{"id":608,"date":"2025-07-11T11:21:49","date_gmt":"2025-07-11T03:21:49","guid":{"rendered":"https:\/\/www.kz-hub.tech\/?p=608"},"modified":"2025-07-14T11:29:54","modified_gmt":"2025-07-14T03:29:54","slug":"%e4%bd%bf%e7%94%a8-bam-readcount-%e7%bb%9f%e8%ae%a1-bam-%e6%96%87%e4%bb%b6%e5%9c%a8%e6%9f%93%e8%89%b2%e4%bd%93%e6%8c%87%e5%ae%9a%e4%bd%8d%e7%bd%ae%e7%9a%84%e7%a2%b1%e5%9f%ba%e6%95%b0%e7%9b%ae","status":"publish","type":"post","link":"https:\/\/www.kz-hub.tech\/index.php\/2025\/07\/11\/%e4%bd%bf%e7%94%a8-bam-readcount-%e7%bb%9f%e8%ae%a1-bam-%e6%96%87%e4%bb%b6%e5%9c%a8%e6%9f%93%e8%89%b2%e4%bd%93%e6%8c%87%e5%ae%9a%e4%bd%8d%e7%bd%ae%e7%9a%84%e7%a2%b1%e5%9f%ba%e6%95%b0%e7%9b%ae\/","title":{"rendered":"\u4f7f\u7528 bam-readcount \u7edf\u8ba1 bam \u6587\u4ef6\u5728\u67d3\u8272\u4f53\u6307\u5b9a\u4f4d\u7f6e\u7684\u78b1\u57fa\u6570\u76ee"},"content":{"rendered":"

\u4ec5\u80fd\u7edf\u8ba1SNP\uff0c\u65e0\u6cd5\u7edf\u8ba1INDEL\uff0c\u6b64\u8f6f\u4ef6\u4f1a\u628aINDEL\u6253\u788e\u6210\u5355\u4e2a\u78b1\u57fa\u8fdb\u884c\u7edf\u8ba1<\/h1>\n

1. \u9996\u5148\u5bf9bqsr\u5904\u7406\u597d\u7684bam\u6587\u4ef6\u8fdb\u884c\u53bb\u9664\u91cd\u590d<\/h3>\n
# \u6ce8\u610f\u52a0\u4e0a \u201c--REMOVE_DUPLICATE true\u201d \u540e\uff0c\u8f93\u51fa\u7684bam\u6587\u4ef6\u5c31\u662f\u5df2\u7ecf\u5254\u9664\u4e86pcr duplicate\u7684\nls ..\/rawdata\/*_R1.fastq.gz|perl -ne 'chomp;my $name=$1 if($_=~\/\\\/([^\\\/]+)\\_R1\/);print "gatk --java-options \\"-Xmx20G -Djava.io.tmpdir=.\/\\" MarkDuplicates --INPUT ..\/align\/$name\\_bqsr.bam --OUTPUT $name\\_bqsr.removedup.bam -M $name.metrics  --VALIDATION_STRINGENCY LENIENT --REMOVE_DUPLICATE true && samtools index $name\\_bqsr.removedup.bam && echo $name ok\\n"' > remove_bam_dup.sh<\/code><\/pre>\n
2. \u5728R\u4e2d\u5bf9\u540c\u4e00\u75c5\u4eba\u7684\u4e0d\u540c\u6837\u672c\u7684\u7a81\u53d8maf\u6587\u4ef6\u8fdb\u884c\u5408\u5e76\uff0c\u5e76\u63d0\u53d6\u4e3abam-readcount\u7684\u8f93\u5165\u683c\u5f0f<\/h3>\n
# \u793a\u4f8b\uff1a\n## X. \u63d0\u53d6\u914d\u5bf9\u4e0a\u76ae\u3001\u57fa\u8d28\u6837\u672c\u4e2d\u7684PASS\u4f4d\u70b9 ####\n# \u8bfb\u53d6\u7684\u662f\u8fc7\u6ee4\u540e\uff0c\u6240\u6709\u75c5\u4eba\u7684\u6240\u6709\u6837\u672c\u7684\u6240\u6709\u7a81\u53d8\u7684maf\u6587\u4ef6\nMerged_maf_df <- read.table("\/Users\/zhoukaiwen\/Desktop\/Breast_Phyllodes_Tumor\/Bioinfo\/WES\/Mutation\/6patients_mutect2_varscan2_intersect_pass.Somatic.hc.hg38_multianno_filtered.maf",\n                            header = T,sep = '\\t',quote = "")\n\n# \u6784\u5efa\u533a\u5206\u6837\u672c\u7684\u4fe1\u606f\nMerged_maf_df$PatientID <- Merged_maf_df$Tumor_Sample_Barcode\nMerged_maf_df <- Merged_maf_df %>%\n  separate(PatientID, into = c("PatientID", "TumorType", "TissueType"), sep = "-")\n\nunique_combinations <- unique(Merged_maf_df[, c("PatientID", "TissueType")])\n# Loop through each unique combination\nfor (i in 1:nrow(unique_combinations)) {\n  patient_id <- unique_combinations$PatientID[i]\n  tissue_type <- unique_combinations$TissueType[i]\n\n  # Filter rows based on PatientID and TissueType\n  filtered_df <- Merged_maf_df[Merged_maf_df$PatientID == patient_id & Merged_maf_df$TissueType == tissue_type, ]\n  filtered_df <- filtered_df[,c("Chromosome", "Start_Position", "End_Position")]\n\n  # Create a dynamic name for the new dataframe\n  df_name <- paste(patient_id, tissue_type, sep = "_")\n  df_name <- paste(df_name, "df", sep = "_")\n\n  # Assign the filtered dataframe to a new variable\n  assign(df_name, filtered_df)\n  write.table(filtered_df,paste0("\/Users\/zhoukaiwen\/Desktop\/Breast_Phyllodes_Tumor\/Bioinfo\/WES\/unique_mut_sites\/",patient_id,"-",tissue_type,"_site_list.txt"), \n              col.names = F,row.names = F,sep = '\\t',quote = F)\n}<\/code><\/pre>\n
\u6700\u540e\u8f93\u51fa\u7684\u8303\u4f8b\uff1a<\/p>\n
