docs: miniwdl engine docs and example project for GATK best practices (…

…#158)

* add engine docs
* add miniwdl examples

examples/gatk-best-practices-project-miniwdl/README.md

@@ -0,0 +1,6 @@
+## Introduction
+
+This project includes workflows based on [GATK Best Practices](https://gatk.broadinstitute.org/hc/en-us), developed by
+the [Broad Institute](https://www.broadinstitute.org/). More information on how these workflows work is available in
+the [GATK Workflows Github repository](/~https://github.com/gatk-workflows).
+

examples/gatk-best-practices-project-miniwdl/agc-project.yaml

@@ -0,0 +1,72 @@
+---
+name: GATK
+schemaVersion: 1
+workflows:
+  gatk4-data-processing:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./gatk4-data-processing
+  gatk4-germline-snps-indels:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./gatk4-germline-snps-indels
+  gatk4-basic-joint-genotyping:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./gatk4-basic-joint-genotyping
+  seq-format-validation:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./seq-format-validation
+  bam-to-unmapped-bams:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./seq-format-conversions/bam-to-unmapped-bams
+  cram-to-bam:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./seq-format-conversions/cram-to-bam
+  interleaved-fastq-to-paired-fastq:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./seq-format-conversions/interleaved-fastq-to-paired-fastq
+  paired-fastq-to-unmapped-bam:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./seq-format-conversions/paired-fastq-to-unmapped-bam
+  gatk4-rnaseq-germline-snps-indels:
+    type:
+      language: wdl
+      version: 1.0
+    sourceURL: ./gatk4-rnaseq-germline-snps-indels
+data:
+  - location: s3://gatk-test-data
+    readOnly: true
+  - location: s3://broad-references
+    readOnly: true
+  - location: s3://1000genomes-dragen-3.7.6
+    readOnly: true
+  - location: s3://healthai-public-assets-us-east-1/agc-demo-data
+    readOnly: true
+contexts:
+  # The on demand context uses on-demand EC2 instances which may be more expensive but will not be interrupted
+  onDemandCtx:
+    requestSpotInstances: false
+    engines:
+      - type: wdl
+        engine: miniwdl
+
+  # The spot context uses EC2 spot instances which are usually cheaper but may be interrupted
+  spotCtx:
+    requestSpotInstances: true
+    engines:
+      - type: wdl
+        engine: miniwdl

examples/gatk-best-practices-project-miniwdl/gatk4-basic-joint-genotyping/MANIFEST.json

@@ -0,0 +1,7 @@
+{
+  "mainWorkflowURL": "gatk4-basic-joint-genotyping.wdl",
+  "inputFileURLs": [
+    "gatk4-basic-joint-genotyping.inputs.json"
+  ],
+  "engineOptions": "--no-cache"
+}

examples/gatk-best-practices-project-miniwdl/gatk4-basic-joint-genotyping/gatk4-basic-joint-genotyping.inputs.json

@@ -0,0 +1,12 @@
+{
+  "BasicJointGenotyping.input_gvcfs": [
+    "s3://1000genomes-dragen-3.7.6/data/individuals/hg38-graph-based/NA12329/NA12329.hard-filtered.gvcf.gz",
+    "s3://1000genomes-dragen-3.7.6/data/individuals/hg38-graph-based/NA06984/NA06984.hard-filtered.gvcf.gz",
+    "s3://1000genomes-dragen-3.7.6/data/individuals/hg38-graph-based/NA06989/NA06989.hard-filtered.gvcf.gz"
+  ],
+  "BasicJointGenotyping.ref_fasta": "s3://broad-references/hg38/v0/Homo_sapiens_assembly38.fasta",
+  "BasicJointGenotyping.ref_fasta_index": "s3://broad-references/hg38/v0/Homo_sapiens_assembly38.fasta.fai",
+  "BasicJointGenotyping.ref_dict": "s3://broad-references/hg38/v0/Homo_sapiens_assembly38.dict",
+  "BasicJointGenotyping.interval_list": "s3://broad-references/hg38/v0/hg38.even.handcurated.20k.chr20_test.intervals",
+  "BasicJointGenotyping.callset_name": "Trio"
+}