Added Dockstore-related files

.bashrc

@@ -0,0 +1,2 @@
+source /usr/share/modules/init/bash
+module use /modules/gsi/modulator/modulefiles/Ubuntu18.04

Dockerfile

@@ -0,0 +1,23 @@
+FROM modulator:latest
+
+MAINTAINER Fenglin Chen <f73chen@uwaterloo.ca>
+
+# packages should already be set up in modulator:latest
+USER root
+
+# move in the yaml to build modulefiles from
+COPY recipes/variant_effect_predictor_recipe.yaml /modulator/code/gsi/recipe.yaml
+
+# build the modules and set folder & file permissions
+RUN ./build-local-code /modulator/code/gsi/recipe.yaml --initsh /usr/share/modules/init/sh --output /modules && \
+	find /modules -type d -exec chmod 777 {} \; && \
+	find /modules -type f -exec chmod 777 {} \;
+
+# add the user
+RUN groupadd -r -g 1000 ubuntu && useradd -r -g ubuntu -u 1000 ubuntu
+USER ubuntu
+
+# copy the setup file to load the modules at startup
+COPY .bashrc /home/ubuntu/.bashrc
+
+CMD /bin/bash

Dockstore_README.md

@@ -0,0 +1,82 @@
+# dockstore_variantEffectPredictor
+
+The workflow is made to run in Docker and uploaded to [Dockstore](https://docs.dockstore.org/en/develop/getting-started/getting-started.html).
+You can find OICR's Dockstore page [here](https://dockstore.org/organizations/OICR).
+The Docker container is based on [Modulator](https://gitlab.oicr.on.ca/ResearchIT/modulator), which builds environment modules to set up the docker runtime environment.
+
+### Set Up and Run
+Currently, this WDL must be run with Cromwell. 
+It uses Cromwell configuration files to mount a directory to the docker container.
+The directory contains data modules built with Modulator, which the WDL tasks need to access.
+In addition, you must obtain run files locally and build data modules to a local directory.
+
+#### 1. Build Data Modules
+- Create a local `data_modules/` directory to store the data modules
+    - make sure you have enough disk space
+    - each data module could be 5-30 GB in size
+- In future iterations of the workflow, this process will be simplified
+- Enter the container:
+```
+# Mount this repository as /pipeline/; mount the data module destination directory as /data_modules/
+docker run -it --rm -v [PWD]:/pipeline -v [data_modules]:/data_modules [CONTAINER ID (find in options.json)]
+
+# Copy prerequisite code module YAMLs into the Modulator code directory (code/gsi/)
+cp /pipeline/recipes/variant_effect_predictor_data_modules_prep.yaml code/gsi/data_modules_recipe_prep.yaml
+
+# Build the prerequisite code modules
+./build-local-code code/gsi/data_modules_recipe_prep.yaml --output /data_modules --initsh /usr/share/modules/init/sh
+
+# Copy data module YAMLs into the Modulator data directory (data/gsi/)
+cp /pipeline/recipes/variant_effect_predictor_data_modules.yaml data/gsi/data_modules_recipe.yaml
+
+# Build the data modules
+./build-local-data data/gsi/data_modules_recipe.yaml --output /data_modules --initsh /usr/share/modules/init/sh
+
+# Change resulting file permissions
+find /data_modules/ -type d -exec chmod 777 {} \; && \
+find /data_modules/ -type f -exec chmod 777 {} \;
+
+# /data_modules/ should now contain gsi/modulator/modulefiles/Ubuntu18.04/ and gsi/modulator/modulefiles/data/
+```
+For run directories that are not part of modules, copy them from UGE's archive at `/.mounts/labs/gsi/src/`
+
+#### 2. Obtain Files Locally
+In the test json, change file paths like so:
+- File type files should be copied to local
+    - E.g. use scp to copy from UGE
+    - In the json, change the file path from UGE to local path
+- String type files should be copied or moved to the mounted directory, if it's not already part of a module
+    - In the json, change the file path to how the file would be accessed from inside the docker container
+- $MODULE_ROOT paths can stay the same
+```
+# File type files
+# File is copied to local machine
+UGE:       "/.mounts/labs/gsi/testdata/wgsPipeline/input_data/wgsPipeline_test_pcsi/hg19_random.genome.sizes.bed"
+Dockstore: "/home/ubuntu/data/sample_data/callability/hg19_random.genome.sizes.bed"
+
+# String type files
+# /data_modules/ is a directory mounted to the docker container
+UGE:       "/.mounts/labs/gsi/modulator/sw/data/hg19-p13/hg19_random.fa"
+Dockstore: "/data_modules/gsi/modulator/sw/data/hg19-p13/hg19_random.fa"
+
+# Root type paths
+# The value of $MODULE_ROOT changes, but the path stays the same
+UGE:       "$HG19_BWA_INDEX_ROOT/hg19_random.fa"
+Dockstore: "$HG19_BWA_INDEX_ROOT/hg19_random.fa"
+```
+
+#### 3. Run with Cromwell
+Submit the preprocessed subworkflow and modified json to Cromwell, with configs and options attached
+```
+# Validate the wrapper workflow and json
+java -jar $womtool validate [WDL] --inputs [TEST JSON]
+
+# For example:
+java -jar $womtool validate wgsPipeline.wdl --inputs tests/wgsPipeline_test_cre_uge.json
+
+# Submit to Cromwell
+java -Dconfig.file=[CONFIG] -jar $cromwell run [WRAPPER WDL] --inputs [JSON] --options [OPTIONS]
+
+# For example:
+java -Dconfig.file=local.config -jar $cromwell run wgsPipeline.wdl --inputs tests/wgsPipeline_test_cre.json --options options.json
+```

