{"id":495,"date":"2025-03-05T09:57:08","date_gmt":"2025-03-05T01:57:08","guid":{"rendered":"https:\/\/www.kz-hub.tech\/?p=495"},"modified":"2025-03-05T10:57:47","modified_gmt":"2025-03-05T02:57:47","slug":"pyclone%e8%80%81%e7%89%88%e4%ba%9a%e5%85%8b%e9%9a%86%e9%89%b4%e5%ae%9a","status":"publish","type":"post","link":"https:\/\/www.kz-hub.tech\/index.php\/2025\/03\/05\/pyclone%e8%80%81%e7%89%88%e4%ba%9a%e5%85%8b%e9%9a%86%e9%89%b4%e5%ae%9a\/","title":{"rendered":"pyclone(\u8001\u7248)\u4e9a\u514b\u9686\u9274\u5b9a"},"content":{"rendered":"

1.\u4f7f\u7528mutect\u6309\u75c5\u4eba\u540c\u65f6\u5904\u7406\u6837\u672c<\/h3>\n
gatk Mutect2 -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -I ..\/align\/FETB01-BNPT-E_bqsr.bam -I ..\/align\/FETB01-BNPT-M_bqsr.bam -I ..\/align\/FETB01-FA-E_bqsr.bam -I ..\/align\/FETB01-FA-M_bqsr.bam -I ..\/align\/FETB01-B_bqsr.bam -normal FETB01-B -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed --germline-resource \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -pon \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_1000g_pon.hg38.vcf.gz --f1r2-tar-gz FETB01.f1r2.tar.gz -O FETB01.raw.vcf && gatk LearnReadOrientationModel -I FETB01.f1r2.tar.gz -O FETB01.read-orientation-model.tar.gz && gatk GetPileupSummaries -I ..\/align\/FETB01-BNPT-E_bqsr.bam -I ..\/align\/FETB01-BNPT-M_bqsr.bam -I ..\/align\/FETB01-FA-E_bqsr.bam -I ..\/align\/FETB01-FA-M_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB01.pileups.table && gatk GetPileupSummaries -I ..\/align\/FETB01-B_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB01-B.pileups.table && gatk CalculateContamination -I FETB01.pileups.table -matched FETB01-B.pileups.table -O FETB01.CalculateContamination.table && gatk FilterMutectCalls -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -V FETB01.raw.vcf --contamination-table FETB01.CalculateContamination.table --ob-priors FETB01.read-orientation-model.tar.gz -O FETB01.somatic.vcf && gatk FilterAlignmentArtifacts -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa --bwa-mem-index-image \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa.img -V FETB01.somatic.vcf -O FETB01.somatic.FAA.vcf -I ..\/align\/FETB01-BNPT-E_bqsr.bam -I ..\/align\/FETB01-BNPT-M_bqsr.bam -I ..\/align\/FETB01-FA-E_bqsr.bam -I ..\/align\/FETB01-FA-M_bqsr.bam && awk '\/^#\/ {print $0; next} $7=="PASS"  {print $0}' FETB01.somatic.FAA.vcf > .\/FETB01.somatic.passed.vcf && echo FETB01 somatic ok\ngatk Mutect2 -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -I ..\/align\/FETB02-BNPT-E_bqsr.bam -I ..\/align\/FETB02-BNPT-M_bqsr.bam -I ..\/align\/FETB02-FA-E_bqsr.bam -I ..\/align\/FETB02-FA-M_bqsr.bam -I ..\/align\/FETB02-B_bqsr.bam -normal FETB02-B -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed --germline-resource \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -pon \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_1000g_pon.hg38.vcf.gz --f1r2-tar-gz FETB02.f1r2.tar.gz -O FETB02.raw.vcf && gatk LearnReadOrientationModel -I FETB02.f1r2.tar.gz -O FETB02.read-orientation-model.tar.gz && gatk GetPileupSummaries -I ..\/align\/FETB02-BNPT-E_bqsr.bam -I ..\/align\/FETB02-BNPT-M_bqsr.bam -I ..\/align\/FETB02-FA-E_bqsr.bam -I ..\/align\/FETB02-FA-M_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB02.pileups.table && gatk GetPileupSummaries -I ..