From 9952aa5f47cea2170299b1cfc9c88d49021dfc31 Mon Sep 17 00:00:00 2001
From: Dominik Brilhaus <brilhaus@nfdi4plants.org>
Date: Wed, 7 Aug 2024 13:42:24 +0200
Subject: [PATCH] add ebi trimmomatic workflows
---
workflows/trimmomatic/README.md | 5 +
workflows/trimmomatic/trimmomatic-Dockerfile | 20 ++
workflows/trimmomatic/trimmomatic-docker.yml | 4 +
.../trimmomatic/trimmomatic-end_mode.yaml | 3 +
.../trimmomatic-illumina_clipping.yaml | 41 +++
.../trimmomatic/trimmomatic-max_info.yaml | 7 +
workflows/trimmomatic/trimmomatic-phred.yaml | 3 +
.../trimmomatic-sliding_window.yaml | 7 +
workflows/trimmomatic/trimmomatic.cwl | 321 ++++++++++++++++++
9 files changed, 411 insertions(+)
create mode 100644 workflows/trimmomatic/README.md
create mode 100644 workflows/trimmomatic/trimmomatic-Dockerfile
create mode 100644 workflows/trimmomatic/trimmomatic-docker.yml
create mode 100644 workflows/trimmomatic/trimmomatic-end_mode.yaml
create mode 100755 workflows/trimmomatic/trimmomatic-illumina_clipping.yaml
create mode 100755 workflows/trimmomatic/trimmomatic-max_info.yaml
create mode 100644 workflows/trimmomatic/trimmomatic-phred.yaml
create mode 100644 workflows/trimmomatic/trimmomatic-sliding_window.yaml
create mode 100755 workflows/trimmomatic/trimmomatic.cwl
diff --git a/workflows/trimmomatic/README.md b/workflows/trimmomatic/README.md
new file mode 100644
index 0000000..87b73ce
--- /dev/null
+++ b/workflows/trimmomatic/README.md
@@ -0,0 +1,5 @@
+
+# Trimmomatic
+
+adapted from: https://github.com/EBI-Metagenomics/ebi-metagenomics-cwl/commit/7bb76f33bf40b5cd2604001cac46f967a209c47f
+
diff --git a/workflows/trimmomatic/trimmomatic-Dockerfile b/workflows/trimmomatic/trimmomatic-Dockerfile
new file mode 100644
index 0000000..9d08d88
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-Dockerfile
@@ -0,0 +1,20 @@
+#################################################################
+# Dockerfile
+#
+# Software: trimmomatic
+# Software Version: 0.32+dfsg-1
+# Description: DukeGCB trimmomatic image
+# Website: http://www.usadellab.org/cms/?page=trimmomatic
+# Provides: trimmomatic
+# Base Image: dukegcb/trimmomatic
+# Build Cmd: docker build --rm -t dukegcb/trimmomatic .
+# Pull Cmd: docker pull dukegcb/trimmomatic
+# Run Cmd: docker run --rm -it dukegcb/trimmomatic
+#################################################################
+
+FROM phusion/baseimage
+MAINTAINER Dan Leehr <dan.leehr@duke.edu>
+
+RUN apt-get update && apt-get install -y \
+ openjdk-7-jre-headless \
+ trimmomatic="0.32+dfsg-1"
diff --git a/workflows/trimmomatic/trimmomatic-docker.yml b/workflows/trimmomatic/trimmomatic-docker.yml
new file mode 100644
index 0000000..8a8df26
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-docker.yml
@@ -0,0 +1,4 @@
+class: DockerRequirement
+dockerPull: dukegcb/trimmomatic
+dockerFile: >
+ $import: trimmomatic-Dockerfile
diff --git a/workflows/trimmomatic/trimmomatic-end_mode.yaml b/workflows/trimmomatic/trimmomatic-end_mode.yaml
new file mode 100644
index 0000000..2c53a6f
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-end_mode.yaml
@@ -0,0 +1,3 @@
+type: enum
+name: end_mode
+symbols: [ SE, PE ]
diff --git a/workflows/trimmomatic/trimmomatic-illumina_clipping.yaml b/workflows/trimmomatic/trimmomatic-illumina_clipping.yaml
new file mode 100755
index 0000000..8a18874
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-illumina_clipping.yaml
@@ -0,0 +1,41 @@
+type: record
+name: illuminaClipping
+fields:
+ - name: adapters
+ type: File
+ doc: |
+ FASTA file containing adapters, PCR sequences, etc. It is used to search
+ for and remove these sequences in the input FASTQ file(s)
+ - name: seedMismatches
+ type: int
+ doc: |
+ specifies the maximum mismatch count which will still allow a full match
+ to be performed
+ - name: palindromeClipThreshold
+ type: int
+ doc: |
+ specifies how accurate the match between the two 'adapter ligated' reads
+ must be for PE palindrome read alignment.
