Merge branch 'master' into crukmi

.editorconfig

@@ -8,5 +8,5 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml}]
+[*.{md,yml,yaml,cff}]
 indent_size = 2

CITATION.cff

@@ -0,0 +1,56 @@
+cff-version: 1.2.0
+message: "If you use `nf-core tools` in your work, please cite the `nf-core` publication"
+authors:
+  - family-names: Ewels
+    given-names: Philip
+  - family-names: Peltzer
+    given-names: Alexander
+  - family-names: Fillinger
+    given-names: Sven
+  - family-names: Patel
+    given-names: Harshil
+  - family-names: Alneberg
+    given-names: Johannes
+  - family-names: Wilm
+    given-names: Andreas
+  - family-names: Ulysse Garcia
+    given-names: Maxime
+  - family-names: Di Tommaso
+    given-names: Paolo
+  - family-names: Nahnsen
+    given-names: Sven
+title: "The nf-core framework for community-curated bioinformatics pipelines."
+version: 2.4.1
+doi: 10.1038/s41587-020-0439-x
+date-released: 2022-05-16
+url: https://github.com/nf-core/tools
+prefered-citation:
+  type: article
+  authors:
+    - family-names: Ewels
+      given-names: Philip
+    - family-names: Peltzer
+      given-names: Alexander
+    - family-names: Fillinger
+      given-names: Sven
+    - family-names: Patel
+      given-names: Harshil
+    - family-names: Alneberg
+      given-names: Johannes
+    - family-names: Wilm
+      given-names: Andreas
+    - family-names: Ulysse Garcia
+      given-names: Maxime
+    - family-names: Di Tommaso
+      given-names: Paolo
+    - family-names: Nahnsen
+      given-names: Sven
+  doi: 10.1038/s41587-020-0439-x
+  journal: nature biotechnology
+  start: 276
+  end: 278
+  title: "The nf-core framework for community-curated bioinformatics pipelines."
+  issue: 3
+  volume: 38
+  year: 2020
+  url: https://dx.doi.org/10.1038/s41587-020-0439-x

README.md

@@ -199,6 +199,7 @@ Currently documentation is available for the following pipelines within specific
 - mag
   - [EVA](docs/pipeline/mag/eva.md)
 - rnafusion
+  - [HASTA](docs/pipeline/rnafusion/hasta.md)
   - [MUNIN](docs/pipeline/rnafusion/munin.md)
 - rnavar
   - [MUNIN](docs/pipeline/rnavar/munin.md)

conf/cheaha.config

@@ -5,9 +5,15 @@ params {
     config_profile_url = 'https://www.uab.edu/cores/ircp/bds'
 }
 
+env {
+    TMPDIR="$USER_SCRATCH"
+    SINGULARITY_TMPDIR="$USER_SCRATCH"
+}
+
 singularity {
     enabled = true
     autoMounts = true
+    runOptions = "--contain --workdir $USER_SCRATCH"
 }
 
 process {

conf/google.config

@@ -19,4 +19,6 @@ google.lifeSciences.preemptible = params.google_preemptible
 if (google.lifeSciences.preemptible) {
   process.errorStrategy = { task.exitStatus in [8,10,14] ? 'retry' : 'terminate' }
   process.maxRetries = 5
-}
+}
+
+process.machineType = { task.memory > task.cpus * 6.GB ? ['custom', task.cpus, task.cpus * 6656].join('-') : null }

conf/hasta.config

@@ -16,19 +16,29 @@ singularity {
 params {
     max_memory = 180.GB
     max_cpus   = 36
-    max_time   = 336.h    
+    max_time   = 336.h
 }
 
 process {
     executor = 'slurm'
-    clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''}" }    
+    clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''}" }
 }
 
 profiles {
-    dev_prio {
+    stub_prio {
         params {
            priority = 'development'
            clusterOptions = "--qos=low"
+           max_memory = 6.GB
+           max_cpus   = 1
+           max_time   = 1.h
+        }
+    }
+
+    dev_prio {
+        params {
+            priority = 'development'
+            clusterOptions = "--qos=low"
         }
     }
 

conf/pipeline/raredisease/hasta.config

@@ -1,5 +1,5 @@
 process {
-    
+
     withName:'PICARD_MARKDUPLICATES' {
         memory = { check_max( 90.GB  * task.attempt, 'memory' ) }
     }
@@ -7,7 +7,26 @@ process {
         cpus   = { check_max( 16      * task.attempt, 'cpus' ) }
         memory = { check_max( 80.GB   * task.attempt, 'memory' ) }
     }
-    withName:'QUALIMAP_BAMQC' {
+    withLabel:'sentieon' {
-        ext.args = { "--java-mem-size=${task.memory.giga / 1.15 as long}G" }
+        beforeScript = { "export PATH=\$PATH:\$SENTIEON_INSTALL_DIR/sentieon-genomics-202112.02/bin" }
     }
-}
+    withName: 'BCFTOOLS_VIEW' {
+        if (params.genome == 'GRCh37') {
+            ext.args = '--output-type z --apply-filters PASS --exclude "INFO/clinical_genomics_mipAF > 0.40 | INFO/swegenAF > 0.40 | INFO/clingen_ngiAF > 0.40 | INFO/gnomad_svAF > 0.40 "'
+        } else if (params.genome == 'GRCh38') {
+            ext.args = '--output-type z --apply-filters PASS --exclude "INFO/swegen_FRQ > 0.40"'
+        }
+        publishDir = [
+            enabled: false,
+        ]
+    }
+
+    // Java memory fixes
+    withName:'QUALIMAP_BAMQC' {
+        clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''} ${task.memory ? "--mem ${task.memory.mega * 1.15 as long}M" : ''}" }
+    }
+    withName:'PICARD_MARKDUPLICATES' {
+        clusterOptions = { "-A $params.priority ${params.clusterOptions ?: ''} ${task.memory ? "--mem ${task.memory.mega * 1.15 as long}M" : ''}" }
+    }
+    
+}

