change default threads

Author: ATPs

src/PrecisionProDB_Sqlite.py

@@ -416,7 +416,7 @@ 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" 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 all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', 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')

src/PrecisionProDB_core.py

@@ -89,7 +89,7 @@ def __init__(
                     file_gtf,
                     file_mutations,
                     file_protein,
-                    threads = os.cpu_count(),
+                    threads = min(20, os.cpu_count()),
                     outprefix = 'perGeno',
                     datatype = 'gtf',
                     protein_keyword = 'auto',
@@ -622,7 +622,7 @@ def main():
     parser.add_argument('-f', '--gtf', help='gtf file with CDS and exon annotations. It can be a gzip file', required=True)
     parser.add_argument('-m', '--mutations', help='a file stores the variants', required=True)
     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', required=True)
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=min(20, os.cpu_count()))
     parser.add_argument('-o', '--out', help='''output prefix. Three files will be saved, including the annotation for mutated transcripts, the mutated or all protein sequences. {out}.pergeno.aa_mutations.csv, {out}.pergeno.protein_all.fa, {out}.protein_changed.fa. 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')

src/PrecisionProDB_vcf.py

@@ -143,7 +143,7 @@ def main():
     parser.add_argument('-f', '--gtf', help='gtf file with CDS and exon annotations. It can be a gzip file', required=True)
     parser.add_argument('-m', '--mutations', help='a file stores the variants', required=True)
     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', required=True)
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=min(20, os.cpu_count()))
     parser.add_argument('-o', '--out', help='''output prefix. Five files will be saved, including 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')

src/buildSqlite.py

@@ -606,7 +606,7 @@ def main():
     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')
     parser.add_argument('--keep_all', help='If set, do not delete files generated during the run', action='store_true')
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=min(20, os.cpu_count()))
     if TEST:
         args = parser.parse_args(['-q', file_sqlite, '-g', file_genome, '-p', file_protein, '-f', file_gtf, '-o', outprefix, '-a', 'GENCODE_GTF', '-k', protein_keyword, '--keep_all', str(keep_all)])
 

src/perChrom.py

@@ -784,7 +784,7 @@ def main():
     parser.add_argument('-p','--protein', help = 'protein sequences in fasta format. It can be a gzip file.', default=None)
     parser.add_argument('-f', '--gtf', help='gtf file with CDS and exon annotations', required=True)
     parser.add_argument('-m', '--mutations', help='a file stores the variants', required=True)
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=min(20, os.cpu_count()))
     parser.add_argument('-o', '--out', help='output prefix. two file will be output. One is the annotation for mutated transcripts, one is the protein sequences. {out}.aa_mutations.csv, {out}.mutated_protein.fa. {out}.mutated_protein.fa only includes the proteins AA changes. ''')
     parser.add_argument('-c', '--chromosome', help='''chromosome name/id, default="chr1" ''', default='chr1', type=str)
     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'])

src/perChromSqlite.py

@@ -184,7 +184,7 @@ def main():
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument('-q', '--sqlite', help='sqlite file file with CDS and exon annotations', required=True)
     parser.add_argument('-m', '--mutations', help='a file stores the variants, or a string looks like "1-55051215-G-GA" or "chr1-55051215-G-GA" ', required=True)
-    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=os.cpu_count())
+    parser.add_argument('-t', '--threads', help='number of threads/CPUs to run the program. default, use all CPUs available', type=int, default=min(20, os.cpu_count()))
     parser.add_argument('-o', '--out', help='output prefix. two file will be output. One is the annotation for mutated transcripts, one is the protein sequences. {out}.aa_mutations.csv, {out}.mutated_protein.fa. default "perChrom" ', default = "perChrom")
     parser.add_argument('-c', '--chromosome', help='''chromosome name/id, default="chr1" ''', default='chr1', type=str)
     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'])