Merge pull request nf-core#1058 from nf-core/add_angsd_gl

Add angsd gl

.github/workflows/ci.yml

@@ -33,7 +33,7 @@ jobs:
           - "-profile test,docker --mapping_tool bowtie2 --damagecalculation_tool mapdamage --damagecalculation_mapdamage_downsample 100 --run_genotyping --genotyping_tool 'hc' --genotyping_source 'raw'"
           - "-profile test,docker --skip_preprocessing"
           - "-profile test_humanbam,docker --run_mtnucratio --run_contamination_estimation_angsd --snpcapture_bed 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz' --run_genotyping --genotyping_tool 'pileupcaller' --genotyping_source 'raw'"
-          - "-profile test_humanbam,docker --run_sexdeterrmine"
+          - "-profile test_humanbam,docker --run_sexdeterrmine --run_genotyping --genotyping_tool 'angsd' --genotyping_source 'raw'"
           - "-profile test_multiref,docker" ## TODO add damage manipulation here instead once it goes multiref
     steps:
       - name: Check out pipeline code

conf/modules.config

@@ -1152,4 +1152,24 @@ process {
             pattern: '*.txt'
         ]
     }
+
+    withName: ANGSD_GL {
+        tag = { "${meta.reference}" }
+        ext.args = {
+            gl_model = params.genotyping_angsd_glmodel == 'samtools' ? 1 : params.genotyping_angsd_glmodel == 'gatk' ? 2 : params.genotyping_angsd_glmodel == 'soapsnp' ? 3 : 4
+            gl_format = params.genotyping_angsd_glformat == 'binary' ? 1 : params.genotyping_angsd_glformat == 'beagle_binary' ? 2 : params.genotyping_angsd_glformat == 'binary_three' ? 3 : 4
+            [
+                ( gl_format == 2 || gl_format == 3 ) ? '-doMajorMinor 1': '',
+                "-GL ${gl_model}",
+                "-doGlf ${gl_format}",
+            ].join(' ').trim()
+        }
+        ext.prefix = { "angsd_${meta.reference}" }
+        publishDir = [
+            path: { "${params.outdir}/genotyping/" },
+            mode: params.publish_dir_mode,
+            enabled: true,
+            pattern: '*.{glf,beagle}.gz'
+        ]
+    }
 }

