Merge pull request #121 from matq007/issue-120

fix: upgrade `STAR` aligner and `STAR-Fusion`

build-ctat.nf

@@ -29,8 +29,6 @@ def helpMessage() {
     Mandatory arguments:
       --fasta [file]                Path to fasta reference
       --gtf [file]                  Path to GTF annotation
-      --reference_release [int]     Release number of Ensembl reference for FASTA and GTF
-                                    example: 97 -> ftp://ftp.ensembl.org/pub/release-97
       --outdir [path]               Output directory for downloading
       -profile [str]                Configuration profile [https://github.com/nf-core/configs]
     """.stripIndent()
@@ -40,21 +38,22 @@ def helpMessage() {
  * SET UP CONFIGURATION VARIABLES
  */
 
-// Show help emssage
+// Show help message
 if (params.help) exit 0, helpMessage()
 
-if (!params.reference_release) exit 1, "You did not specify the release number of reference!"
-if (!params.outdir) exit 1, "Output directory not specified!"
+params.fasta = params.genome ? params.genomes[params.genome].fasta ?: null : null
+params.gtf = params.genome ? params.genomes[params.genome].gtf ?: null : null
 
 ch_fasta = Channel.value(file(params.fasta)).ifEmpty{exit 1, "Fasta file not found: ${params.fasta}"}
 ch_gtf = Channel.value(file(params.gtf)).ifEmpty{exit 1, "GTF annotation file not found: ${params.gtf}"}
 
+if (!params.outdir) exit 1, "Output directory not specified!"
+
 // Header log info
 log.info nfcoreHeader()
 def summary = [:]
-summary['Pipeline Name']  = 'nf-core/rnafusion/download-references.nf'
+summary['Pipeline Name']  = 'nf-core/rnafusion/build-ctat.nf'
 summary['Pipeline Version'] = workflow.manifest.version
-summary['References']       = params.running_tools.size() == 0 ? 'None' : params.running_tools.join(", ")
 if(workflow.containerEngine) summary['Container'] = "$workflow.containerEngine - $workflow.container"
 summary['Max Resources']    = "$params.max_memory memory, $params.max_cpus cpus, $params.max_time time per job"
 summary['Output dir']   = params.outdir
@@ -73,6 +72,7 @@ checkHostname()
 
 process star_fusion {
     label 'process_high'
+    label 'process_long'
     publishDir "${params.outdir}", mode: 'copy'
 
     input:
@@ -100,7 +100,7 @@ process star_fusion {
     prep_genome_lib.pl \\
         --genome_fa ${fasta} \\
         --gtf ${gtf} \\
-        --annot_filter_rule /opt/conda/envs/star-fusion_v1.6.0/ctat-genome-lib-builder-2830cd708c5bb9353878ca98069427e83acdd625/AnnotFilterRuleLib/AnnotFilterRule.pm \\
+        --annot_filter_rule /opt/conda/envs/nf-core-rnafusion-star-fusion_1.8.1/ctat-genome-lib-builder-2830cd708c5bb9353878ca98069427e83acdd625/AnnotFilterRuleLib/AnnotFilterRule.pm \\
         --fusion_annot_lib CTAT_HumanFusionLib.dat.gz \\
         --pfam_db Pfam-A.hmm \\
         --dfam_db homo_sapiens_dfam.hmm \\
@@ -157,4 +157,4 @@ def checkHostname() {
             }
         }
     }
-}
+}

conf/base.config

@@ -11,20 +11,19 @@
 
 params {
     versions {
-    arriba = '1.1.0'
+    arriba = '1.1.0-star2.7.2b'
     ericscript = '0.5.5'
     fusioncatcher = '1.20'
-    fusion_inspector = '1.3.1-star2.7.0f'
     pizzly = '0.37.3'
-    squid = '1.5-star2.7.0f'
-    star_fusion = '1.6.0'
+    squid = '1.5-star2.7.2b'
+    star_fusion = '1.8.1'
   }
 }
 
 process {
   cpus = { check_max( 1 * task.attempt, 'cpus' ) }
   memory = { check_max( 7.GB * task.attempt, 'memory' ) }
-  time = { check_max( 4.h * task.attempt, 'time' ) }
+  time = { check_max( 6.h * task.attempt, 'time' ) }
 