+ - name: simpleClipThreshold
+ type: int
+ doc: |
+ specifies how accurate the match between any adapter etc. sequence must
+ be against a read
+ - name: minAdapterLength
+ type: int?
+ doc: |
+ In addition to the alignment score, palindrome mode can verify that a
+ minimum length of adapter has been detected. If unspecified, this
+ defaults to 8 bases, for historical reasons. However, since palindrome
+ mode has a very low false positive rate, this can be safely reduced, even
+ down to 1, to allow shorter adapter fragments to be removed.
+ - name: keepBothReads
+ type: boolean
+ doc: |
+ After read-though has been detected by palindrome mode, and the adapter
+ sequence removed, the reverse read contains the same sequence information
+ as the forward read, albeit in reverse complement. For this reason, the
+ default behaviour is to entirely drop the reverse read. By specifying
+ "true" for this parameter, the reverse read will also be retained, which
+ may be useful e.g. if the downstream tools cannot handle a combination of
+ paired and unpaired reads.
diff --git a/workflows/trimmomatic/trimmomatic-max_info.yaml b/workflows/trimmomatic/trimmomatic-max_info.yaml
new file mode 100755
index 0000000..086b295
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-max_info.yaml
@@ -0,0 +1,7 @@
+type: record
+name: maxinfo
+fields:
+ - name: targetLength
+ type: int
+ - name: strictness
+ type: int
diff --git a/workflows/trimmomatic/trimmomatic-phred.yaml b/workflows/trimmomatic/trimmomatic-phred.yaml
new file mode 100644
index 0000000..6015346
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-phred.yaml
@@ -0,0 +1,3 @@
+type: enum
+name: phred
+symbols: [ '64', '33' ]
diff --git a/workflows/trimmomatic/trimmomatic-sliding_window.yaml b/workflows/trimmomatic/trimmomatic-sliding_window.yaml
new file mode 100644
index 0000000..66d3b8c
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic-sliding_window.yaml
@@ -0,0 +1,7 @@
+type: record
+name: slidingWindow
+fields:
+ - name: windowSize
+ type: int
+ - name: requiredQuality
+ type: int
diff --git a/workflows/trimmomatic/trimmomatic.cwl b/workflows/trimmomatic/trimmomatic.cwl
new file mode 100755
index 0000000..2aaf27e
--- /dev/null
+++ b/workflows/trimmomatic/trimmomatic.cwl
@@ -0,0 +1,321 @@
+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.0
+class: CommandLineTool
+
+hints:
+ SoftwareRequirement:
+ packages:
+ trimmomatic:
+ specs: [ "https://identifiers.org/rrid/RRID:SCR_011848" ]
+ version: [ "0.32", "0.35", "0.36" ]
+
+requirements:
+ ResourceRequirement:
+ ramMin: 10240
+ coresMin: 8
+ SchemaDefRequirement:
+ types:
+ - $import: trimmomatic-end_mode.yaml
+ - $import: trimmomatic-sliding_window.yaml
+ - $import: trimmomatic-phred.yaml
+ - $import: trimmomatic-illumina_clipping.yaml
+ - $import: trimmomatic-max_info.yaml
+ InlineJavascriptRequirement: {}
+ ShellCommandRequirement: {}
+
+# hints:
+# - $import: trimmomatic-docker.yml
+
+inputs:
+ phred:
+ type: trimmomatic-phred.yaml#phred?
+ inputBinding:
+ prefix: -phred
+ separate: false
+ position: 4
+ doc: |
+ "33" or "64" specifies the base quality encoding. Default: 64
+
+ tophred64:
+ type: boolean?
+ inputBinding:
+ position: 12
+ prefix: TOPHRED64
+ separate: false
+ doc: This (re)encodes the quality part of the FASTQ file to base 64.
+
+ headcrop:
+ type: int?
