{"id":411,"date":"2025-01-20T15:16:08","date_gmt":"2025-01-20T07:16:08","guid":{"rendered":"https:\/\/www.kz-hub.tech\/?p=411"},"modified":"2025-02-26T09:41:33","modified_gmt":"2025-02-26T01:41:33","slug":"tmb%e7%9a%84%e5%ae%9a%e4%b9%89%e4%b8%8e%e8%ae%a1%e7%ae%97","status":"publish","type":"post","link":"https:\/\/www.kz-hub.tech\/index.php\/2025\/01\/20\/tmb%e7%9a%84%e5%ae%9a%e4%b9%89%e4%b8%8e%e8%ae%a1%e7%ae%97\/","title":{"rendered":"TMB\u7684\u5b9a\u4e49\u4e0e\u8ba1\u7b97"},"content":{"rendered":"

\u53c2\u8003\u94fe\u63a51<\/a><\/p>\n

TMB\u7684\u5b9a\u4e49<\/h2>\n

TMB\u7684\u5b9a\u4e49\u5982\u4e0b\uff1aTMB was defined as the number of somatic<\/em><\/strong>, coding<\/em><\/strong>, base substitution<\/em><\/strong>, and indel mutations<\/em><\/strong> per megabase of genome examined.<\/p>\n

\u8ba1\u7b97TMB\u7684\u6d41\u7a0b\uff1a<\/p>\n

    \n
  1. \u7edf\u8ba1\u5916\u663e\u5b50\u533a\u57df\u957f\u5ea6\uff08bed\u6587\u4ef6\uff09<\/li>\n
  2. \u4f7f\u7528ANNOVAR\u6ce8\u91cavcf\u6587\u4ef6\uff08\u57fa\u56e0\u540d\u5e93:refGene\uff0cgermline\u5e93\uff1aExAC\uff0cgenomad_exome\uff0c\u80bf\u7624Driver\u57fa\u56e0\u5e93\uff1acosmic70\uff09<\/li>\n
  3. \u7eb3\u5165\u7684\u7a81\u53d8\u7c7b\u578b\uff1a\u9664\u4e86non-coding\u548cunknown\u7684<\/li>\n
  4. \u8fc7\u6ee4germline\u7a81\u53d8\uff1apopulation frequency \u9700\u8981< 0.05<\/li>\n
  5. \u8fc7\u6ee4COSMIC driver mutation\uff1apopulation allele count \u9700\u8981<50<\/li>\n
  6. \u8fc7\u6ee4Tumor suppressor gene\u91cc\u9762\u7684stopgain\u7a81\u53d8<\/li>\n
  7. \u7edf\u8ba1\u5269\u4e0b\u7684\u6240\u6709\u7a81\u53d8\u6570\u5e76\u9664\u4ee5\u5916\u663e\u5b50\u957f\u5ea6\u4ece\u800c\u83b7\u5f97TMB<\/li>\n<\/ol>\n

    \u53ef\u8fd0\u884c\u811a\u672c<\/h4>\n
    #!\/usr\/bin\/env python\n"""\nThis is an open source Script written by K.Z. to calculate TMB from ANNOVAR annotated files\nThis scipt filters variants annotated by exac03,genomad41_exome using the user-defined Population Frequency cutoff and filters COSMIC driver mutations according to the variant population allele count\n"""\nimport argparse\nimport re\n#import vcf # pip install open-cravat -i https:\/\/pypi.tuna.tsinghua.edu.cn\/simple\/\nimport csv\n#from collections import defaultdict\nimport pandas as pd\nfrom io import StringIO\n\ndef main():\n    # Create a Custom ArgumentParser\n    parser = argparse.ArgumentParser(description='Calculate TMB from ANNOVAR annotated files')\n\n    # Set Input Argument\n    parser.add_argument('-sampleid', dest='sampleid', required=True, help="Sample name: EXAMPLE, if in multisample mode, this could be set as tumor name")\n    parser.add_argument('-input', dest='inputfile', required=True, help="TXT output of ANNOVAR annotated VCF file: EXAMPLE.hg38_multianno.txt")\n    parser.add_argument('-bed', dest='bedfile', required=True, help="BED file used in exome sequencing or BED files targeting exon region that want to be used to calculate TMB")\n    parser.add_argument('-annovar_db', dest='annovar_database', required=True, help="Databases used in ANNOVAR annotation, seperate using ',' and the following can be included: cosmic70,exac03,genomad41_exome")\n    parser.add_argument('-tsg', dest='tsgfile', required=True, help="Tumor suppressor genes with stopgain to exlude in TMB calculation, can be downloaded from https:\/\/bioinfo.uth.edu\/TSGene\/Human_TSGs.txt")\n    parser.add_argument('-populationfreqcutoff', dest='Population_Freq_cutoff', required=False, default=0.05, help="Population Frequency cutoff to filter in exac03,genomad41_exome, default is 0.05(5%%)")\n    parser.add_argument('-cosmiccutoff', dest='COSMIC_cutoff', required=False, default=50, help="Cutoff for COSMIC driver gene count to filter in cosmic70, default is 50")\n    parser.add_argument('-multisample', dest='multi_sample', required=False, default="FALSE", help="Whether the input file is merged with multiple samples, if set to TRUE, the input file must contain a column named SampleID, default is FALSE")\n    