edger.yaml

{
  id: edger,
  name: edgeR,
  article: "10.18129/B9.bioc.edgeR",
  website: "http://bioconductor.org/packages/release/bioc/html/edgeR.html",
  git: "git clone https://git.bioconductor.org/packages/edgeR",
  description: "Empirical Analysis of Digital Gene Expression Data.",
  version: "3.14.0",
  documentation: "http://bioconductor.org/packages/release/bioc/manuals/edgeR/man/edgeR.pdf",
  multiqc: "custom",
  commands:
    [
      {
        name: edger,
        command: ~,
        category: "differential_expression",
        output_dir: edger,
        inputs: 
          [
            { name: counts, type: "tsv" },
            { name: group_file, type: "popmap", file: "", description: "Path to tsv file with samples conditions"},
          ],
        outputs:
          [
            { name: de_table, type: "csv", file: de_table.csv, description: "Tableau d'expression différentielle" },
            { name: RData, type: "RData", file: data.RData, description: "Sauvegarde de la session R" },
            { name: PCA, type: "png", file: PCA_mqc.png, description: "PCA plot" },
            { name: Top_genes, type: "tsv", file: Top_genes_mqc.tsv, description: "Tableau des top gènes" },
            { name: Heatmap, type: "png", file: Heatmap_mqc.png, description: "Heatmap" },
          ],
        options:
          [
            {
              name: edger_threads,
              prefix: -t,
              type: numeric,
              value: 4,
              min: 1,
              max: NA,
              step: 1,
              label: "Number of threads to use",
            },
            {
              name: "edger_tx2gene",
              type: "checkbox",
              value: FALSE,
              label: "Aggregate transcripts counts to gene counts : ",
            },
            {
              name: "edger_annotations",
              type: "input_file",
              value: "",
              label: "Annotation file (gtf or gff) : ",
            },
            {
              name: edger_normfact,
              type: radio,
              value: "TMM",
              choices:
                [TMM: TMM, RLE: RLE, upperquartile: upperquartile, none: none],
              label: "Calculate normalization factors to scale the raw library sizes.",
            },
            {
              name: "edger_dispersion",
              type: "text",
              value: "0",
              label: "Dispersion: either a numeric vector of dispersions or a character string indicating that dispersions should be taken from the data.",
            },
            {
              name: edger_testType,
              type: radio,
              value: "exactTest",
              choices: [exactTest: exactTest, glmLRT: glmLRT],
              label: "Test type: exactTest: Computes p-values for differential abundance for each gene between two samples, conditioning on the total count for each gene. The counts in each group are assumed to follow a binomial distribution. glmLRT: Fits a negative binomial generalized log-linear model to the read counts for each gene and conducts genewise statistical tests.",
            },
          ],
      },
    ],
  install:
    {
      limma: ['Rscript -e ''BiocManager::install("limma", version = "3.8",Ncpus=8, clean=TRUE);library("limma")'''],
      edger: ['Rscript -e ''BiocManager::install("edgeR", version = "3.8",Ncpus=8, clean=TRUE);library("edgeR")'''],
      tximport: ['Rscript -e ''BiocManager::install("tximport", version = "3.8",Ncpus=8, clean=TRUE);library("tximport")'''],
      rhdf5: ['Rscript -e ''BiocManager::install("rhdf5", version = "3.8",Ncpus=8, clean=TRUE);library("rhdf5")'''],
      GenomicFeatures: ['Rscript -e ''BiocManager::install("GenomicFeatures", version = "3.8",Ncpus=8, clean=TRUE);library("GenomicFeatures")'''],
      pheatmap: ['Rscript -e ''install.packages("pheatmap",Ncpus=8, clean=TRUE);library("pheatmap"))''']
    },
  script: edger.script.R,
  citations:  {
    edger: [
      "Robinson MD, McCarthy DJ, Smyth GK (2010). edgeR: a Bioconductor package for differential expression analysis of digital gene expression data. Bioinformatics, 26(1), 139-140. doi: 10.1093/bioinformatics/btp616"
    ],
    limma: [
      "Ritchie ME, Phipson B, Wu D, Hu Y, Law CW, Shi W, Smyth GK (2015). limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Research, 43(7), e47. doi: 10.1093/nar/gkv007"
    ],
    tximport: [
      "Soneson C, Love MI, Robinson MD (2015). Differential analyses for RNA-seq: transcript-level estimates improve gene-level inferences. F1000Research, 4. doi: 10.12688/f1000research.7563.1"
    ],
    GenomicFeatures: [
      "Lawrence M, Huber W, Pagès H, Aboyoun P, Carlson M, et al. (2013) Software for Computing and Annotating Genomic Ranges. PLOS Computational Biology 9(8): e1003118. https://doi.org/10.1371/journal.pcbi.1003118"
    ],
    pheatmap: [
      "Kolde, R. (2012). Pheatmap: pretty heatmaps. R package version, 61, 617"
    ]
  }
}