Copy across test data and docs for trimgalore

software/trimgalore/meta.yml

@@ -0,0 +1,40 @@
+name: Trim Galore!
+description: Trim FastQ files using Trim Galore!
+keywords:
+    - trimming
+    - adapters
+    - sequencing adapters
+tools:
+    - fastqc:
+        description: |
+            A wrapper tool around Cutadapt and FastQC to consistently apply quality
+            and adapter trimming to FastQ files, with some extra functionality for
+            MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/
+        documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md
+input:
+    -
+        - sample_id:
+            type: string
+            description: Sample identifier
+        - reads:
+            type: file
+            description: Input FastQ file, or pair of files
+output:
+    -
+        - sample_id:
+            type: string
+            description: Sample identifier
+        - trimmed_fastq:
+            type: file
+            description: Trimmed FastQ files
+            pattern: "*fq.gz"
+    -
+        - report:
+            type: file
+            description: Trim Galore! trimming report
+            pattern: "*trimming_report.txt"
+
+authors:
+    - "@ewels"
+    - "@FelixKrueger"

software/trimgalore/test/input/test_R1.fastq.gz

@@ -0,0 +1 @@
+../../../../tests/data/fastq/rna/test_R1.fastq.gz

software/trimgalore/test/input/test_R2.fastq.gz

@@ -0,0 +1 @@
+../../../../tests/data/fastq/rna/test_R2.fastq.gz

software/trimgalore/test/main.nf

@@ -0,0 +1,27 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl=2
+
+params.outdir = "."             // gets set in the nextflow.config files (to './results/trim_galore')
+params.verbose = false
+params.trim_galore_args = ''
+// trim_galore_args are best passed into the workflow in the following manner, e.g.:
+// --trim_galore_args="--clip_r1 10 --clip_r2 15 -j 2"
+
+if (params.verbose){
+    println ("[WORKFLOW] TRIM GALORE ARGS: "      + params.trim_galore_args)
+}
+
+// TODO: check the output files in some way
+// include '../../../tests/functions/check_process_outputs.nf'
+include '../main.nf'  // params (clip_r1: 6, clip_r2: 10) // how to pass additional parameters
+
+ch_read_files = Channel
+  .fromFilePairs('../../../test-datasets/test*{1,2}.fastq.gz',size:-1)
+  // .view()  // to check whether the input channel works
+
+workflow {
+
+    main:
+        TRIM_GALORE (ch_read_files, params.outdir, params.trim_galore_args, params.verbose)
+
+}

software/trimgalore/test/nextflow.config

@@ -0,0 +1,2 @@
+// docker.enabled = true
+params.outdir = './results'

software/trimgalore/test/output/test_R1.fastq.gz_trimming_report.txt

@@ -0,0 +1,97 @@
+
+SUMMARISING RUN PARAMETERS
+==========================
+Input filename: test_R1.fastq.gz
+Trimming mode: paired-end
+Trim Galore version: 0.6.5
+Cutadapt version: 2.3
+Number of cores used for trimming: 1
+Quality Phred score cutoff: 20
+Quality encoding type selected: ASCII+33
+Using Nextera adapter for trimming (count: 83). Second best hit was smallRNA (count: 0)
+Adapter sequence: 'CTGTCTCTTATA' (Nextera Transposase sequence; auto-detected)
+Maximum trimming error rate: 0.1 (default)
+Minimum required adapter overlap (stringency): 1 bp
+Minimum required sequence length for both reads before a sequence pair gets removed: 20 bp
+Output file will be GZIP compressed
+
+
+This is cutadapt 2.3 with Python 3.7.3
+Command line parameters: -j 1 -e 0.1 -q 20 -O 1 -a CTGTCTCTTATA test_R1.fastq.gz
+Processing reads on 1 core in single-end mode ...
+Finished in 0.19 s (19 us/read; 3.12 M reads/minute).
+
+=== Summary ===
+
+Total reads processed:                  10,000
+Reads with adapters:                     3,225 (32.2%)
+Reads written (passing filters):        10,000 (100.0%)
+
+Total basepairs processed:       760,000 bp
+Quality-trimmed:                   4,492 bp (0.6%)
+Total written (filtered):        748,403 bp (98.5%)
+
+=== Adapter 1 ===
+
+Sequence: CTGTCTCTTATA; Type: regular 3'; Length: 12; Trimmed: 3225 times.
+
+No. of allowed errors:
+0-9 bp: 0; 10-12 bp: 1
+
+Bases preceding removed adapters:
+  A: 23.8%
+  C: 28.2%
+  G: 22.7%
+  T: 25.3%
+  none/other: 0.0%
+
+Overview of removed sequences
+length	count	expect	max.err	error counts
+1	2170	2500.0	0	2170
+2	622	625.0	0	622
+3	223	156.2	0	223
+4	64	39.1	0	64
+5	14	9.8	0	14
+6	9	2.4	0	9
+7	8	0.6	0	8
+8	5	0.2	0	5
+9	4	0.0	0	4
+10	8	0.0	1	7 1
+11	3	0.0	1	3
+12	4	0.0	1	4
+13	6	0.0	1	6
+14	5	0.0	1	4 1
+15	5	0.0	1	5
+16	6	0.0	1	5 1
+17	3	0.0	1	3
+18	3	0.0	1	3
+19	1	0.0	1	1
+20	3	0.0	1	3
+21	7	0.0	1	7
+22	7	0.0	1	7
+23	3	0.0	1	3
+24	6	0.0	1	6
+25	4	0.0	1	4
+26	2	0.0	1	2
+27	4	0.0	1	4
+28	1	0.0	1	1
+29	3	0.0	1	3
+30	4	0.0	1	4
+32	3	0.0	1	3
+33	2	0.0	1	1 1
+34	1	0.0	1	1
+35	1	0.0	1	1
+40	1	0.0	1	1
+42	1	0.0	1	0 1
+45	1	0.0	1	0 1
+49	1	0.0	1	0 1
+52	1	0.0	1	0 1
+56	2	0.0	1	0 2
+59	1	0.0	1	0 1
+67	1	0.0	1	0 1
+70	2	0.0	1	0 2
+
+RUN STATISTICS FOR INPUT FILE: test_R1.fastq.gz
+=============================================
+10000 sequences processed in total
+

