Merge pull request #56 from ctuni/feature/seqfu

added seqfu stats

CHANGELOG.md

@@ -12,6 +12,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#20](https://github.com/nf-core/seqinspector/pull/20) Use tags to generate group reports
 - [#13](https://github.com/nf-core/seqinspector/pull/13) Generate reports per run, per project and per lane.
 - [#49](https://github.com/nf-core/seqinspector/pull/49) Merge with template 3.0.2.
+- [#56](https://github.com/nf-core/seqinspector/pull/56) Added SeqFu stats module.
 - [#50](https://github.com/nf-core/seqinspector/pull/50) Add an optional subsampling step.
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 - [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools

CITATIONS.md

@@ -14,6 +14,10 @@
 
 > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].
 
+- [SeqFu](https://telatin.github.io/seqfu2/)
+
+> Telatin A, Fariselli P, Birolo G. SeqFu: A Suite of Utilities for the Robust and Reproducible Manipulation of Sequence Files. Bioengineering 2021, 8, 59. doi.org/10.3390/bioengineering8050059
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.

conf/modules.config

@@ -26,6 +26,15 @@ process {
         ext.args = '--quiet'
     }
 
+    withName: 'SEQFU_STATS' {
+        ext.args   = ''
+        publishDir = [
+            path: { "${params.outdir}/seqfu_stats" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'MULTIQC_GLOBAL' {
         ext.args   = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
         publishDir = [

docs/output.md

@@ -12,6 +12,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 - [Seqtk](#seqtk) - Subsample a specific number of reads per sample
 - [FastQC](#fastqc) - Raw read QC
+- [SeqFu Stats](#seqfu_stats) - Statistics for FASTA or FASTQ files
 - [MultiQC](#multiqc) - Aggregate report describing results and QC from the whole pipeline
 - [Pipeline information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -40,6 +41,19 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 
 [FastQC](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/) gives general quality metrics about your sequenced reads. It provides information about the quality score distribution across your reads, per base sequence content (%A/T/G/C), adapter contamination and overrepresented sequences. For further reading and documentation see the [FastQC help pages](http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/).
 
+#### SeqFu Stats
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `seqfu/`
+  - `*.tsv`: Tab-separated file containing quality metrics.
+  - `*_mqc.txt`: File containing the same quality metrics as the TSV file, ready to be read by MultiQC.
+
+</details>
+
+[SeqFu](https://telatin.github.io/seqfu2/) is general-purpose program to manipulate and parse information from FASTA/FASTQ files, supporting gzipped input files. Includes functions to interleave and de-interleave FASTQ files, to rename sequences and to count and print statistics on sequence lengths. In this pipeline, the `seqfu stats` module is used to produce general quality metrics statistics.
+
 ### MultiQC
 
 nf-core/seqinspector will generate the following MultiQC reports:

modules.json

@@ -15,6 +15,11 @@
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",
                         "installed_by": ["modules"]
                     },
+                    "seqfu/stats": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "seqtk/sample": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",

workflows/seqinspector.nf

@@ -6,6 +6,7 @@
 
 include { SEQTK_SAMPLE                  } from '../modules/nf-core/seqtk/sample/main'
 include { FASTQC                        } from '../modules/nf-core/fastqc/main'
+include { SEQFU_STATS                   } from '../modules/nf-core/seqfu/stats'
 
 include { MULTIQC as MULTIQC_GLOBAL     } from '../modules/nf-core/multiqc/main'
 include { MULTIQC as MULTIQC_PER_TAG    } from '../modules/nf-core/multiqc/main'
@@ -58,6 +59,16 @@ workflow SEQINSPECTOR {
     ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip)
     ch_versions = ch_versions.mix(FASTQC.out.versions.first())
 
+
+    //
+    // Module: Run SeqFu stats
+    //
+    SEQFU_STATS (
+        ch_samplesheet
+    )
+    ch_multiqc_files = ch_multiqc_files.mix(SEQFU_STATS.out.multiqc)
+    ch_versions = ch_versions.mix(SEQFU_STATS.out.versions.first())
+
     //
     // Collate and save software versions
     //