Merge remote-tracking branch 'origin' into BIOWDL-475

CHANGELOG.md

@@ -11,6 +11,11 @@ that users understand how the changes affect the new version.
 
 version 4.0.0-develop
 ---------------------------
++ TALON: Update `FilterTalonTranscripts` to new version, which removes the
+  pairingsFile and replaces this with datasetsFile.
++ TALON: Add `GetSpliceJunctions` & `LabelReads` tasks.
++ TALON: Update to version 5.0.
++ Add tasks for pbmm2, the PacBio wrapper for minimap2.
 + Update the image for chunked-scatter and make use of new features from 0.2.0.
 + Tuned resource requirements for GATK VariantEval, MultiQC, Picard metrics and 
   STAR.

pbmm2.wdl

+version 1.0
+
+# Copyright (c) 2020 Leiden University Medical Center
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+task Mapping {
+    input {
+        String presetOption
+        Boolean sort=true
+        String sample
+        File referenceMMI
+        File queryFile
+
+        Int cores = 4
+        String memory = "30G"
+        Int timeMinutes = 1 + ceil(size(queryFile, "G") * 200 / cores)
+        String dockerImage = "quay.io/biocontainers/pbmm2:1.3.0--h56fc30b_1"
+    }
+
+    command {
+        pbmm2 align \
+        --preset ~{presetOption} \
+        ~{true="--sort" false="" sort} \
+        -j ~{cores} \
+        ~{referenceMMI} \
+        ~{queryFile} \
+        ~{sample}.align.bam
+    }
+
+    output {
+        File outputAlignmentFile = sample + ".align.bam"
+        File outputIndexFile = sample + ".align.bam.bai"
+    }
+
+    runtime {
+        cpu: cores
+        memory: memory
+        time_minutes: timeMinutes
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        presetOption: {description: "This option applies multiple options at the same time.", category: "required"}
+        sort: {description: "Sort the output bam file.", category: "advanced"}
+        sample: {description: "Name of the sample"}
+        referenceMMI: {description: "MMI file for the reference.", category: "required"}
+        queryFile: {description: "BAM file with reads to align against the reference.", 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"}
+        timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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: "Mapped bam file."}
+        outputIndexFile: {description: "Bam index file."}
+    }
+}

scripts @ 325a129c

-Subproject commit b83da72b9b43b956a3062b78fb08044eb9fae464
+Subproject commit 325a129c14de56b2055ee0e9e0da7dc74df5fec4

talon.wdl

@@ -32,7 +32,7 @@ task CreateAbundanceFileFromDatabase {
 
         String memory = "4G"
         Int timeMinutes = 30
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -88,7 +88,7 @@ task CreateGtfFromDatabase {
 
         String memory = "4G"
         Int timeMinutes = 30
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -137,12 +137,16 @@ task FilterTalonTranscripts {
         File databaseFile
         String annotationVersion
         String outputPrefix
+        Float maxFracA = 0.5
+        Int minCount = 5
+        Boolean allowGenomic = false
 
-        File? pairingsFile
+        File? datasetsFile
+        Int? minDatasets
 
         String memory = "4G"
         Int timeMinutes = 30
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -152,7 +156,11 @@ task FilterTalonTranscripts {
         --db=~{databaseFile} \
         -a ~{annotationVersion} \
         ~{"--o=" + outputPrefix + "_whitelist.csv"} \
-        ~{"-p " + pairingsFile}
+        --maxFracA=~{maxFracA} \
+        --minCount=~{minCount} \
+        ~{true="--allowGenomic" false="" allowGenomic} \
+        --datasets=~{datasetsFile} \
+        --minDatasets=~{minDatasets}
     }
 
     output {
@@ -170,7 +178,11 @@ task FilterTalonTranscripts {
         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"}
+        maxFracA: {description: "Maximum fraction of As to allow in the window located immediately after any read assigned to a novel transcript.", category: "advanced"}
+        minCount: {description: "Number of minimum occurrences required for a novel transcript PER dataset.", category: "advanced"}
+        allowGenomic: {description: "If this option is set, transcripts from the Genomic novelty category will be permitted in the output.", category: "advanced"}
+        datasetsFile: {description: "Datasets to include.", category: "advanced"}
+        minDatasets: {description: "Minimum number of datasets novel transcripts must be found in.", category: "advanced"}
         memory: {description: "The amount of memory available to the job.", category: "advanced"}
         timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}
@@ -190,7 +202,7 @@ task GetReadAnnotations {
 
         String memory = "4G"
         Int timeMinutes = 30
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -228,6 +240,57 @@ task GetReadAnnotations {
     }
 }
 
