Dsl2 sex determination

.github/workflows/ci.yml

@@ -33,6 +33,7 @@ jobs:
           - "-profile test,docker --mapping_tool bowtie2 --damagecalculation_tool mapdamage --damagecalculation_mapdamage_downsample 100"
           - "-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'"
+          - "-profile test_humanbam,docker --run_sexdeterrmine"
           - "-profile test_multiref,docker" ## TODO add damage manipulation here instead once it goes multiref
     steps:
       - name: Check out pipeline code

CITATIONS.md

@@ -103,8 +103,13 @@
   > QualiMap Okonechnikov, K., Conesa, A., & García-Alcalde, F. (2016). Qualimap 2: advanced multi-sample quality control for high-throughput sequencing data. Bioinformatics , 32(2), 292–294. Download: http://qualimap.bioinfo.cipf.es/
 
 - [DamageProfiler](https://doi.org/10.1093/bioinformatics/btab190)
+
   > DamageProfiler Neukamm, J., Peltzer, A., & Nieselt, K. (2020). DamageProfiler: Fast damage pattern calculation for ancient DNA. In Bioinformatics (btab190). doi: [10.1093/bioinformatics/btab190](https://doi.org/10.1093/bioinformatics/btab190). Download: https://github.com/Integrative-Transcriptomics/DamageProfiler
 
+  - [Sex.DetERRmine.py](http://dx.doi.org/10.1038/s41467-018-07483-5)
+
+  > Sex.DetERRmine.py Lamnidis, T.C. et al., 2018. Ancient Fennoscandian genomes reveal origin and spread of Siberian ancestry in Europe. Nature communications, 9(1), p.5018. Available at: http://dx.doi.org/10.1038/s41467-018-07483-5. Download: https://github.com/TCLamnidis/Sex.DetERRmine
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

conf/modules.config

@@ -909,6 +909,29 @@ process {
         ]
     }
 
+    //
+    // RUN SEXDETERRMINE
+    //
+    withName: SAMTOOLS_DEPTH_SEXDETERRMINE {
+        tag = { "${meta1.reference}|${meta1.sample_id}_${meta1.library_id}" }
+        ext.prefix = { "${meta2.id}_samtoolsdepth" }
+        ext.args = '-aa -q30 -Q30 -H'
+        publishDir = [
+        enabled: false
+        ]
+    }
+
+    withName: SEXDETERRMINE {
+        tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+        ext.prefix = { "${meta.reference}_sexdeterrmine" }
+        publishDir = [
+            path: { "${params.outdir}/sex_determination/" },
+            mode: params.publish_dir_mode,
+            pattern: '*{_sexdeterrmine}*',
+            enabled: true
+        ]
+    }
+
     //
     // LIBRARY MERGE
     //

conf/test_humanbam.config

@@ -36,7 +36,7 @@ params {
 
     // TODO Reactivate sexDet and genotyping params when those steps get implemented.
     // //Sex Determination
-    // sexdeterrmine_bedfile = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
+    sexdeterrmine_bedfile = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
     // // Genotyping
     // pileupcaller_bedfile = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz'
     // pileupcaller_snpfile = 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K_covered_in_JK2067_downsampled_s0.1.numeric_chromosomes.snp'

docs/development/manual_tests.md

@@ -110,6 +110,12 @@ Tool Specific combinations
     - single reference: with damage manipulation (pmd + trimming), on pmd filtered data ✅
     - multi reference: no damage manipulation ✅
 
+- Sex determination
+
+  - With sexdeterrmine
+
+    - with default parameters
+
 ### Multi-reference tests
 
 ```bash
@@ -738,3 +744,11 @@ nextflow run main.nf -profile test,docker --outdir ./results -w work/ -resume --
 ## NOTE: PG tags are repeated for each chromosome in the reference, times each library! Maybe there's some flag missing from samtools MERGE runs?
 nextflow run main.nf -profile test_multiref,docker --outdir ./results -w work/ -resume --genotyping_source 'raw' -ansi-log false -dump-channels
 ```
+
+### Run Sexdeterrmine
+
+```bash
+## Running sex determination subworkflow from deduplicated bams
+## Expect: sex_deterrmine/sexdeterrmine directory with tsv summary table for all individuals.
+nextflow run main.nf -profile test_humanbam,arm,docker --outdir ./results --run_sexdeterrmine
+```

docs/output.md

@@ -540,3 +540,19 @@ is a tool which calculates a variety of standard 'aDNA' metrics from a BAM file.
 </details>
 