+ inputBinding:
+ position: 13
+ prefix: 'HEADCROP:'
+ separate: false
+ doc: |
+ Removes the specified number of bases, regardless of quality, from the
+ beginning of the read.
+ The numbser specified is the number of bases to keep, from the start of
+ the read.
+
+ tophred33:
+ type: boolean?
+ inputBinding:
+ position: 12
+ prefix: TOPHRED33
+ separate: false
+ doc: This (re)encodes the quality part of the FASTQ file to base 33.
+
+ minlen:
+ type: int?
+ inputBinding:
+ position: 100
+ prefix: 'MINLEN:'
+ separate: false
+ doc: |
+ This module removes reads that fall below the specified minimal length.
+ If required, it should normally be after all other processing steps.
+ Reads removed by this step will be counted and included in the "dropped
+ reads" count presented in the trimmomatic summary.
+
+ java_opts:
+ type: string?
+ inputBinding:
+ position: 1
+ shellQuote: false
+ doc: |
+ JVM arguments should be a quoted, space separated list
+ (e.g. "-Xms128m -Xmx512m")
+
+ leading:
+ type: int?
+ inputBinding:
+ position: 14
+ prefix: 'LEADING:'
+ separate: false
+ doc: |
+ Remove low quality bases from the beginning. As long as a base has a
+ value below this threshold the base is removed and the next base will be
+ investigated.
+
+ slidingwindow:
+ type: trimmomatic-sliding_window.yaml#slidingWindow?
+ inputBinding:
+ position: 15
+ valueFrom: |
+ ${ if ( self ) {
+ return "SLIDINGWINDOW:" + self.windowSize + ":"
+ + self.requiredQuality;
+ } else {
+ return self;
+ }
+ }
+ doc: |
+ Perform a sliding window trimming, cutting once the average quality
+ within the window falls below a threshold. By considering multiple
+ bases, a single poor quality base will not cause the removal of high
+ quality data later in the read.
+ <windowSize> specifies the number of bases to average across
+ <requiredQuality> specifies the average quality required
+
+ illuminaClip:
+ type: trimmomatic-illumina_clipping.yaml#illuminaClipping?
+ inputBinding:
+ valueFrom: |
+ ${ if ( self ) {
+ return "ILLUMINACLIP:" + inputs.illuminaClip.adapters.path + ":"
+ + self.seedMismatches + ":" + self.palindromeClipThreshold + ":"
+ + self.simpleClipThreshold + ":" + self.minAdapterLength + ":"
+ + self.keepBothReads;
+ } else {
+ return self;
+ }
+ }
+ position: 11
+ doc: Cut adapter and other illumina-specific sequences from the read.
+
+ crop:
+ type: int?
+ inputBinding:
+ position: 13
+ prefix: 'CROP:'
+ separate: false
+ doc: |
+ Removes bases regardless of quality from the end of the read, so that the
+ read has maximally the specified length after this step has been
+ performed. Steps performed after CROP might of course further shorten the
+ read. The value is the number of bases to keep, from the start of the read.
+
+ reads2:
+ type: File?
+ format: edam:format_1930 # fastq
+ inputBinding:
+ position: 6
+ doc: FASTQ file of R2 reads in Paired End mode
+
+ reads1:
+ type: File
+ format: edam:format_1930 # fastq
+ inputBinding:
+ position: 5
+ doc: FASTQ file of reads (R1 reads in Paired End mode)
+
+ avgqual:
+ type: int?
+ inputBinding:
+ position: 101
+ prefix: 'AVGQUAL:'
+ separate: false
+ doc: |
+ Drop the read if the average quality is below the specified level
+
+ trailing:
+ type: int?
+ inputBinding:
+ position: 14
+ prefix: 'TRAILING:'
+ separate: false
+ doc: |
+ Remove low quality bases from the end. As long as a base has a value
+ below this threshold the base is removed and the next base (which as
+ trimmomatic is starting from the 3' prime end would be base preceding
+ the just removed base) will be investigated. This approach can be used
+ removing the special Illumina "low quality segment" regions (which are
+ marked with quality score of 2), but we recommend Sliding Window or
+ MaxInfo instead
+
+ maxinfo:
+ type: trimmomatic-max_info.yaml#maxinfo?