\/align\/FETB02-B_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB02-B.pileups.table && gatk CalculateContamination -I FETB02.pileups.table -matched FETB02-B.pileups.table -O FETB02.CalculateContamination.table && gatk FilterMutectCalls -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -V FETB02.raw.vcf --contamination-table FETB02.CalculateContamination.table --ob-priors FETB02.read-orientation-model.tar.gz -O FETB02.somatic.vcf && gatk FilterAlignmentArtifacts -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa --bwa-mem-index-image \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa.img -V FETB02.somatic.vcf -O FETB02.somatic.FAA.vcf -I ..\/align\/FETB02-BNPT-E_bqsr.bam -I ..\/align\/FETB02-BNPT-M_bqsr.bam -I ..\/align\/FETB02-FA-E_bqsr.bam -I ..\/align\/FETB02-FA-M_bqsr.bam && awk '\/^#\/ {print $0; next} $7=="PASS"  {print $0}' FETB02.somatic.FAA.vcf > .\/FETB02.somatic.passed.vcf && echo FETB02 somatic ok\ngatk Mutect2 -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -I ..\/align\/FETB03-BNPT-E_bqsr.bam -I ..\/align\/FETB03-BNPT-M_bqsr.bam -I ..\/align\/FETB03-FA-E_bqsr.bam -I ..\/align\/FETB03-FA-M_bqsr.bam -I ..\/align\/FETB03-B_bqsr.bam -normal FETB03-B -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed --germline-resource \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -pon \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_1000g_pon.hg38.vcf.gz --f1r2-tar-gz FETB03.f1r2.tar.gz -O FETB03.raw.vcf && gatk LearnReadOrientationModel -I FETB03.f1r2.tar.gz -O FETB03.read-orientation-model.tar.gz && gatk GetPileupSummaries -I ..\/align\/FETB03-BNPT-E_bqsr.bam -I ..\/align\/FETB03-BNPT-M_bqsr.bam -I ..\/align\/FETB03-FA-E_bqsr.bam -I ..\/align\/FETB03-FA-M_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB03.pileups.table && gatk GetPileupSummaries -I ..\/align\/FETB03-B_bqsr.bam -L \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.filtered.bed -V \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/somatic-hg38_af-only-gnomad.hg38.vcf.gz -O FETB03-B.pileups.table && gatk CalculateContamination -I FETB03.pileups.table -matched FETB03-B.pileups.table -O FETB03.CalculateContamination.table && gatk FilterMutectCalls -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa -V FETB03.raw.vcf --contamination-table FETB03.CalculateContamination.table --ob-priors FETB03.read-orientation-model.tar.gz -O FETB03.somatic.vcf && gatk FilterAlignmentArtifacts -R \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa --bwa-mem-index-image \/data02\/zhangmengmeng\/database\/hg38\/gencode_GRCh38.p14.genome.fa.img -V FETB03.somatic.vcf -O FETB03.somatic.FAA.vcf -I ..\/align\/FETB03-BNPT-E_bqsr.bam -I ..\/align\/FETB03-BNPT-M_bqsr.bam -I ..\/align\/FETB03-FA-E_bqsr.bam -I ..\/align\/FETB03-FA-M_bqsr.bam && awk '\/^#\/ {print $0; next} $7=="PASS"  {print $0}' FETB03.somatic.FAA.vcf > .\/FETB03.somatic.passed.vcf && echo FETB03 somatic ok\n<\/code><\/pre>\n
2.\u4f7f\u7528 Annovar \u5bf9\u6bcf\u4e2a\u75c5\u4eba\u7684\u591a\u6837\u672cvcf\u8fdb\u884c\u6ce8\u91ca<\/h3>\n
ls *somatic.passed.vcf | perl -ne 'chomp; my $name = $1 if ($_ =~ \/([^\\\/]+)\\.somatic\\.passed\\.vcf\/); print "table_annovar.pl $name.somatic.passed.vcf \/data02\/zhangmengmeng\/database\/annovar_db\/humandb_hg38 -buildver hg38 -out $name -remove -protocol refGene,cytoBand,avsnp151,cosmic70,exac03 -operation g,r,f,f,f -nastring . -vcfinput \\n"'>annovar.sh<\/code><\/pre>\n
3.\u5bf9\u6ce8\u91ca\u540e\u7684vcf\u8fdb\u884c\u63d0\u53d6\uff0c\u83b7\u53d6\u57fa\u56e0\u540d\uff0c\u7a81\u53d8\u70b9\u4f4d\uff0c\u6837\u672c\u540d\uff0ct_ref_count\u53cat_alt_count<\/h3>\n
