Update parameter_meta and fix centrifuge index locating.

2105f016 · JasperBoom · 801e82aa · 2105f016 · 2105f016 · 2105f016
Commit 2105f016 authored 5 years ago by JasperBoom
--- a/centrifuge.wdl
+++ b/centrifuge.wdl
@@ -68,6 +68,7 @@ task Build {
    }

    parameter_meta {
+        # inputs
        disableDifferenceCover: {description: "Disable use of the difference-cover sample.", category: "required"}
        conversionTable: {description: "List of UIDs (unique ID) and corresponding taxonomic IDs.", category: "required"}
        taxonomyTree: {description: "Taxonomic tree (e.g. nodes.dmp).", category: "required"}
@@ -79,6 +80,12 @@ task Build {
        ftabChars: {description: "Calculate an initial BW range with respect to this character.", category: "common"}
        kmerCount: {description: "Use <int> as kmer-size for counting the distinct number of k-mers in the input sequences.", category: "common"}
        sizeTable: {description: "List of taxonomic IDs and lengths of the sequences belonging to the same taxonomic IDs.", category: "common"}
+        threads: {description: "The number of threads to be used.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+        # outputs
+        outputIndex: {description: "Generated Centrifuge index."}
    }
 }

@@ -139,6 +146,7 @@ task Classify {
    }

    parameter_meta {
+        # inputs
        inputFormat: {description: "The format of the read file(s).", category: "required"}
        phred64: {description: "If set to true, Phred+64 encoding is used.", category: "required"}
        minHitLength: {description: "Minimum length of partial hits.", category: "required"}
@@ -151,13 +159,21 @@ task Classify {
        reportMaxDistinct: {description: "It searches for at most <int> distinct, primary assignments for each read or pair.", category: "common"}
        hostTaxIDs: {description: "A comma-separated list of taxonomic IDs that will be preferred in classification procedure.", category: "common"}
        excludeTaxIDs: {description: "A comma-separated list of taxonomic IDs that will be excluded in classification procedure.", category: "common"}
+        threads: {description: "The number of threads to be used.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+        # outputs
+        outputMetrics: {description: "File with Centrifuge metrics."}
+        outputClassification: {description: "File with the classification results."}
+        outputReport: {description: "File with a classification summary."}
    }
 }

 task Inspect {
    input {
        String printOption = "fasta"
-        String indexBasename
+        Array[File]+ indexFiles
        String outputPrefix

        Int? across
@@ -174,7 +190,7 @@ task Inspect {
        centrifuge-inspect \
        ~{outputOptions[printOption]} \
        ~{"--across " + across} \
-        ~{indexBasename} \
+        ~{sub(indexFiles[0], "\.[0-9]\.cf", "")} \
        > ~{outputPrefix + "/" + printOption}
    }

@@ -188,10 +204,16 @@ task Inspect {
    }

    parameter_meta {
+        # inputs
        printOption: {description: "The output option for inspect (fasta, summary, conversionTable, taxonomyTree, nameTable, sizeTable)", category: "required"}
        indexBasename: {description: "The basename of the index to be inspected.", category: "required"}
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        across: {description: "When printing FASTA output, output a newline character every <int> bases.", category: "common"}
+        memory: {description: "The amount of memory available to the job.", category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+        # outputs
+        outputInspect: {description: "Output file according to output option."}
    }
 }


--- a/minimap2.wdl
+++ b/minimap2.wdl
@@ -68,8 +68,7 @@ task Indexing {
        splitIndex: {description: "Split index for every ~NUM input bases.", category: "advanced"}
        cores: {description: "The number of cores to be used.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # output
        outputIndexFile: {description: "Indexed reference file."}
@@ -150,8 +149,7 @@ task Mapping {
        queryFile: {description: "Input fasta file.", category: "required"}
        cores: {description: "The number of cores to be used.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # output
        outputAlignmentFile: {description: "Mapping and alignment between collections of DNA sequences file."}

--- a/talon.wdl
+++ b/talon.wdl
@@ -64,8 +64,7 @@ task CreateAbundanceFileFromDatabase {
        whitelistFile: {description: "Whitelist file of transcripts to include in the output.", category: "advanced"}
        datasetsFile: {description: "A file indicating which datasets should be included.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputAbundanceFile: {description: "Abundance for each transcript in the TALON database across datasets."}
@@ -120,8 +119,7 @@ task CreateGtfFromDatabase {
        whitelistFile: {description: "Whitelist file of transcripts to include in the output.", category: "advanced"}
        datasetFile: {description: "A file indicating which datasets should be included.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputGTFfile: {description: "The genes, transcripts, and exons stored a TALON database in GTF format."}
@@ -160,13 +158,16 @@ task FilterTalonTranscripts {
    }

    parameter_meta {
+        # inputs
        databaseFile: {description: "TALON database.", category: "required"}
        annotationVersion: {description: "Which annotation version to use.", category: "required"}
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        pairingsFile: {description: "A file indicating which datasets should be considered together.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+        # outputs
+        outputTranscriptWhitelist: {description: "A transcript whitelist produced from the TALON database."}
    }
 }

@@ -208,8 +209,7 @@ task GetReadAnnotations {
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        datasetFile: {description: "A file indicating which datasets should be included.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputAnnotation: {description: "Read-specific annotation information from a TALON database."}
@@ -265,8 +265,7 @@ task InitializeTalonDatabase {
        cutoff3p: {description: "Maximum allowable distance (bp) at the 3' end during annotation.", category: "advanced"}
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputDatabase: {description: "TALON database."}
@@ -297,10 +296,13 @@ task ReformatGtf {
    }

    parameter_meta {
+        # inputs
        GTFfile: {description: "GTF annotation containing genes, transcripts, and edges.", category: "required"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}
+
+        # outputs
+        outputReformattedGTF: {description: "Reformatted GTF file."}
    }
 }

@@ -342,8 +344,7 @@ task SummarizeDatasets {
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        datasetGroupsCSV: {description: "File of comma-delimited dataset groups to process together.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputSummaryFile: {description: "Tab-delimited file of gene and transcript counts for each dataset."}
@@ -413,8 +414,7 @@ task Talon {
        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
        cores: {description: "The number of cores to be used.", category: "advanced"}
        memory: {description: "The amount of memory available to the job.", category: "advanced"}
-        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.",
-                      category: "advanced"}
+        dockerImage: {description: "The docker image used for this task. Changing this may result in errors which the developers may choose not to address.", category: "advanced"}

        # outputs
        outputUpdatedDatabase: {description: "Updated TALON database."}