+ inputBinding:
+ position: 15
+ valueFrom: |
+ ${ if ( self ) {
+ return "MAXINFO:" + self.targetLength + ":" + self.strictness;
+ } else {
+ return self;
+ }
+ }
+ doc: |
+ Performs an adaptive quality trim, balancing the benefits of retaining
+ longer reads against the costs of retaining bases with errors.
+ <targetLength>: This specifies the read length which is likely to allow
+ the location of the read within the target sequence to be determined.
+ <strictness>: This value, which should be set between 0 and 1, specifies
+ the balance between preserving as much read length as possible vs.
+ removal of incorrect bases. A low value of this parameter (<0.2) favours
+ longer reads, while a high value (>0.8) favours read correctness.
+
+ end_mode:
+ type: trimmomatic-end_mode.yaml#end_mode
+ inputBinding:
+ position: 3
+ doc: |
+ Single End (SE) or Paired End (PE) mode
+
+outputs:
+ reads1_trimmed:
+ type: File
+ format: edam:format_1930 # fastq
+ outputBinding:
+ glob: $(inputs.reads1.nameroot).trimmed.fastq
+
+ output_log:
+ type: File
+ outputBinding:
+ glob: trim.log
+ label: Trimmomatic log
+ doc: |
+ log of all read trimmings, indicating the following details:
+ the read name
+ the surviving sequence length
+ the location of the first surviving base, aka. the amount trimmed from the start
+ the location of the last surviving base in the original read
+ the amount trimmed from the end
+
+ reads1_trimmed_unpaired:
+ type: File?
+ format: edam:format_1930 # fastq
+ outputBinding:
+ glob: $(inputs.reads1.nameroot).unpaired.trimmed.fastq
+
+ reads2_trimmed_paired:
+ type: File?
+ format: edam:format_1930 # fastq
+ outputBinding:
+ glob: |
+ ${ if (inputs.reads2 ) {
+ return inputs.reads2.nameroot + '.trimmed.fastq';
+ } else {
+ return null;
+ }
+ }
+
+ reads2_trimmed_unpaired:
+ type: File?
+ format: edam:format_1930 # fastq
+ outputBinding:
+ glob: |
+ ${ if (inputs.reads2 ) {
+ return inputs.reads2.nameroot + '.unpaired.trimmed.fastq';
+ } else {
+ return null;
+ }
+ }
+
+baseCommand: [ java, org.usadellab.trimmomatic.Trimmomatic ]
+
+arguments:
+- valueFrom: trim.log
+ prefix: -trimlog
+ position: 4
+- valueFrom: $(runtime.cores)
+ position: 4
+ prefix: -threads
+- valueFrom: $(inputs.reads1.nameroot).trimmed.fastq
+ position: 7
+- valueFrom: |
+ ${
+ if (inputs.end_mode == "PE" && inputs.reads2) {
+ return inputs.reads1.nameroot + '.trimmed.unpaired.fastq';
+ } else {
+ return null;
+ }
+ }
+ position: 8
+- valueFrom: |
+ ${
+ if (inputs.end_mode == "PE" && inputs.reads2) {
+ return inputs.reads2.nameroot + '.trimmed.fastq';
+ } else {
+ return null;
+ }
+ }
+ position: 9
+- valueFrom: |
+ ${
+ if (inputs.end_mode == "PE" && inputs.reads2) {
+ return inputs.reads2.nameroot + '.trimmed.unpaired.fastq';
+ } else {
+ return null;
+ }
+ }
+ position: 10
+
+doc: |
+ Trimmomatic is a fast, multithreaded command line tool that can be used to trim and crop
+ Illumina (FASTQ) data as well as to remove adapters. These adapters can pose a real problem
+ depending on the library preparation and downstream application.
+ There are two major modes of the program: Paired end mode and Single end mode. The
+ paired end mode will maintain correspondence of read pairs and also use the additional
+ information contained in paired reads to better find adapter or PCR primer fragments
+ introduced by the library preparation process.
+ Trimmomatic works with FASTQ files (using phred + 33 or phred + 64 quality scores,
+ depending on the Illumina pipeline used).
+
+$namespaces:
+ edam: http://edamontology.org/
+ s: http://schema.org/
+$schemas:
+ - http://edamontology.org/EDAM_1.16.owl
+
+s:license: "https://www.apache.org/licenses/LICENSE-2.0"
+s:copyrightHolder: "EMBL - European Bioinformatics Institute"
--
GitLab