local.config

@@ -0,0 +1,49 @@
+backend {
+  default = "Local"
+  providers {
+    Local {
+      actor-factory = "cromwell.backend.impl.sfs.config.ConfigBackendLifecycleActorFactory"
+      config {
+        concurrent-job-limit = 10
+        #run-in-background = true
+        runtime-attributes = """
+        String? docker
+        String? docker_volume
+        String? modules
+        """
+        submit = "/usr/bin/env bash ${script}"
+        submit-docker = """
+        docker run \
+        --rm -i \
+        -v ${cwd}:${docker_cwd} \
+        ${"-v " + docker_volume} \
+        ${docker} /bin/bash -c 'source /home/ubuntu/.bashrc; ${"module load " + modules + " || exit 1; "} /bin/bash ${docker_script}'
+        """
+        root = "cromwell-executions"
+        dockerRoot = "/cromwell-executions"
+      }
+    }
+  }
+}
+call-caching {
+  enabled = true
+  invalidate-bad-cache-results = true
+}
+database {
+  profile = "slick.jdbc.HsqldbProfile$"
+  db {
+    driver = "org.hsqldb.jdbcDriver"
+    url = """
+    jdbc:hsqldb:file:/tmp/cromwell-executions/cromwell-db/cromwell-db;
+    shutdown=false;
+    hsqldb.default_table_type=cached;hsqldb.tx=mvcc;
+    hsqldb.result_max_memory_rows=10000;
+    hsqldb.large_data=true;
+    hsqldb.applog=1;
+    hsqldb.lob_compressed=true;
+    hsqldb.script_format=3
+    """
+    connectionTimeout = 120000
+    numThreads = 2
+   }
+}

options.json

@@ -0,0 +1,6 @@
+{
+  "default_runtime_attributes": {
+    "docker": "g3chen/varianteffectpredictor:2.0",
+    "docker_volume": "/home/ubuntu/Downloads/sample_data:/data"
+  }
+}

recipes/variant_effect_predictor_data_modules_prep.yaml

@@ -0,0 +1,112 @@
+# htslib/1.9
+- name: htslib
+  version: 1.9
+  build_type: autotools
+  build_args:
+    prereq_args:
+      prereq_args:
+        sha256: e04b877057e8b3b8425d957f057b42f0e8509173621d3eccaedd0da607d9929a
+        url: https://github.com/samtools/htslib/releases/download/1.9/htslib-1.9.tar.bz2
+      prereq_type: download
+    prereq_type: extract
+  system_depends:
+    - name: libbz2-dev
+    - name: liblzma-dev
+
+# samtools/1.9
+- name: samtools
+  version: 1.9
+  build_type: autotools
+  build_args:
+    prereq_args:
+      prereq_args:
+        sha256: 083f688d7070082411c72c27372104ed472ed7a620591d06f928e653ebc23482
+        url: https://github.com/samtools/samtools/releases/download/1.9/samtools-1.9.tar.bz2
+      prereq_type: download
+    prereq_type: extract
+    configure:
+    - --with-htslib={htslib_root}
+    - --enable-configure-htslib=false
+  depends:
+  - name: htslib
+    version: 1.9
+  system_depends:
+  - name: libncurses5-dev
+
+# fasplit/1.0
+- name: fasplit
+  version: 1.0
+  hidden: true
+  build_type: copy
+  build_args:
+    from: /pipeline/build_files/faSplit-20200114T16_09
+    to: "bin/faSplit"
+
+# java/8
+- name: java
+  version: 8
+  build_type: extract
+  build_args:
+    prereq_args:
+      sha256: 4ee3b37cb70fe1dbfad0ef449fe2c5fec43d81bd37ef0a65ec9f65afac190b4f
+      url: https://github.com/AdoptOpenJDK/openjdk8-upstream-binaries/releases/download/jdk8u222-b10/OpenJDK8U-jdk_x64_linux_8u222b10.tar.gz
+    prereq_type: download
+  system_depends:
+    - name: libfontconfig1-dev
+
+# picard/2.19.2
+- name: picard
+  version: 2.19.2
+  build_type: copy
+  build_args:
+    prereq_args:
+      sha256: 2b27f3c19529bfa9b1120b9a149b7b2a5ddf0832b1a9011dc803a80779b8ca35
+      url: https://github.com/broadinstitute/picard/releases/download/2.19.2/picard.jar
+    prereq_type: download
+    to: 'picard.jar'
+  depends:
+    - name: java
+      version: 8
+
+# bcftools/1.9
+- name: bcftools
+  version: 1.9
+  permitted_os: ["Ubuntu18.04"]
+  build_type: autotools
+  build_args:
+    prereq_args:
+      prereq_args:
+        sha256: 6f36d0e6f16ec4acf88649fb1565d443acf0ba40f25a9afd87f14d14d13070c8
+        url: https://github.com/samtools/bcftools/releases/download/1.9/bcftools-1.9.tar.bz2
+      prereq_type: download
+    prereq_type: extract
+    configure: ["--enable-libgsl"]
+  depends:
+    - name: htslib
+      version: 1.9
+  system_depends:
+    - name: libgsl-dev
+    - name: zlib1g-dev
+    - name: libbz2-dev
+    - name: liblzma-dev
+
+# tabix/1.9
+- name: tabix
+  version: 1.9
+  build_type: aggregate
+  depends:
+    - name: htslib
+      version: 1.9
+
+# vep-hg19-filter-somaticsites/0
+- name: vep-hg19-filter-somaticsites
+  version: 0
+  build_type: copy
+  build_args:
+    from: /pipeline/build_files/vep_hg19_filter_somaticsites.sh
+    to: bin/vep_hg19_filter_somaticsites
+  depends:
+    - name: bcftools
+      version: 1.9
+    - name: tabix
+      version: 1.9