parser.add_argument("-V", "--version", action="version", version="TMB calculation Version 1.1")\n\n    # Parse Arguments\n    args = parser.parse_args()\n\n    # Obtain input and output file names\n    sample_id = args.sampleid\n    input_filename = args.inputfile\n    bed_file_name = args.bedfile\n    annovar_db = args.annovar_database\n    tsg_filename = args.tsgfile\n    Population_Freq_cutoff = args.Population_Freq_cutoff\n    Population_Freq_cutoff = float(Population_Freq_cutoff)\n    COSMIC_cutoff = args.COSMIC_cutoff\n    COSMIC_cutoff = int(COSMIC_cutoff)\n    multi_sample = args.multi_sample\n\n    # Load all files first\n    with open(input_filename, 'r') as f:\n        lines = [line for line in f if not line.startswith('##')]\n    input_file = pd.read_csv(StringIO(''.join(lines)), sep='\\t', header=0)\n    bed_file = pd.read_csv(bed_file_name, sep='\\t', header=None,comment='#')\n    # Calculate Total Chromosome length in the bed file\n    bed_file = bed_file.rename(columns={0: "Chr", 1: "Start", 2: "End"})\n    Exon_length = (bed_file['End']-bed_file['Start']).sum()\/1000000\n    # print("The Total length of exon regions is: ",Exon_length)\n    annovar_db_list = annovar_db.split(",")\n    tsg_file = pd.read_csv(tsg_filename, sep='\\t', header=0,comment='#')\n\n    if multi_sample == "FALSE":\n        print("Running TMB Calculation in ",sample_id)\n        # filter input file to exclude non-exon and exon functions unknown\n        input_file = input_file[~input_file['ExonicFunc.refGene'].isin(['.', 'unknown'])]\n        # print("non-exon and gene-exon with unknown functions have been filtered")\n\n        # Now Filter vcf files according to the criterias\n        for annovar_db_name in annovar_db_list:\n            if annovar_db_name=="cosmic70":\n                # print("Processing cosmic70 annotation...")\n                # filter cosmic genes with score over 50\n                cosmic70_sum = []\n                for value in input_file['cosmic70']:  # Replace `input_file['cosmic70']` with the correct reference\n                    # Extract all the numbers after "=" using regular expressions\n                    if value !=  ".":\n                        value = value.split("OCCURENCE=")[1]\n                        numbers = re.findall(r"\\d+\\.?\\d*", value)\n                    else:\n                        numbers = 0\n\n                    # Convert the extracted numbers to integers and calculate their sum\n                    if numbers != 0:\n                        sum_numbers = sum(int(num) for num in numbers)\n                    else:\n                        sum_numbers = 0  # In case no numbers are found\n\n                    # Append the sum to the cosmic70_sum list\n                    cosmic70_sum.append(sum_numbers)\n\n                # Add the new column to the DataFrame\n                input_file['cosmic70_sum'] = cosmic70_sum\n                input_file = input_file[input_file['cosmic70_sum'] < COSMIC_cutoff]\n                # print("There're ",len(input_file)," mutations left")\n            elif annovar_db_name=="exac03":\n                # print("Processing exac03 annotation...")\n                input_file['ExAC_ALL'] = input_file['ExAC_ALL'].replace('.', '0')\n                input_file['ExAC_ALL'] = input_file['ExAC_ALL'].astype(float)\n                input_file = input_file[input_file['ExAC_ALL'] < Population_Freq_cutoff]\n                # print("There're ",len(input_file)," mutations left")\n            elif annovar_db_name=="genomad41_exome":\n                # print("Processing genomad41_exome annotation...")