(echo -e "CHROM\\tPOS\\tREF\\tALT\\tGENE\\t$(bcftools query -l FETB01.hg38_multianno.vcf | tr '\\n' '\\t')" && bcftools query -f '%CHROM\\t%POS\\t%REF\\t%ALT\\t%INFO\/Gene.refGene[\\t%AD]\\n' FETB01.hg38_multianno.vcf) > ..\/pyclonevi\/FETB01_mut.tsv\n(echo -e "CHROM\\tPOS\\tREF\\tALT\\tGENE\\t$(bcftools query -l FETB02.hg38_multianno.vcf | tr '\\n' '\\t')" && bcftools query -f '%CHROM\\t%POS\\t%REF\\t%ALT\\t%INFO\/Gene.refGene[\\t%AD]\\n' FETB02.hg38_multianno.vcf) > ..\/pyclonevi\/FETB02_mut.tsv\n(echo -e "CHROM\\tPOS\\tREF\\tALT\\tGENE\\t$(bcftools query -l FETB03.hg38_multianno.vcf | tr '\\n' '\\t')" && bcftools query -f '%CHROM\\t%POS\\t%REF\\t%ALT\\t%INFO\/Gene.refGene[\\t%AD]\\n' FETB03.hg38_multianno.vcf) > ..\/pyclonevi\/FETB03_mut.tsv<\/code><\/pre>\n
4.\u8fd0\u884c\u811a\u672c\u8f6c\u6362\u4e3apyclone\u7684\u8f93\u5165\u683c\u5f0f<\/h3>\n
ls *_mut.tsv | perl -ne 'chomp;if($_=~\/(\\S+)\\_mut\\.tsv\/){print "PreparePycloneVIInput -sampleid $1 -mut $1_mut.tsv -facets_cncf ..\/facets\/$1-BNPT-E_cncf.xls,..\/facets\/$1-BNPT-M_cncf.xls,..\/facets\/$1-FA-E_cncf.xls,..\/facets\/$1-FA-M_cncf.xls && echo $1 ok\\n"}' > RunPycloneVIPrepare.sh<\/code><\/pre>\n
5.\u5bf9\u51c6\u5907\u597d\u7684\u8f93\u5165\u6587\u4ef6\u6309\u6837\u672c\u8fdb\u884c\u5206\u5272<\/h3>\n
.\/split_pyclone_input.py -tsv FETB01_pyclonevi_input.tsv,FETB02_pyclonevi_input.tsv,FETB03_pyclonevi_input.tsv<\/code><\/pre>\n
6.\u8fd0\u884cpyclone<\/h3>\n
ls *_pyclonevi_input.tsv | perl -ne 'chomp; if ($_ =~ \/(\\S+)_pyclonevi_input\\.tsv\/) { print "PyClone run_analysis_pipeline --in_files $1-BNPT-E_pyclone_input.tsv $1-FA-E_pyclone_input.tsv --working_dir $1-E && "; print "PyClone run_analysis_pipeline --in_files $1-BNPT-M_pyclone_input.tsv $1-FA-M_pyclone_input.tsv --working_dir $1-M && echo $1 ok\\n"; }' > RunPyclone.sh\n<\/code><\/pre>\n
split_pyclone_input.py<\/em><\/strong><\/h4>\n
#!\/usr\/bin\/env python\nimport pandas as pd\nimport argparse\n\ndef split_tsv(input_file):\n    # Read the TSV file\n    df = pd.read_csv(input_file, sep='\\t')\n\n    # Filter: Keep only rows where 'major_cn' > 0\n    df = df[df['major_cn'] > 0]\n\n    # Rename 'alt_counts' column to 'var_counts'\n    df.rename(columns={'alt_counts': 'var_counts'}, inplace=True)\n\n    # Group by 'sample_id' and create separate files\n    for sample, group in df.groupby('sample_id'):\n        # Drop 'sample_id' column\n        group = group.drop(columns=['sample_id'])\n\n        # Generate the output filename based on the sample_id\n        output_filename = f"{sample}_pyclone_input.tsv"\n\n        # Write the group to a TSV file\n        group.to_csv(output_filename, sep='\\t', index=False)\n        print(f"Saved: {output_filename}")\n\ndef main():\n    parser = argparse.ArgumentParser(description="Split TSV files by sample_id and filter rows where major_cn > 0")\n    parser.add_argument('-tsv', type=str, help='Comma-separated list of TSV files', required=True)\n\n    # Parse the command line arguments\n    args = parser.parse_args()\n    tsv_files = args.tsv.split(',')\n\n    # Process each TSV file\n    for file in tsv_files:\n        split_tsv(file)\n\nif __name__ == "__main__":\n    main()<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
1.\u4f7f\u7528mutect\u6309\u75c5\u4eba\u540c\u65f6\u5904\u7406\u6837\u672c gatk Mutect2 -R \/data02\/zhangmengme…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-495","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/495","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/comments?post=495"}],"version-history":[{"count":5,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/495\/revisions"}],"predecessor-version":[{"id":501,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/495\/revisions\/501"}],"wp:attachment":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/media?parent=495"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/categories?post=495"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/tags?post=495"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}