software/trimgalore/test/output/test_R1_val_1.fq.gz

@@ -0,0 +1 @@
+../../../../tests/data/fastq/rna/test_R1_val_1.fq.gz

software/trimgalore/test/output/test_R2.fastq.gz_trimming_report.txt

@@ -0,0 +1,100 @@
+
+SUMMARISING RUN PARAMETERS
+==========================
+Input filename: test_R2.fastq.gz
+Trimming mode: paired-end
+Trim Galore version: 0.6.5
+Cutadapt version: 2.3
+Number of cores used for trimming: 1
+Quality Phred score cutoff: 20
+Quality encoding type selected: ASCII+33
+Using Nextera adapter for trimming (count: 83). Second best hit was smallRNA (count: 0)
+Adapter sequence: 'CTGTCTCTTATA' (Nextera Transposase sequence; auto-detected)
+Maximum trimming error rate: 0.1 (default)
+Minimum required adapter overlap (stringency): 1 bp
+Minimum required sequence length for both reads before a sequence pair gets removed: 20 bp
+Output file will be GZIP compressed
+
+
+This is cutadapt 2.3 with Python 3.7.3
+Command line parameters: -j 1 -e 0.1 -q 20 -O 1 -a CTGTCTCTTATA test_R2.fastq.gz
+Processing reads on 1 core in single-end mode ...
+Finished in 0.22 s (22 us/read; 2.71 M reads/minute).
+
+=== Summary ===
+
+Total reads processed:                  10,000
+Reads with adapters:                     3,295 (33.0%)
+Reads written (passing filters):        10,000 (100.0%)
+
+Total basepairs processed:       760,000 bp
+Quality-trimmed:                   7,096 bp (0.9%)
+Total written (filtered):        745,649 bp (98.1%)
+
+=== Adapter 1 ===
+
+Sequence: CTGTCTCTTATA; Type: regular 3'; Length: 12; Trimmed: 3295 times.
+
+No. of allowed errors:
+0-9 bp: 0; 10-12 bp: 1
+
+Bases preceding removed adapters:
+  A: 22.6%
+  C: 28.2%
+  G: 23.6%
+  T: 25.6%
+  none/other: 0.0%
+
+Overview of removed sequences
+length	count	expect	max.err	error counts
+1	2213	2500.0	0	2213
+2	647	625.0	0	647
+3	239	156.2	0	239
+4	53	39.1	0	53
+5	10	9.8	0	10
+6	7	2.4	0	7
+7	8	0.6	0	8
+8	5	0.2	0	5
+9	5	0.0	0	5
+10	10	0.0	1	8 2
+11	2	0.0	1	2
+12	4	0.0	1	4
+13	7	0.0	1	7
+14	3	0.0	1	3
+15	4	0.0	1	4
+16	5	0.0	1	5
+17	3	0.0	1	3
+18	5	0.0	1	4 1
+19	2	0.0	1	1 1
+20	3	0.0	1	3
+21	7	0.0	1	7
+22	6	0.0	1	6
+23	3	0.0	1	3
+24	7	0.0	1	7
+25	4	0.0	1	4
+26	2	0.0	1	2
+27	4	0.0	1	4
+28	1	0.0	1	1
+29	3	0.0	1	3
+30	4	0.0	1	4
+32	3	0.0	1	3
+33	1	0.0	1	1
+34	1	0.0	1	1
+35	2	0.0	1	1 1
+40	1	0.0	1	0 1
+41	1	0.0	1	1
+46	1	0.0	1	0 1
+48	1	0.0	1	0 1
+49	2	0.0	1	0 2
+56	2	0.0	1	0 2
+59	1	0.0	1	0 1
+70	1	0.0	1	0 1
+73	2	0.0	1	0 2
+
+RUN STATISTICS FOR INPUT FILE: test_R2.fastq.gz
+=============================================
+10000 sequences processed in total
+
+Total number of sequences analysed for the sequence pair length validation: 10000
+
+Number of sequence pairs removed because at least one read was shorter than the length cutoff (20 bp): 21 (0.21%)

software/trimgalore/test/output/test_R2_val_2.fq.gz

@@ -0,0 +1 @@
+../../../../tests/data/fastq/rna/test_R2_val_2.fq.gz