\n                input_file['gnomAD_exome_ALL'] = input_file['gnomAD_exome_ALL'].replace('.', '0')\n                input_file['gnomAD_exome_ALL'] = input_file['gnomAD_exome_ALL'].astype(float)\n                input_file = input_file[input_file['gnomAD_exome_ALL'] < Population_Freq_cutoff]\n                # print("There're ",len(input_file)," mutations left")\n\n        # Filter TSGs with stopgain\n        tsg_gene_symbols = tsg_file["GeneSymbol"]\n\n        input_file = input_file[~((input_file["Gene.refGene"].isin(tsg_gene_symbols)) & (input_file["ExonicFunc.refGene"] == "stopgain"))]\n        # print("There're ",len(input_file)," mutations left")\n\n        # Calculate final mutation count\n        mut_count = len(input_file)\n        print("The total filtered mutation count in ", sample_id, " is: ", mut_count)\n        TMB_value = mut_count\/Exon_length\n\n        output_filename = str(sample_id)+"_TMB.txt"\n        print("Writing OutPut Files...")\n        with open(output_filename, 'w', newline='', encoding='utf-8') as outputfile:\n            writer = csv.writer(outputfile, delimiter='\\t')  # Use tab as delimiter\n            writer.writerow(["SampleID",\n                            "ExonLength",\n                            "MutCount",\n                            "TMB"])\n            writer.writerow([sample_id,\n                            Exon_length,\n                            mut_count,\n                            TMB_value])\n\n    elif multi_sample == "TRUE":\n        TMB_allsamples = {}\n        for tmp_sampleid in input_file['SampleID'].unique():\n            tmp_inputfile = input_file[input_file['SampleID'] == tmp_sampleid]\n            # print("Running TMB Calculation in ",tmp_sampleid)\n            # filter input file to exclude non-exon and exon functions unknown\n            tmp_inputfile = tmp_inputfile[~tmp_inputfile['ExonicFunc.refGene'].isin(['.', 'unknown'])]\n            # print("non-exon and gene-exon with unknown functions have been filtered")\n\n            # Now Filter vcf files according to the criterias\n            for annovar_db_name in annovar_db_list:\n                if annovar_db_name=="cosmic70":\n                    # print("Processing cosmic70 annotation...")\n                    # filter cosmic genes with score over 50\n                    cosmic70_sum = []\n                    for value in tmp_inputfile['cosmic70']:  # Replace `tmp_inputfile['cosmic70']` with the correct reference\n                        # Extract all the numbers after "=" using regular expressions\n                        if value !=  ".":\n                            value = value.split("OCCURENCE=")[1]\n                            numbers = re.findall(r"\\d+\\.?\\d*", value)\n                        else:\n                            numbers = 0\n\n                        # Convert the extracted numbers to integers and calculate their sum\n                        if numbers != 0:\n                            sum_numbers = sum(int(num) for num in numbers)\n                        else:\n                            sum_numbers = 0  # In case no numbers are found\n\n                        # Append the sum to the cosmic70_sum list\n                        cosmic70_sum.append(sum_numbers)\n\n                    # Add the new column to the DataFrame\n                    tmp_inputfile['cosmic70_sum'] = cosmic70_sum\n                    tmp_inputfile = tmp_inputfile[tmp_inputfile['cosmic70_sum'] < COSMIC_cutoff]\n                    # print("There're ",len(tmp_inputfile)," mutations left")\n\n                elif annovar_db_name=="exac03":\n                    # print("Processing exac03 annotation...")\n                    tmp_inputfile['ExAC_ALL'] = tmp_inputfile['ExAC_ALL'].replace('.', '0')\n                    tmp_inputfile['ExAC_ALL'] = tmp_inputfile['ExAC_ALL'].astype(float)\n                    tmp_inputfile = tmp_inputfile[tmp_inputfile['ExAC_ALL'] < Population_Freq_cutoff]\n                    # print("There're ",len(tmp_inputfile)," mutations left")\n\n                elif annovar_db_name=="genomad41_exome":\n                    # print("Processing genomad41_exome annotation...")