Update PrecisionProDB.py

Author: ATPs

src/PrecisionProDB.py

@@ -19,7 +19,7 @@ def main():
     parser.add_argument('-f', '--gtf', help='gtf file with CDS and exon annotations. It can be a gzip file', default='')
     parser.add_argument('-m', '--mutations', help='''a file stores the variants. If the file ends with ".vcf" or ".vcf.gz", treat as vcf input. Otherwise, treat as TSV input. a string like "chr1-788418-CAG-C" or "chr1-942451-T-C,1-6253878-C-T,1-2194700-C-G" can used as variant input, too. ''', default = '', required=False)
     parser.add_argument('-p','--protein', help = 'protein sequences in fasta format. It can be a gzip file. Only proteins in this file will be checked', default='')
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use 20 or all CPUs available, whichever is smaller', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use 20 or all CPUs available, whichever is smaller', type=int, default=min(20, os.cpu_count()))
     parser.add_argument('-o', '--out', help='''output prefix, folder path could be included. Three or five files will be saved depending on the variant file format. Outputs include the annotation for mutated transcripts, the mutated or all protein sequences, two variant files from vcf. {out}.pergeno.aa_mutations.csv, {out}.pergeno.protein_all.fa, {out}.protein_changed.fa, {out}.vcf2mutation_1/2.tsv. default "perGeno" ''', default="perGeno")
     parser.add_argument('-a', '--datatype', help='''input datatype, could be GENCODE_GTF, GENCODE_GFF3, RefSeq, Ensembl_GTF or gtf. default "gtf". Ensembl_GFF3 is not supported. ''', default='gtf', type=str, choices=['GENCODE_GTF', 'GENCODE_GFF3','RefSeq','Ensembl_GTF','gtf'])
     parser.add_argument('-k','--protein_keyword', help='''field name in attribute column of gtf file to determine ids for proteins. default "auto", determine the protein_keyword based on datatype. "transcript_id" for GENCODE_GTF, "protein_id" for "RefSeq" and "Parent" for gtf and GENCODE_GFF3 ''', default='auto')
@@ -54,9 +54,7 @@ def main():
     keep_all = f.keep_all
     file_sqlite = f.sqlite
     print(f)
-    
-    if threads is None:
-        threads = min(20, os.cpu_count())
+
 
     time0 = time.time()