 [ANGSD](http://www.popgen.dk/angsd/index.php/ANGSD) is a software for analyzing next generation sequencing data. Among other functions, ANGSD can estimate contamination for chromosomes for which one copy exists, i.e. X-chromosome for humans with karyotype XY. To do this, we first generate a binary count file for the X-chromosome (`angsd`) and then perform a Fisher's exact test for finding a p-value and jackknife to get an estimate of contamination (`contamination`). Contamination is estimated with Method of Moments (MOM) and Maximum Likelihood (ML) for both Method1 and Method2. Method1 compares the total number of minor and major reads at SNP sites with the number of minor and major reads at adjacent sites, assuming independent errors between reads and sites, while Method2 only samples one read at each site to remove the previous assumption. The results of all methods for each library, as well as respective standard errors are summarised in `nuclear_contamination.txt` and `nuclear_contamination_mqc.json`.
+
+### Sex Determination
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `sex_determination/`: this contains the output for the sex determination run. This is a single `.tsv` file that includes a table with the sample name, the number of autosomal SNPs, number of SNPs on the X/Y chromosome, the number of reads mapping to the autosomes, the number of reads mapping to the X/Y chromosome, the relative coverage on the X/Y chromosomes, and the standard error associated with the relative coverages. These measures are provided for each bam file, one row per file. If the `sexdeterrmine_bedfile` option has not been provided, the error bars cannot be trusted!
+- </details>
+
+#### Sex.DetERRmine
+
+Sex.DetERRmine calculates the coverage of your mapped reads on the X and Y chromosomes relative to the coverage on the autosomes (X-/Y-rate). This metric can be thought of as the number of copies of chromosomes X and Y that is found within each cell, relative to the autosomal copies. The number of autosomal copies is assumed to be two, meaning that an X-rate of 1.0 means there are two X chromosomes in each cell, while 0.5 means there is a single copy of the X chromosome per cell. Human females have two copies of the X chromosome and no Y chromosome (XX), while human males have one copy of each of the X and Y chromosomes (XY).
+
+When a bedfile of specific sites is provided, Sex.DetERRmine runs much faster and additionally calculates error bars around each relative coverage estimate. For this estimate to be trustworthy, the sites included in the bedfile should be spaced apart enough that a single sequencing read cannot overlap multiple sites. Hence, when a bedfile has not been provided, this error should be ignored. When a suitable bedfile is provided, each observation of a covered site is independent, and the error around the coverage is equal to the binomial error estimate. This error is then propagated during the calculation of relative coverage for the X and Y chromosomes.
+
+> Note that in nf-core/eager this will be run on single- and double-stranded variants of the same library separately. This can also help assess for differential contamination between libraries.

modules.json

@@ -170,6 +170,11 @@
                         "git_sha": "6b0e4fe14ca1b12e131f64608f0bbaf36fd11451",
                         "installed_by": ["modules"]
                     },
+                    "samtools/depth": {
+                        "branch": "master",
+                        "git_sha": "a1ffbc1fd87bd5a829e956cc26ec9cc53af3e817",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/faidx": {
                         "branch": "master",
                         "git_sha": "ce0b1aed7d504883061e748f492a31bf44c5777c",
@@ -214,25 +219,11 @@
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["modules"]
-                    }
-                }
-            },
-            "subworkflows": {
-                "nf-core": {
-                    "bam_docounts_contamination_angsd": {
-                        "branch": "master",
-                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
-                        "installed_by": ["subworkflows"]
                     },
-                    "bam_split_by_region": {
+                    "sexdeterrmine": {
                         "branch": "master",
-                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
-                        "installed_by": ["subworkflows"]
-                    },
-                    "fastq_align_bwaaln": {
-                        "branch": "master",
-                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
-                        "installed_by": ["subworkflows"]
+                        "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
+                        "installed_by": ["modules"]
                     }
                 }
             },