# FETB01-E_site_list.txt (tab\u5206\u9694):\nchr1    10008116        10008116\nchr1    52495456        52495456\nchr2    54649645        54649645\nchr3    138084166       138084166\nchr5    50667572        50667572\nchr6    1611682 1611682\nchr7    4221252 4221252\nchr7    94420457        94420457\nchr8    3387676 3387676\nchr8    115515228       115515228\nchr11   434096  434096\nchr11   119313110       119313110\nchr12   242757  242757\nchr12   51806999        51806999\nchr13   99866404        99866404\nchr14   19760391        19760391\nchr16   1314177 1314177\nchr16   2183864 2183864\nchr16   29861014        29861014\nchr19   35835836        35835836\nchr19   38119394        38119394\nchr19   47353134        47353134<\/code><\/pre>\n
3. \u8fd0\u884cbam-readcount<\/h1>\n
github\uff1ahttps:\/\/github.com\/genome\/bam-readcount<\/a>
\n\u53c2\u8003\uff1ahttps:\/\/www.jianshu.com\/p\/0697dbfe316c<\/a><\/p>\n
# \u4f7f\u7528\u8bf4\u660e\uff1a\nUsage: bam-readcount [OPTIONS] bam_file|cram_file [region]\nGenerate metrics for bam_file at single nucleotide positions.\nExample: bam-readcount -f ref.fa some.bam|some.cram\n\nAvailable options:\n  -h [ --help ]                         produce this message\n  -v [ --version ]                      output the version number\n  -q [ --min-mapping-quality ] arg (=0) minimum mapping quality of reads used \n                                        for counting.\n  -b [ --min-base-quality ] arg (=0)    minimum base quality at a position to \n                                        use the read for counting.\n  -d [ --max-count ] arg (=10000000)    max depth to avoid excessive memory \n                                        usage.\n  -l [ --site-list ] arg                file containing a list of regions to \n                                        report readcounts within.\n  -f [ --reference-fasta ] arg          reference sequence in the fasta format.\n  -D [ --print-individual-mapq ] arg    report the mapping qualities as a comma\n                                        separated list.\n  -p [ --per-library ]                  report results by library.\n  -w [ --max-warnings ] arg             maximum number of warnings of each type\n                                        to emit. -1 gives an unlimited number.\n  -i [ --insertion-centric ]            generate indel centric readcounts. \n                                        Reads containing insertions will not be\n                                        included in per-base counts<\/code><\/pre>\n
bam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB01-M_site_list.txt ..\/align\/FETB01-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB01-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB01-M_site_list.txt ..\/align\/FETB01-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB01-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB01-E_site_list.txt ..\/align\/FETB01-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB01-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB01-E_site_list.txt ..\/align\/FETB01-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB01-FA-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB02-M_site_list.txt ..\/align\/FETB02-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB02-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB02-M_site_list.txt ..\/align\/FETB02-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB02-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB02-E_site_list.txt ..\/align\/FETB02-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB02-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB02-E_site_list.txt ..