   errorStrategy = { task.exitStatus in [143,137,104,134,139] ? 'retry' : 'finish' }
   maxRetries = 1
@@ -38,15 +37,15 @@ process {
   withLabel:process_medium {
     cpus = { check_max( 6 * task.attempt, 'cpus' ) }
     memory = { check_max( 42.GB * task.attempt, 'memory' ) }
-    time = { check_max( 8.h * task.attempt, 'time' ) }
+    time = { check_max( 12.h * task.attempt, 'time' ) }
   }
   withLabel:process_high {
     cpus = { check_max( 12 * task.attempt, 'cpus' ) }
     memory = { check_max( 84.GB * task.attempt, 'memory' ) }
-    time = { check_max( 10.h * task.attempt, 'time' ) }
+    time = { check_max( 24.h * task.attempt, 'time' ) }
   }
   withLabel:process_long {
-    time = { check_max( 20.h * task.attempt, 'time' ) }
+    time = { check_max( 48.h * task.attempt, 'time' ) }
   }
   withName:get_software_versions {
     cache = false
@@ -62,16 +61,13 @@ process {
   withName:fusioncatcher {
     container = "nfcore/rnafusion:fusioncatcher_${params.versions.fusioncatcher}"
   }
-  withName:fusion_inspector {
-    container = "nfcore/rnafusion:fusion-inspector_${params.versions.fusion_inspector}"
-  }
   withName:pizzly {
     container = "nfcore/rnafusion:pizzly_${params.versions.pizzly}"
   }
   withName:squid {
     container = "nfcore/rnafusion:squid_${params.versions.squid}"
   }
-  withName:"star_fusion" {
+  withName:"star_fusion|fusion_inspector" {
     container = "nfcore/rnafusion:star-fusion_${params.versions.star_fusion}"
   }
 }

containers/arriba/Dockerfile

@@ -8,7 +8,7 @@ COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-rnafusion-arriba_1.1.0/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-rnafusion-arriba_1.1.0-star2.7.2b/bin:$PATH
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-rnafusion-arriba_1.1.0 > nf-core-rnafusion-arriba_1.1.0.yml
+RUN conda env export --name nf-core-rnafusion-arriba_1.1.0-star2.7.2b > nf-core-rnafusion-arriba_1.1.0-star2.7.2b.yml

containers/arriba/environment.yml

@@ -1,4 +1,4 @@
-name: nf-core-rnafusion-arriba_1.1.0
+name: nf-core-rnafusion-arriba_1.1.0-star2.7.2b
 channels:
   - conda-forge
   - bioconda
@@ -8,7 +8,7 @@ dependencies:
   - bioconda::bioconductor-genomicalignments
   - bioconda::bioconductor-genomicranges
   - bioconda::samtools=1.9
-  - bioconda::star=2.7.0f
+  - bioconda::star=2.7.2b
   - conda-forge::openssl=1.0
   - conda-forge::r-circlize
   - conda-forge::readline=6.2

containers/squid/Dockerfile

@@ -8,12 +8,12 @@ COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.0f/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.2b/bin:$PATH
 
-RUN cd /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.0f/bin \
+RUN cd /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.2b/bin \
     && wget https://raw.githubusercontent.com/Kingsford-Group/squid/f45c9025d41cffd982ecbbdd52844e5a4f074de9/utils/AnnotateSQUIDOutput.py \
-    && chmod +x /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.0f/bin/AnnotateSQUIDOutput.py \
-    && ln -s /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.0f/bin/python3 /bin/python
+    && chmod +x /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.2b/bin/AnnotateSQUIDOutput.py \
+    && ln -s /opt/conda/envs/nf-core-rnafusion-squid_1.5-star2.7.2b/bin/python3 /bin/python
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-rnafusion-squid_1.5-star2.7.0f > nf-core-rnafusion-squid_1.5-star2.7.0f.yml
+RUN conda env export --name nf-core-rnafusion-squid_1.5-star2.7.2b > nf-core-rnafusion-squid_1.5-star2.7.2b.yml

containers/squid/environment.yml

@@ -1,11 +1,11 @@
-name: nf-core-rnafusion-squid_1.5-star2.7.0f
+name: nf-core-rnafusion-squid_1.5-star2.7.2b
 channels:
   - conda-forge
   - bioconda
   - defaults
 dependencies:
   - bioconda::samtools=1.9
   - bioconda::squid=1.5
-  - bioconda::star=2.7.0f
+  - bioconda::star=2.7.2b
   - conda-forge::numpy=1.18.1
   - conda-forge::python=3.7.6

containers/star-fusion/Dockerfile

@@ -8,19 +8,13 @@ COPY environment.yml /
 RUN conda env create -f /environment.yml && conda clean -a
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
-ENV PATH /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/bin:$PATH
+ENV PATH /opt/conda/envs/nf-core-rnafusion-star-fusion_1.8.1/bin:$PATH
 
-# ctat-genome-lib-builder
-RUN cd /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/ && \
-    wget https://github.com/NCIP/ctat-genome-lib-builder/archive/2830cd708c5bb9353878ca98069427e83acdd625.zip && \
-    unzip 2830cd708c5bb9353878ca98069427e83acdd625.zip && \
-    cd ctat-genome-lib-builder-2830cd708c5bb9353878ca98069427e83acdd625 && \
-    rm /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/bin/prep_genome_lib.pl
-
-ENV PATH /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/ctat-genome-lib-builder-2830cd708c5bb9353878ca98069427e83acdd625/:$PATH
+# FusionInspector
+ENV PATH /opt/conda/envs/nf-core-rnafusion-star-fusion_1.8.1/lib/STAR-Fusion/FusionInspector:$PATH
 
-RUN ln -s /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/lib/libssl.so /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/lib/libssl.so.1.0.0 && \
-    ln -s /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/lib/libcrypto.so /opt/conda/envs/nf-core-rnafusion-star-fusion_1.6.0/lib/libcrypto.so.1.0.0
+# ctat-genome-lib-builder
+ENV PATH /opt/conda/envs/nf-core-rnafusion-star-fusion_1.8.1/lib/STAR-Fusion/ctat-genome-lib-builder:$PATH
 
