Identification of somatic and germline variants from tumor and normal sample pairs tutorial

Last updated Oct 10, 2020

Launch in Tutorial Mode question
License: None Specified, defaults to CC-BY-4.0
Tests: ✅ Results: Not yet automated

flowchart TD
  0["ℹ️ Input Dataset\nSLGFSK-N_231335_r1_chr5_12_17.fastq"];
  style 0 stroke:#2c3143,stroke-width:4px;
  1["ℹ️ Input Dataset\nSLGFSK-N_231335_r2_chr5_12_17.fastq"];
  style 1 stroke:#2c3143,stroke-width:4px;
  2["ℹ️ Input Dataset\nSLGFSK-T_231336_r1_chr5_12_17.fastq"];
  style 2 stroke:#2c3143,stroke-width:4px;
  3["ℹ️ Input Dataset\nSLGFSK-T_231336_r2_chr5_12_17.fastq"];
  style 3 stroke:#2c3143,stroke-width:4px;
  4["ℹ️ Input Dataset\nhg19.chr5_12_17.fa"];
  style 4 stroke:#2c3143,stroke-width:4px;
  5["ℹ️ Input Dataset\nhotspots.bed"];
  style 5 stroke:#2c3143,stroke-width:4px;
  6["ℹ️ Input Dataset\ncgi_variant_positions.bed"];
  style 6 stroke:#2c3143,stroke-width:4px;
  7["ℹ️ Input Dataset\n01-Feb-2019-CIVic.bed"];
  style 7 stroke:#2c3143,stroke-width:4px;
  8["ℹ️ Input Dataset\ndbsnp.b147.chr5_12_17.vcf.gz"];
  style 8 stroke:#2c3143,stroke-width:4px;
  9["ℹ️ Input Dataset\nUniprot_Cancer_Genes.13Feb2019.txt"];
  style 9 stroke:#2c3143,stroke-width:4px;
  10["ℹ️ Input Dataset\ncgi_genes.txt"];
  style 10 stroke:#2c3143,stroke-width:4px;
  11["ℹ️ Input Dataset\n01-Feb-2019-GeneSummaries.tsv"];
  style 11 stroke:#2c3143,stroke-width:4px;
  12["FastQC"];
  0 -->|output| 12;
  13["FastQC"];
  1 -->|output| 13;
  14["Trimmomatic"];
  0 -->|output| 14;
  1 -->|output| 14;
  15["FastQC"];
  2 -->|output| 15;
  16["FastQC"];
  3 -->|output| 16;
  17["Trimmomatic"];
  2 -->|output| 17;
  3 -->|output| 17;
  18["FastQC"];
  14 -->|fastq_out_r2_paired| 18;
  19["FastQC"];
  14 -->|fastq_out_r1_paired| 19;
  20["Map with BWA-MEM"];
  14 -->|fastq_out_r1_paired| 20;
  14 -->|fastq_out_r2_paired| 20;
  21["MultiQC"];
  13 -->|text_file| 21;
  15 -->|text_file| 21;
  16 -->|text_file| 21;
  12 -->|text_file| 21;
  22["FastQC"];
  17 -->|fastq_out_r1_paired| 22;
  23["FastQC"];
  17 -->|fastq_out_r2_paired| 23;
  24["Map with BWA-MEM"];
  17 -->|fastq_out_r1_paired| 24;
  17 -->|fastq_out_r2_paired| 24;
  25["Filter"];
  20 -->|bam_output| 25;
  26["MultiQC"];
  19 -->|text_file| 26;
  22 -->|text_file| 26;
  23 -->|text_file| 26;
  18 -->|text_file| 26;
  27["Filter"];
  24 -->|bam_output| 27;
  28["RmDup"];
  25 -->|out_file1| 28;
  29["RmDup"];
  27 -->|out_file1| 29;
  30["BamLeftAlign"];
  28 -->|output1| 30;
  31["BamLeftAlign"];
  29 -->|output1| 31;
  32["CalMD"];
  30 -->|output_bam| 32;
  33["CalMD"];
  31 -->|output_bam| 33;
  34["Filter"];
  32 -->|calmd_output| 34;
  35["Filter"];
  33 -->|calmd_output| 35;
  36["VarScan somatic"];
  34 -->|out_file1| 36;
  35 -->|out_file1| 36;
  37["SnpEff eff:"];
  36 -->|output| 37;
  38["GEMINI load"];
  37 -->|snpeff_output| 38;
  39["GEMINI annotate"];
  36 -->|output| 39;
  38 -->|outfile| 39;
  40["GEMINI annotate"];
  8 -->|output| 40;
  39 -->|outfile| 40;
  41["GEMINI annotate"];
  5 -->|output| 41;
  40 -->|outfile| 41;
  42["GEMINI annotate"];
  7 -->|output| 42;
  41 -->|outfile| 42;
  43["GEMINI annotate"];
  6 -->|output| 43;
  42 -->|outfile| 43;
  44["GEMINI query"];
  43 -->|outfile| 44;
  45["GEMINI query"];
  43 -->|outfile| 45;
  46["GEMINI query"];
  43 -->|outfile| 46;
  47["GEMINI query"];
  43 -->|outfile| 47;
  48["Join"];
  47 -->|outfile| 48;
  9 -->|output| 48;
  49["Join"];
  48 -->|output| 49;
  10 -->|output| 49;
  50["Join"];
  49 -->|output| 50;
  11 -->|output| 50;
  51["Column arrange"];
  50 -->|output| 51;
  dab02ec2-5aac-47bc-9075-34417a4ea850["Output\ngene_report_output"];
  51 --> dab02ec2-5aac-47bc-9075-34417a4ea850;
  style dab02ec2-5aac-47bc-9075-34417a4ea850 stroke:#2c3143,stroke-width:4px;