{"id":458,"date":"2025-02-24T09:30:03","date_gmt":"2025-02-24T01:30:03","guid":{"rendered":"https:\/\/www.kz-hub.tech\/?p=458"},"modified":"2025-07-11T11:08:48","modified_gmt":"2025-07-11T03:08:48","slug":"pyclone-pyclone-vi-%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\/02\/24\/pyclone-pyclone-vi-%e4%ba%9a%e5%85%8b%e9%9a%86%e9%89%b4%e5%ae%9a\/","title":{"rendered":"pyclone-vi \u4e9a\u514b\u9686\u9274\u5b9a + Citup\u8fdb\u5316\u6811\u63a8\u65ad + Timescape \u53ef\u89c6\u5316"},"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\u4e3apyclonevi\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 $1 ok\\n"}' > RunPycloneVIPrepare.sh\n<\/code><\/pre>\n
5.\u8fd0\u884cpyclonevi<\/h3>\n
ls *_pyclonevi_input.tsv | perl -ne 'chomp;if($_=~\/(\\S+)\\_pyclonevi\\_input\\.tsv\/){print "pyclone-vi fit -i $1_pyclonevi_input\\.tsv -o $1.h5 -c 40 -d beta-binomial -r 10 && pyclone-vi write-results-file -i $1.h5 -o $1.pyclonevi_results.tsv && echo $1 ok\\n"}' > RunPycloneVI.sh<\/code><\/pre>\n
PreparePycloneVIInput \u811a\u672c<\/em><\/strong><\/h3>\n
#!\/usr\/bin\/env python\n"""\nThis is an open source Script written by K.Z. to prepare Pyclone-VI input files\nfrom Merged filtered PASS and Annovar annotated vcf file and extracted counts\nand facets called cncf file\n\nInput example:\n(echo -e "CHROM\\tPOS\\tREF\\tALT\\tGENE\\t$(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"""\nimport argparse\nimport pandas as pd\nimport os\nimport numpy as np\n\ndef main():\n    # Create a Custom ArgumentParser\n    parser = argparse.ArgumentParser(description='Create Pyclone-VI input file from MAF file and facets called cncf file')\n\n    # Set Input Argument\n    parser.add_argument('-sampleid', dest='sampleid', required=True, help="Sample name: EXAMPLE")\n    parser.add_argument('-mut', dest='mutfile', required=True, help="Merged filtered PASS and Annovar annotated vcf file and extracted counts: EXAMPLE_filtered.maf")\n    parser.add_argument('-facets_cncf', dest='facetsfile', required=True, help="Merged cncf file of facets R output, with header and rownames(can have multiple inputs): EXAMPLE_1_cncf.xls,EXAMPLE_2_cncf.xls,EXAMPLE_3_cncf.xls,EXAMPLE_4_cncf.xls")\n    parser.add_argument("-V", "--version", action="version", version="Pyclone-VI Input Prepare Version 1.0")\n\n    # Parse Arguments\n    args = parser.parse_args()\n\n    # Obtain input and output file names\n    sample_id = args.sampleid\n    mut_filename = args.mutfile\n    facets_filename = args.facetsfile\n    output_filename = str(sample_id)+"_pyclonevi_input.tsv"\n\n    # Load all files first\n    mut_file = pd.read_csv(mut_filename, sep='\\t', header=0,comment='#') \n    mut_file = mut_file.loc[:, ~mut_file.columns.str.contains("^Unnamed")]   \n    mut_dict = mut_file.to_dict(orient='records')\n\n    facets_filenames = facets_filename.split(",")\n    facets_dfs = []\n    for filename in facets_filenames:\n        df = pd.read_csv(filename, sep='\\t', header=0, index_col=0, comment='#')\n\n        # Extract sample name (assuming it's before '_cncf.xls')\n        basename = os.path.basename(filename)\n        sample_name = basename.split("_cncf.xls")[0]\n\n        # Add a new column for the sample name\n        df["Sample"] = sample_name\n\n        # Append the DataFrame to the list\n        facets_dfs.append(df)\n\n    facets_file = pd.concat(facets_dfs, ignore_index=True)\n    facets_file['lcn.em'].fillna(1, inplace=True)\n    facets_file['chrom'] = 'chr' + facets_file['chrom'].astype(str)\n    facets_file['chrom'] = facets_file['chrom'].replace('chr23', 'chrX')\n    facets_dict = facets_file[['Sample','chrom','start','end','tcn.em','lcn.em']].to_dict(orient='records')\n\n    facets_lookup = {}\n    for entry in facets_dict:\n        key = (entry['chrom'], entry['Sample'])  # Key by chromosome and sample name\n        if key not in facets_lookup:\n            