docs: add files to build rtd and test the build

.github/workflows/test-build-docs.yaml

@@ -0,0 +1,34 @@
+
+name: build mkdocs
+
+on:
+  push:
+    branches:
+     - develop
+     - master
+  pull_request:
+    branches:
+     - develop
+     - master
+  workflow_dispatch:
+
+jobs:
+  build-mkdocs:
+    name: build mkdocs
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.8
+      - name: Install requirements.txt
+        run: |
+          pip install -r requirements.txt
+      - name: Install requirements.test.txt
+        run: |
+          pip install -r requirements.test.txt
+          pip install -r docs/requirements.txt
+      - name: build mkdocs
+        run: |
+          mkdocs build

.readthedocs.yaml

@@ -0,0 +1,20 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
+mkdocs:
+  configuration: mkdocs.yml
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/requirements.txt

README.md

@@ -1,3 +1,7 @@
+<p align="center">
+<a href="https://hydra-genetics-qc.readthedocs.io">https://hydra-genetics-qc.readthedocs.io</a>
+</p>
+
 # <img src="images/hydragenetics.png" width=40 /> hydra-genetics/qc
 
 #### Snakemake module containing steps for quality control of sequencing data

docs/images/qc.dot

@@ -16,13 +16,15 @@ digraph snakemake_dag {
 	18[label = "bam", color = "0.0 0.0 0.0", style="dotted"];
 	19[label = "fastq", color = "0.0 0.0 0.0", style="dotted"];
 	20[label = "vcf", color = "0.0 0.0 0.0", style="dotted"];
+	21[label = "verifybamid2", color = "0.2 0.9 0.45", style="rounded"];
 	20 -> 2
 	19 -> 4
 	18 -> 5
 	18 -> 9
 	18 -> 10
 	18 -> 14
 	18 -> 17
+	18 -> 21
 	1 -> 0
 	16 -> 1
 	5 -> 1
@@ -32,5 +34,5 @@ digraph snakemake_dag {
 	9 -> 1
 	4 -> 1
 	17 -> 16
+	21 -> 1
 }            
-1

docs/intro.md

@@ -8,10 +8,11 @@ The qc module is a collection of qc programs that performs analysis on the align
 | [fastqQC](https://github.com/s-andrews/FastQC) | fastq | Sequencing report |
 | [GATK](https://gatk.broadinstitute.org/hc/en-us) | pileup | Sample contamination |
 | [mosdepth](https://github.com/brentp/mosdepth) | bam | Coverage |
-| [picard](https://broadinstitute.github.io/picard/) | | Alignment statistics, gc bias, panel statistics, insert size |
-| [rseqc](https://rseqc.sourceforge.net/) | | RNA gene coverage and inner distance |
-| [samtools](http://www.htslib.org/doc/samtools-stats.html) | _ _ | Alignment statistics |
+| [picard](https://broadinstitute.github.io/picard/) | bam | Alignment statistics, gc bias, panel statistics, insert size |
+| [rseqc](https://rseqc.sourceforge.net/) | bam | RNA gene coverage and inner distance |
+| [samtools](http://www.htslib.org/doc/samtools-stats.html) | bam | Alignment statistics |
 | [peddy](http://www.htslib.org/doc/samtools-stats.html) | vcf | Sex and relatedness checks |
+| [verifybamid2](https://github.com/Griffan/VerifyBamID) | bam | Sample contamination estimate |
 | [multiQC](https://github.com/ewels/MultiQC) | QC-files | Summary html-report |
 
 
@@ -24,6 +25,7 @@ The qc module is a collection of qc programs that performs analysis on the align
 The QC programs operate mostly on bam files but also fastq and vcf files.
 
 * `alignment/samtools_merge_bam/{sample}_{type}.bam`
+* `alignment/star/{sample}_R.bam`
 * `prealignment/merged/{sample}_{type}_fastq1.fastq.gz`
 * `prealignment/merged/{sample}_{type}_fastq2.fastq.gz`
 * `qc/peddy/all.vcf.gz`

docs/softwares.md

@@ -302,7 +302,6 @@ Collects multiple statistics st once that can be used by MultiQC.
 ## [verifybamid2](https://github.com/Griffan/VerifyBamID)
 verifybamid2 estimates contamination in samples by simultaneously estimating genetic background and contamination using population allele frequencies. The output is parsed and displayed by the MultiQC rapport.
 
-
 ### :snake: Rule
 
 #SNAKEMAKE_RULE_SOURCE__verifybamid2__verifybamid2#

workflow/schemas/resources.schema.yaml

@@ -328,8 +328,6 @@ properties:
         type: string
         description: max execution time
 
-
-
   verifybamid2:
     type: object
     description: resource definitions for verifybamid2

workflow/schemas/rules.schema.yaml

@@ -74,8 +74,7 @@ properties:
             type: string
             description: Pileup file with allele information for selected sites
 
-
-   mosdepth:
+  mosdepth:
     type: object
     description: input and output parameters for mosdepth
     properties:
@@ -467,9 +466,12 @@ properties:
         type: object
         description: list of outputs
         properties:
-          metrics:
+          selfsm:
+            type: string
+            description: Text file with the estimated contamination level
+          ancestry:
             type: string
-            description: Contamination statistics used by MultiQC
+            description: Text file containing the PC coordinates for both intended sample and contaminating sample