\n                    tmp_inputfile['gnomAD_exome_ALL'] = tmp_inputfile['gnomAD_exome_ALL'].replace('.', '0')\n                    tmp_inputfile['gnomAD_exome_ALL'] = tmp_inputfile['gnomAD_exome_ALL'].astype(float)\n                    tmp_inputfile = tmp_inputfile[tmp_inputfile['gnomAD_exome_ALL'] < Population_Freq_cutoff]\n                    # print("There're ",len(tmp_inputfile)," mutations left")\n\n            # Filter TSGs with stopgain\n            # print("Removing  TSGs with stopgain...")\n            tsg_gene_symbols = tsg_file["GeneSymbol"]\n            tmp_inputfile = tmp_inputfile[~((tmp_inputfile["Gene.refGene"].isin(tsg_gene_symbols)) & (tmp_inputfile["ExonicFunc.refGene"] == "stopgain"))]\n            # print("There're ",len(tmp_inputfile)," mutations left")\n\n            # Calculate final mutation count\n            mut_count = len(tmp_inputfile)\n            print("The total filtered mutation count in ", tmp_sampleid, " is: ", mut_count)\n            TMB_value = mut_count\/Exon_length\n            #output_filename = str(tmp_sampleid)+"_TMB.txt"\n            #print("Writing OutPut Files of ",tmp_sampleid)\n            #with open(output_filename, 'w', newline='', encoding='utf-8') as outputfile:\n            #    writer = csv.writer(outputfile, delimiter='\\t')  # Use tab as delimiter\n            #    writer.writerow(["SampleID",\n            #                    "ExonLength",\n            #                    "MutCount",\n            #                    "TMB"])\n            #    writer.writerow([tmp_sampleid,\n            #                    Exon_length,\n            #                    mut_count,\n            #                    TMB_value])\n            TMB_allsamples[tmp_sampleid] = {\n                "ExonLength": Exon_length,\n                "MutCount": mut_count,\n                "TMB": TMB_value}\n\n        output_filename = str(sample_id)+"Samples_TMB.txt"\n        print("Writing OutPut Files of All Samples")\n        with open(output_filename, 'w', newline='', encoding='utf-8') as outputfile:\n            writer = csv.writer(outputfile, delimiter='\\t')  # Use tab as delimiter\n            writer.writerow(["SampleID",\n                            "ExonLength",\n                            "MutCount",\n                            "TMB"])\n            for sample_id, values in TMB_allsamples.items():\n                writer.writerow([sample_id, values['ExonLength'], values['MutCount'], values['TMB']])\n\nif __name__ == "__main__":\n    main()<\/code><\/pre>\n
    \u6784\u5efa\u6279\u91cf\u8fd0\u884c\u811a\u672c<\/h3>\n
    ls *.hg38_multianno.vcf | perl -ne 'chomp; my $name = $1 if ($_ =~ \/([^\\\/]+)\\.hg38\\_multianno\\.vcf\/); print "\/data02\/zhangmengmeng\/software\/kztools\/TMB\/TMBCalculation -sampleid $name -input $name.hg38_multianno.txt -bed \/data02\/zhangmengmeng\/database\/gatk_resource_bundle\/hg38\/AgilentV6_GRCh38_ex_region.sort.bed  -annovar_db cosmic70,exac03 -tsg \/data02\/zhangmengmeng\/software\/kztools\/TMB\/Human_TSGs.txt -populationfreqcutoff 0.05 -cosmiccutoff 50 && echo $name TMB ok\\n"'>TMBCalculation.sh\n\n# \u5c06\u7ed3\u679c\u6587\u4ef6\u8f93\u51fa\u6574\u5408\u5230\u4e00\u8d77\nawk 'FNR==1 && NR!=1 {next} {print}' *_TMB.txt > All_TMB.txt\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
    \u53c2\u8003\u94fe\u63a51 TMB\u7684\u5b9a\u4e49 TMB\u7684\u5b9a\u4e49\u5982\u4e0b\uff1aTMB was defined as the number of …<\/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-411","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\/411","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=411"}],"version-history":[{"count":9,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/411\/revisions"}],"predecessor-version":[{"id":471,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/posts\/411\/revisions\/471"}],"wp:attachment":[{"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/media?parent=411"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/categories?post=411"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kz-hub.tech\/index.php\/wp-json\/wp\/v2\/tags?post=411"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}