\/align\/FETB02-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB02-FA-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB03-M_site_list.txt ..\/align\/FETB03-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB03-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB03-M_site_list.txt ..\/align\/FETB03-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB03-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB03-E_site_list.txt ..\/align\/FETB03-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB03-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB03-E_site_list.txt ..\/align\/FETB03-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB03-FA-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB04-M_site_list.txt ..\/align\/FETB04-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB04-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB04-M_site_list.txt ..\/align\/FETB04-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB04-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB04-E_site_list.txt ..\/align\/FETB04-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB04-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB04-E_site_list.txt ..\/align\/FETB04-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB04-FA-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB05-M_site_list.txt ..\/align\/FETB05-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB05-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB05-M_site_list.txt ..\/align\/FETB05-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB05-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB05-E_site_list.txt ..\/align\/FETB05-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB05-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB05-E_site_list.txt ..\/align\/FETB05-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB05-FA-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB06-M_site_list.txt ..\/align\/FETB06-BNPT-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB06-BNPT-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB06-M_site_list.txt ..\/align\/FETB06-FA-M_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB06-FA-M.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB06-E_site_list.txt ..\/align\/FETB06-BNPT-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB06-BNPT-E.matched.sites.txt\nbam-readcount -q 20 -b 10 -f \/home\/zhoukaiwen\/database\/GRCh38\/genecode_GRCh38.p14.genome.fa -l FETB06-E_site_list.txt ..\/align\/FETB06-FA-E_bqsr.bam | grep -v WARNING |awk 'BEGIN{FS=OFS="\\t"}{split($6,A,":");split($7,C,":");split($8,G,":");split($9,T,":");print $1,$2,$3,$4,"A:"A[2],"C:"C[2],"G:"G[2],"T:"T[2]}' > FETB06-FA-E.matched.sites.txt<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
\u4ec5\u80fd\u7edf\u8ba1SNP\uff0c\u65e0\u6cd5\u7edf\u8ba1INDEL\uff0c\u6b64\u8f6f\u4ef6\u4f1a\u628aINDEL\u6253\u788e\u6210\u5355\u4e2a\u78b1\u57fa\u8fdb\u884c\u7edf\u8ba1 1. \u9996\u5148\u5bf9bqsr\u5904\u7406\u597d\u7684b…<\/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-608","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\/608","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=608"}],"version-history":[{"count":2,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/608\/revisions"}],"predecessor-version":[{"id":617,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/608\/revisions\/617"}],"wp:attachment":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/media?parent=608"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/categories?post=608"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/tags?post=608"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}