+task GetSpliceJunctions {
+    input {
+        File SJinformationFile
+        String inputFileType = "db"
+        File referenceGTF
+        String runMode = "intron"
+        String outputPrefix
+
+        String memory = "4G"
+        Int timeMinutes = 30
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
+    }
+
+    Map[String, String] SJfileType = {"db": "--db", "gtf": "--gtf"}
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPrefix})"
+        talon_get_sjs \
+        ~{SJfileType[inputFileType] + SJinformationFile} \
+        --ref ~{referenceGTF} \
+        --mode ~{runMode} \
+        --outprefix ~{outputPrefix}
+    }
+
+    output {
+        File outputSJfile = outputPrefix + "_" + runMode + "s.tsv"
+    }
+
+    runtime {
+        memory: memory
+        time_minutes: timeMinutes
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        SJinformationFile: {description: "TALON GTF file or database from which to extract exons/introns.", category: "required"}
+        inputFileType: {description: "The file type of SJinformationFile.", category: "common"}
+        referenceGTF: {description: "GTF reference file (ie GENCODE).", category: "required"}
+        runMode: {description: "Determines whether to include introns or exons in the output.", category: "common"}
+        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
+        memory: {description: "The amount of memory available to the job.", category: "advanced"}
+        timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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
+        outputSJfile: {description: "File containing locations, novelty and transcript assignments of exons/introns."}
+    }
+}
+
 task InitializeTalonDatabase {
     input {
         File GTFfile
@@ -241,7 +304,7 @@ task InitializeTalonDatabase {
 
         String memory = "10G"
         Int timeMinutes = 60
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -287,13 +350,72 @@ task InitializeTalonDatabase {
     }
 }
 
+task LabelReads {
+    input {
+        File SAMfile
+        File referenceGenome
+        Int fracaRangeSize = 20
+        String tmpDir = "./tmp_label_reads"
+        Boolean deleteTmp = true
+        String outputPrefix
+
+        Int threads = 4
+        String memory = "25G"
+        Int timeMinutes = 2880
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
+    }
+
+    command {
+        set -e
+        mkdir -p "$(dirname ~{outputPrefix})"
+        talon_label_reads \
+        --f=~{SAMfile} \
+        --g=~{referenceGenome} \
+        --t=~{threads} \
+        --ar=~{fracaRangeSize} \
+        --tmpDir=~{tmpDir} \
+        ~{true="--deleteTmp" false="" deleteTmp} \
+        --o=~{outputPrefix}
+    }
+
+    output {
+        File outputLabeledSAM = outputPrefix + "_labeled.sam"
+        File outputReadLabels = outputPrefix + "_read_labels.tsv"
+    }
+
+    runtime {
+        cpu: threads
+        memory: memory
+        time_minutes: timeMinutes
+        docker: dockerImage
+    }
+
+    parameter_meta {
+        # inputs
+        SAMfile: {description: "SAM file of transcripts.", category: "required"}
+        referenceGenome: {description: "Reference genome fasta file.", category: "required"}
+        fracaRangeSize: {description: "Size of post-transcript interval to compute fraction.", category: "common"}
+        tmpDir: {description: "Path to directory for tmp files.", category: "advanced"}
+        deleteTmp: {description: "If set, tmp dir will be removed.", category: "advanced"}
+        outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
+        threads: {description: "The number of threads to be used.", category: "advanced"}
+        memory: {description: "The amount of memory available to the job.", category: "advanced"}
+        timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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
+        outputLabeledSAM: {description: "SAM file with labeled transcripts."}
+        outputReadLabels: {description: "Tabular file with fraction description per read."}
+    }
+}
+
 task ReformatGtf {
     input {
         File GTFfile
 
         String memory = "4G"
         Int timeMinutes = 30
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -334,7 +456,7 @@ task SummarizeDatasets {
 
         String memory = "4G"
         Int timeMinutes = 50
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command {
@@ -383,10 +505,10 @@ task Talon {
         Float minimumIdentity = 0.8
         String outputPrefix
 
-        Int cores = 4
+        Int threads = 4
         String memory = "25G"
         Int timeMinutes = 2880
-        String dockerImage = "biocontainers/talon:v4.4.2_cv1"
+        String dockerImage = "biocontainers/talon:v5.0_cv1"
     }
 
     command <<<
@@ -405,7 +527,7 @@ task Talon {
         ~{"--f " + outputPrefix + "/talonConfigFile.csv"} \
         --db ~{databaseFile} \
         --build ~{genomeBuild} \
-        --threads ~{cores} \
+        --threads ~{threads} \
         --cov ~{minimumCoverage} \
         --identity ~{minimumIdentity} \
         ~{"--o " + outputPrefix + "/run"}
@@ -419,7 +541,7 @@ task Talon {
     }
 
     runtime {
-        cpu: cores
+        cpu: threads
         memory: memory
         time_minutes: timeMinutes
         docker: dockerImage
@@ -435,7 +557,7 @@ task Talon {
         minimumCoverage: {description: "Minimum alignment coverage in order to use a SAM entry.", category: "common"}
         minimumIdentity: {description: "Minimum alignment identity in order to use a SAM entry.", category: "common" }
         outputPrefix: {description: "Output directory path + output file prefix.", category: "required"}
-        cores: {description: "The number of cores to be used.", category: "advanced"}
+        threads: {description: "The number of threads to be used.", category: "advanced"}
         memory: {description: "The amount of memory available to the job.", category: "advanced"}
         timeMinutes: {description: "The maximum amount of time the job will run in minutes.", 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"}