_sqlite, output_test):
             f.write(f'{ls_cmd[i]}\n{result}\n\n')
 
 
-if __name__ == '__main__':
+
+def main():
     description = """
     Run PrecisionProDB tests.
     Usage: test.py -s PATH_OF_PRECISIONPRODB [-o OUTPUT_TEST]
@@ -158,7 +159,8 @@ def main(dc_variant, dc_inputs, dc_sqlite, output_test):
     main(dc_variant, dc_inputs, dc_sqlite, output_test)
 
 
-
+if __name__ == '__main__':
+    main()
 
 
 

src/PrecisionProDB_vcf.py

@@ -135,7 +135,8 @@ def runPerGenoVCF(
 
 description = '''PrecisionProDB_vcf, personal proteogenomic tools which outputs a new reference protein based on the variants data. VCF file as the variant input
 '''
-if __name__ == '__main__':
+
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-g','--genome', help = 'the reference genome sequence in fasta format. It can be a gzip file', required=True)
@@ -182,3 +183,6 @@ def runPerGenoVCF(
         chromosome_only=chromosome_only, 
         keep_all=keep_all
         )
+
+if __name__ == '__main__':
+    main()

src/buildSqlite.py

@@ -594,8 +594,7 @@ def get_proteins_from_sqlite(file_sqlite, file_output = None):
 
 
 description = '''create a sqlite file for PrecisionProDB.'''
-
-if __name__ == '__main__':
+def main():
 
     import argparse
     parser = argparse.ArgumentParser(description=description)
@@ -627,3 +626,6 @@ def get_proteins_from_sqlite(file_sqlite, file_output = None):
     )
 
     print('SQLite creation complete.')
+
+if __name__ == '__main__':
+    main()

src/downloadHuman.py

@@ -237,8 +237,7 @@ def download(datatype, workfolder='.'):
 If datatype is "Uniprot", Ensembl and UniProt human sequences (UP000005640_9606, UP000005640_9606_additional) will be downloaded.
 If datatype is 'CHM13', the RefSeq CHM13 file will be downloaded
 '''
-
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-d','--datatype', help = 'RefSeq, CHM13, GENCODE, Ensembl or Uniprot to download.', required=True)
@@ -249,3 +248,5 @@ def download(datatype, workfolder='.'):
     workfolder = f.out
     download(datatype=datatype, workfolder=workfolder)
 
+if __name__ == '__main__':
+    main()

src/extractMutatedUniprot.py

@@ -101,7 +101,7 @@ def extractMutatedUniprot(files_uniprot, files_ref, files_alt, outprefix, length
 write three files, outprefix + '.uniprot_changed.tsv'/'.uniprot_changed.fa'/'.uniprot_all.fa'
 '''
 
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-u','--files_uniprot', help = 'uniprot proteins. If more than one files, join by ","', required=True)
@@ -117,3 +117,5 @@ def extractMutatedUniprot(files_uniprot, files_ref, files_alt, outprefix, length
     outprefix = f.outprefix
     length_min = f.length_min
     extractMutatedUniprot(files_uniprot, files_ref, files_alt, outprefix, length_min = length_min)
+if __name__ == '__main__':
+    main()

src/generatePEFFoutput.py

@@ -218,7 +218,7 @@ def generateUniprotPEFFout(file_PEFF, files_uniprot_ref, file_uniprot_changed, f
 
 description = '''Generate PEFF output file based on amino acid substitutions annotated by PresionProDB and save a PEFF file
 '''
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-p', '--protein', help='protein sequences in fasta format. It can be a gzip file.', required=True)
@@ -235,4 +235,7 @@ def generateUniprotPEFFout(file_PEFF, files_uniprot_ref, file_uniprot_changed, f
     generatePEFFoutput(file_protein = f.protein, file_mutation = f.mutation, file_out = f.outfile, TEST=TEST)
 
     if (f.uniprots is not None) and (f.changed is not None) and (f.outfile2 is not None):
-        generateUniprotPEFFout(file_PEFF = f.outfile, files_uniprot_ref = f.uniprots, file_uniprot_changed = f.changed, file_uniprot_out = f.outfile2)
+        generateUniprotPEFFout(file_PEFF = f.outfile, files_uniprot_ref = f.uniprots, file_uniprot_changed = f.changed, file_uniprot_out = f.outfile2)
+
+if __name__ == '__main__':
+    main()

src/perChrom.py

@@ -774,7 +774,7 @@ def run_perChrom(self, save_results = True):
 description = '''output a new reference protein set by with the variants data for each chromosome. The input files were generated by PrecisionProDB_core.
 '''
 
-if __name__ == '__main__':
+def main():
     import argparse
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-g','--genome', help = 'the reference genome sequence in fasta format. It can be a gzip file', required=True)
@@ -808,3 +808,5 @@ def run_perChrom(self, save_results = True):
     print('run perChrom for chromosome', chromosome)
     perchrom.run_perChrom()
 
+if __name__ == '__main__':
+    main()