facets_lookup[key] = []\n        facets_lookup[key].append(entry)  # Store all matching segments\n\n    # Convert mut_dict into the new format\n    final_list = []\n    for mut in mut_dict:\n        chrom = mut['CHROM']\n\n        # Extract sample names and remove the first sample\n        sample_names = [s for s in mut.keys() if s not in ['CHROM', 'POS', 'REF', 'ALT', 'GENE']]\n        if sample_names:\n            sample_names.pop(0)  # Remove first sample\n\n        for sample in sample_names:\n            ref_alt = mut[sample].split(',')\n            ref_counts, alt_counts = ref_alt[0], ref_alt[1]  # Extract ref and alt counts\n\n            new_entry = {\n                'CHROM': chrom,\n                'POS': mut['POS'],\n                'REF': mut['REF'],\n                'ALT': mut['ALT'],\n                'GENE': mut['GENE'],\n                'sample_id': sample,\n                'ref_counts': ref_counts,\n                'alt_counts': alt_counts\n            }\n\n            # Merge with facets_dict if available\n            if (chrom, sample) in facets_lookup:\n                for segment in facets_lookup[(chrom, sample)]:\n                    if segment['start'] <= mut['POS'] <= segment['end']:  # Check POS in range\n                        new_entry['tcn.em'] = segment['tcn.em']\n                        new_entry['lcn.em'] = segment['lcn.em']\n\n            final_list.append(new_entry)\n\n    # \u53bb\u9664\u6ca1\u6709'tcn.em'\u7684\n    final_list = [item for item in final_list if 'tcn.em' in item]\n\n    for item in final_list:\n        # \u6dfb\u52a0 mutation id\n        item['mutation_id'] = item['GENE'] + ":" + str(item['POS']) + ":" + str(item['ALT'])\n        # \u8ba1\u7b97 mcn.em\n        item['mcn.em'] = item['tcn.em'] - item['lcn.em']\n        # \u6dfb\u52a0 ncn\n        item['ncn'] = 2\n\n    output_data = []\n    for item in final_list:\n        output_data.append({\n            "mutation_id": item['mutation_id'],\n            "sample_id": item['sample_id'],\n            "ref_counts": item['ref_counts'],\n            "alt_counts": item['alt_counts'],\n            "normal_cn": item['ncn'],\n            "major_cn": int(item['mcn.em']),\n            "minor_cn": int(item['lcn.em'])\n        })\n\n    output_df = pd.DataFrame(output_data)\n\n    print("Writing OutPut Files...")\n    output_df.to_csv(output_filename, sep='\\t', index=False)\n\nif __name__ == "__main__":\n    main()<\/code><\/pre>\n
6.\u5904\u7406pyclone \u7ed3\u679c\u83b7\u53d6Citup\u8f93\u5165\u6587\u4ef6<\/h3>\n
find . -maxdepth 1 -name "*pyclonevi_results.tsv" -print0 | xargs -0 -I {} sh -c '\n  base=$(basename "{}" .pyclonevi_results.tsv);\n  echo "cut -f 6 {} | sed '1d' | paste - - - - > ${base}.freq.txt"\n  echo "cut -f 3 {} | sed '1d' | paste - - - - | cut -f 1 > ${base}.cluster.txt"\n  echo "cut -f 2 {} | sed '1d' | head -4 > ${base}.sampleid"\n  echo "echo ${base} ok"\n' > PrepareCitupInput.sh\n<\/code><\/pre>\n
7.\u8fd0\u884cCitup<\/h3>\n
ls *.freq.txt | perl -ne 'chomp;if($_=~\/(\\S+)\\.freq\\.txt\/){print "run_citup_qip.py $1.freq.txt $1.cluster.txt $1.citup.results.h5 && echo $1 ok\\n"}' > RunCitup.sh\n<\/code><\/pre>\n
8.Timescape \u53ef\u89c6\u5316<\/h3>\n
<\/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-458","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\/458","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=458"}],"version-history":[{"count":22,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/458\/revisions"}],"predecessor-version":[{"id":496,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/458\/revisions\/496"}],"wp:attachment":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/media?parent=458"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/categories?post=458"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/tags?post=458"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}