docs/development/manual_tests.md

@@ -877,3 +877,29 @@ nextflow run main.nf -profile test_humanbam,docker --outdir ./results -w work/ -
 ##   Specifically, no geno/snp/ind for the reference that has no bed/snp file (Mammoth). Only data for "human" reference.
 nextflow run main.nf -profile test_multiref,docker --input test/samplesheet_multilane_multilib_noBAM.tsv --outdir ./results -w work/ -resume --run_genotyping --genotyping_tool 'pileupcaller' --genotyping_source 'raw' -ansi-log false -dump-channels
 ```
+
+## ANGSD
+
+```bash
+## ANGSD on raw reads. Default parameters. (--genotyping_angsd_glmodel 'samtools' --genotyping_angsd_glformat 'binary' )
+## Expect: One `glf.gz` file in binary format per reference.
+nextflow run main.nf -profile test,docker --outdir ./results -w work/ -resume --run_genotyping --genotyping_tool 'angsd' --genotyping_source 'raw' -ansi-log false -dump-channels
+```
+
+```bash
+## ANGSD on raw reads. gatk model, beagle binary format.
+## Expect: One `beagle.gz` file in beagle format per reference.
+nextflow run main.nf -profile test,docker --outdir ./results -w work/ -resume --run_genotyping --genotyping_tool 'angsd' --genotyping_angsd_glmodel 'gatk' --genotyping_angsd_glformat 'beagle_binary' --genotyping_source 'raw' -ansi-log false -dump-channels
+```
+
+```bash
+## ANGSD on raw reads. soapSNP model, binary_three format.
+## Expect: One `glf.gz` file in binary_three format per reference.
+nextflow run main.nf -profile test,docker --outdir ./results -w work/ -resume --run_genotyping --genotyping_tool 'angsd' --genotyping_angsd_glmodel 'soapsnp' --genotyping_angsd_glformat 'binary_three' --genotyping_source 'raw' -ansi-log false -dump-channels
+```
+
+```bash
+## ANGSD on raw reads. syk model, text format.
+## Expect: One `glf.gz` file in binary_three format per reference.
+nextflow run main.nf -profile test,docker --outdir ./results -w work/ -resume --run_genotyping --genotyping_tool 'angsd' --genotyping_angsd_glmodel 'syk' --genotyping_angsd_glformat 'text' --genotyping_source 'raw' -ansi-log false -dump-channels
+```

docs/output.md

@@ -621,3 +621,16 @@ When using pileupCaller for genotyping, single-stranded and double-stranded libr
 </details>
 
 [FreeBayes](https://github.com/freebayes/freebayes) is a Bayesian genetic variant detector designed to find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms), indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and complex events (composite insertion and substitution events) smaller than the length of a short-read sequencing alignment. It calls variants based on the literal sequences of reads aligned to a particular target, not their precise alignment. This model is a straightforward generalization of previous ones (e.g. PolyBayes, samtools, GATK) which detect or report variants based on alignments. This method avoids one of the core problems with alignment-based variant detection - that identical sequences may have multiple possible alignments. The output provided is a bgzipped VCF file for containing the genotype calls of each sample, it's index file, as well as the statistics of the VCF file generated by `bcftools stats`.
+
+#### ANGSD
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `genotyping/`
+
+  - `*.{glf,beagle}.gz`: Genotype likelihood file, containing likelihoods across all samples per reference.
+
+</details>
+
+[ANGSD](http://www.popgen.dk/angsd/index.php/ANGSD) is a software for analyzing next generation sequencing data. It can estimate genotype likelihoods and allele frequencies from next-generation sequencing data. The output provided is a bgzipped genotype likelihood file, containing likelihoods across all samples per reference. Users can specify the model used for genotype likelihood estimation, as well as the output format. For more information on the available options, see the [ANGSD](https://www.popgen.dk/angsd/index.php/Genotype_Likelihoods).

modules.json

@@ -20,6 +20,11 @@
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["bam_docounts_contamination_angsd"]
                     },
+                    "angsd/gl": {
+                        "branch": "master",
+                        "git_sha": "c22aa6082716bd372cbb8f7ccf7c83220f180864",
+                        "installed_by": ["modules"]
+                    },
                     "bamutil/trimbam": {
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",

nextflow.config

@@ -227,6 +227,8 @@ params {
     genotyping_gatk_hc_emitrefconf           = 'GVCF'
     genotyping_freebayes_min_alternate_count = 1
     genotyping_freebayes_skip_coverage       = 0
+    genotyping_angsd_glmodel                 = 'samtools'
+    genotyping_angsd_glformat                = 'binary'
 }
 
 // Load base.config by default for all pipelines

nextflow_schema.json

@@ -1025,6 +1025,22 @@
                     "description": "Specify to skip over regions of high depth by discarding alignments overlapping positions where total read depth is greater than specified.",
                     "help_text": "Specify to skip over regions of high depth by discarding alignments overlapping positions where total read depth is greater than the specified value. Setting to 0 (the default) deactivates this behaviour.\n\n> Modifies freebayes parameter: `-g`",
                     "fa_icon": "fab fa-think-peaks"
+                },
+                "genotyping_angsd_glmodel": {
+                    "type": "string",
+                    "default": "samtools",
+                    "fa_icon": "fas fa-project-diagram",
+                    "description": "Specify which ANGSD genotyping likelihood model to use.",
+                    "help_text": "Specify which genotype likelihood model to use.\n\n> Modifies angsd parameter: `-GL`",
+                    "enum": ["samtools", "gatk", "soapsnp", "syk"]
+                },
+                "genotyping_angsd_glformat": {
+                    "type": "string",
+                    "default": "binary",
+                    "fa_icon": "fas fa-text-height",
+                    "description": "Specify the formatting of the output VCF for ANGSD genotype likelihood results.",
+                    "help_text": "Specifies what type of genotyping likelihood file format will be output.\n\nThe options refer to the following descriptions respectively:\n\n- `binary`: binary output of all 10 log genotype likelihood\n- `beagle_binary`: beagle likelihood file\n- `binary_three`: binary 3 times likelihood\n- `text`: text output of all 10 log genotype likelihoods.\n\nSee the [ANGSD documentation](http://www.popgen.dk/angsd/) for more information on which to select for your downstream applications.\n\n> Modifies angsd parameter: `-doGlf`",
+                    "enum": ["binary", "beagle_binary", "binary_three", "text"]
                 }
             },
             "fa_icon": "fas fa-sliders-h",