conf/pipeline/rnafusion/hasta.config

@@ -0,0 +1,7 @@
+// rnafusion/hasta specific profile config for Clinical Genomics Stockholm usage
+
+params {
+    all = true
+    trim = true
+    fusioninspector_filter = true
+}

conf/pipeline/viralrecon/genomes.config

@@ -8,6 +8,8 @@
 params {
   // Genome reference file paths
   genomes {
+
+    // SARS-CoV-2
     'NC_045512.2' {
       // This version of the reference has been kept here for backwards compatibility.
       // Please use 'MN908947.3' if possible because all primer sets are available / have been pre-prepared relative to that assembly
@@ -18,6 +20,8 @@ params {
       nextclade_dataset_reference = 'MN908947'
       nextclade_dataset_tag       = '2022-06-14T12:00:00Z'
     }
+
+    // SARS-CoV-2
     'MN908947.3' {
       fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.fna.gz'
       gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MN908947.3/GCA_009858895.3_ASM985889v3_genomic.200409.gff.gz'
@@ -66,5 +70,28 @@ params {
         }
       }
     }
+
+    // Monkeypox
+    'NC_063383.1' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/GCF_014621545.1_ASM1462154v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/GCF_014621545.1_ASM1462154v1_genomic.220824.gff.gz'
+      nextclade_dataset           = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/NC_063383.1/nextclade_hMPXV_NC_063383.1_2022-08-19T12_00_00Z.tar.gz'
+      nextclade_dataset_name      = 'hMPXV'
+      nextclade_dataset_reference = 'NC_063383.1'
+      nextclade_dataset_tag       = '2022-08-19T12:00:00Z'
+    }
+
+    // Monkeypox
+    'ON563414.3' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/ON563414.3/GCA_023516015.3_ASM2351601v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/ON563414.3/GCA_023516015.3_ASM2351601v1_genomic.220824.gff.gz'
+    }
+
+    // Monkeypox
+    'MT903344.1' {
+      fasta            = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MT903344.1/GCA_014621585.1_ASM1462158v1_genomic.220824.fna.gz'
+      gff              = 'https://github.com/nf-core/test-datasets/raw/viralrecon/genome/MT903344.1/GCA_014621585.1_ASM1462158v1_genomic.220824.gff.gz'
+    }
+
   }
 }

docs/cheaha.md

@@ -13,6 +13,8 @@ module load Singularity
 module load Nextflow
 ```
 
+Various tasks will be run inside of Singularity containers and all temp files typically written to `/tmp` and `/var/tmp` are instead written to the path pointed to by the `USER_SCRATCH` environment variable. This means that these temp files are stored in a user specific location, making them inaccessible to other users for pipeline reruns. Some of these temp files can be large and cleanup is also the responsibility of the user.
+
 All of the intermediate files required to run the pipeline will be stored in the `work/` directory. It is recommended to delete this directory after the pipeline has finished successfully because it can get quite large, and all of the main output files will be saved in the `results/` directory anyway.
 
 > NB: You will need an account to use the HPC cluster on Cheaha in order to run the pipeline. If in doubt contact UAB IT Research Computing.</br></br>

docs/pipeline/rnafusion/hasta.md

@@ -0,0 +1,19 @@
+# nf-core/configs: HASTA rnafusion specific configuration
+
+Extra specific configuration for rnafusion pipeline
+
+## Usage
+
+To use, run the pipeline with `-profile hasta`.
+
+This will download and launch the rnafusion specific [`hasta.config`](../../../conf/pipeline/rnafusion/munin.config) which has been pre-configured with a setup suitable for the `HASTA` cluster.
+
+Example: `nextflow run nf-core/rnafusion -profile hasta`
+
+## rnafusion specific configurations for HASTA
+
+Specific configurations for `HASTA` has been made for rnafusion.
+
+- Always run all the analysis steps (all = true)
+- Use trimming (trim = true)
+- Take the fusions identified by at least 2 fusion detection tools to the fusioninspector analysis (fusioninspector_filter = true)

pipeline/rnafusion.config

@@ -9,5 +9,6 @@
  */
 
 profiles {
+  hasta { includeConfig "${params.custom_config_base}/conf/pipeline/rnafusion/hasta.config" }
   munin { includeConfig "${params.custom_config_base}/conf/pipeline/rnafusion/munin.config" }
-}
+}