 # Dump the details of the installed packages to a file for posterity
-RUN conda env export --name nf-core-rnafusion-star-fusion_1.6.0 > nf-core-rnafusion-star-fusion_1.6.0.yml
+RUN conda env export --name nf-core-rnafusion-star-fusion_1.8.1 > nf-core-rnafusion-star-fusion_1.8.1.yml

containers/star-fusion/environment.yml

@@ -1,13 +1,11 @@
-name: nf-core-rnafusion-star-fusion_1.6.0
+name: nf-core-rnafusion-star-fusion_1.8.1
 channels:
   - conda-forge
   - bioconda
   - defaults
 dependencies:
   - bioconda::dfam=2.0
   - bioconda::hmmer=3.2.1
-  - bioconda::star-fusion=1.6.0
-  - bioconda::star=2.7.0f
+  - bioconda::star-fusion=1.8.1
   - bioconda::trinity=2.6.6
-  - conda-forge::perl-carp-assert
-  - conda-forge::unzip=6.0
+  - conda-forge::perl-carp-assert

environment.yml

@@ -14,7 +14,7 @@ dependencies:
   - bioconda::fastqc=0.11.8
   - bioconda::multiqc=1.7
   # Custom packages
-  - bioconda::star=2.7.0f # update STAR-Fusion and Fusion-Inspector, Arriba
+  - bioconda::star=2.7.1a # has to be for star index
   - conda-forge::r-data.table=1.12.8
   - conda-forge::r-gplots=3.0.1.2
   - bioconda::bioconductor-edger=3.28.0

main.nf

@@ -709,7 +709,7 @@ process fusion_inspector {
         file(reference) from reference.fusion_inspector
 
     output:
-        file("*.{fa,gtf,bed,bam,bai,txt}") into fusion_inspector_output
+        file("*.{fa,gtf,bed,bam,bai,txt,html}") into fusion_inspector_output
 
     when: params.fusion_inspector && (!params.single_end || params.debug)
 
@@ -722,8 +722,9 @@ process fusion_inspector {
         --left_fq ${reads[0]} \\
         --right_fq ${reads[1]} \\
         --CPU ${task.cpus} \\
-        --out_dir . \\
+        -O . \\
         --out_prefix finspector \\
+        --vis \\
         ${extra_params} 
     """
 }
@@ -754,7 +755,7 @@ process get_software_versions {
     multiqc --version > v_multiqc.txt
     cat ${baseDir}/containers/arriba/environment.yml > v_arriba.txt
     cat ${baseDir}/containers/fusioncatcher/environment.yml > v_fusioncatcher.txt
-    cat ${baseDir}/containers/fusion-inspector/environment.yml > v_fusion_inspector.txt
+    cat ${baseDir}/containers/star-fusion/environment.yml > v_fusion_inspector.txt
     cat ${baseDir}/containers/star-fusion/environment.yml > v_star_fusion.txt
     cat ${baseDir}/containers/ericscript/environment.yml > v_ericscript.txt
     cat ${baseDir}/containers/pizzly/environment.yml > v_pizzly.txt

scripts/download-singularity-img.sh

@@ -22,7 +22,6 @@ elif [ -d "$1" ]; then
     ARRIBA=$(get_tool_version "arriba")
     ERICSCRIPT=$(get_tool_version "ericscript")
     FUSIONCATCHER=$(get_tool_version "fusioncatcher")
-    FUSION_INSPECTOR=$(get_tool_version "fusion_inspector")
     PIZZLY=$(get_tool_version "pizzly")
     RNAFUSION="$(cat nextflow.config | grep -m1 "container" | cut -d":" -f2 | cut -d "'" -f1)"
     SQUID=$(get_tool_version "squid")
@@ -33,7 +32,6 @@ elif [ -d "$1" ]; then
     singularity pull --name "${PREFIX}-arriba_${ARRIBA}.img" docker://nfcore/rnafusion:arriba_${ARRIBA}
     singularity pull --name "${PREFIX}-ericscript_${ERICSCRIPT}.img" docker://nfcore/rnafusion:ericscript_${ERICSCRIPT}
     singularity pull --name "${PREFIX}-fusioncatcher_${FUSIONCATCHER}.img" docker://nfcore/rnafusion:fusioncatcher_${FUSIONCATCHER}
-    singularity pull --name "${PREFIX}-fusion-inspector_${FUSION_INSPECTOR}.img" docker://nfcore/rnafusion:fusion-inspector_${FUSION_INSPECTOR}
     singularity pull --name "${PREFIX}-pizzly_${PIZZLY}.img" docker://nfcore/rnafusion:pizzly_${PIZZLY}
     singularity pull --name "${PREFIX}-${RNAFUSION}.img" docker://nfcore/rnafusion:${RNAFUSION}
     singularity pull --name "${PREFIX}-squid_${SQUID}.img" docker://nfcore/rnafusion:squid_${SQUID}