Skip to content

Commit

Permalink
Adding in all the work from the long-term Special Project Malaria bra…
Browse files Browse the repository at this point in the history
…nch (#440)

* Adding in all the work from the long-term Special Project Malaria branch
  • Loading branch information
jonn-smith authored Jan 10, 2024
1 parent b1655b1 commit 35a109c
Show file tree
Hide file tree
Showing 69 changed files with 13,917 additions and 202 deletions.
54 changes: 54 additions & 0 deletions .dockstore.yml
Original file line number Diff line number Diff line change
Expand Up @@ -72,12 +72,30 @@ workflows:
- name: PBMASIsoSeqDemultiplex
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/PacBio/Utility/PBMASIsoSeqDemultiplex.wdl
- name: SRBamToFq
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/SRBamToFq.wdl
- name: SRIndexBam
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/SRIndexBam.wdl
- name: SRWholeGenome
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/ILMN/VariantCalling/SRWholeGenome.wdl
- name: SRFlowcell
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/ILMN/Alignment/SRFlowcell.wdl
- name: SRJointCallGVCFsWithGenomicsDB
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/VariantCalling/SRJointCallGVCFsWithGenomicsDB.wdl
- name: LRJointCallGVCFs
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/VariantCalling/LRJointCallGVCFs.wdl
- name: ConvertToHailMT
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/ConvertToHailMT.wdl
- name: ConvertToZarrStore
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/ConvertToZarrStore.wdl
- name: LRConvertBCF
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/LRConvertBCF.wdl
Expand All @@ -96,3 +114,39 @@ workflows:
- name: CleanupIntermediate
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/CleanupIntermediate.wdl
- name: BenchmarkVCFs
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/BenchmarkVCFs.wdl
- name: CompareVcfBenchmarks
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/CompareVcfBenchmarks.wdl
- name: PanelProcessMalariaBarcodesForRh
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/TertiaryAnalysis/PanelProcessMalariaBarcodesForRh.wdl
- name: ProcessMalariaBarcodesDemo
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/TertiaryAnalysis/ProcessMalariaBarcodesDemo.wdl
- name: ExtractRegionsFromBam
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/Utility/ExtractRegionsFromBam.wdl
- name: PfalciparumDrugResistanceSummary
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/TertiaryAnalysis/PfalciparumDrugResistanceSummary.wdl
- name: SRWholeGenome_Pf_Niare_VQSR
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/Z_One_Off_Analyses/SRWholeGenome_Pf_Niare_VQSR.wdl
- name: SRWholeGenome_Pf_Niare_VETS
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/Z_One_Off_Analyses/SRWholeGenome_Pf_Niare_VETS.wdl
- name: SRJointCallGVCFsWithGenomicsDB_Pf_Niare_VQSR
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/Z_One_Off_Analyses/SRJointCallGVCFsWithGenomicsDB_Pf_Niare_VQSR.wdl
- name: SRJointCallGVCFsWithGenomicsDB_Pf_Niare_VETS
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/Z_One_Off_Analyses/SRJointCallGVCFsWithGenomicsDB_Pf_Niare_VETS.wdl
- name: ExpandedDrugResistanceMarkerExtraction
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/TertiaryAnalysis/ExpandedDrugResistanceMarkerExtraction.wdl
- name: ExpandedDrugResistanceMarkerAggregation
subclass: wdl
primaryDescriptorPath: /wdl/pipelines/TechAgnostic/TertiaryAnalysis/ExpandedDrugResistanceMarkerAggregation.wdl
70 changes: 70 additions & 0 deletions docker/lr-functional-annotation/Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
# Start with a good base python3 image:
FROM ubuntu:20.04
MAINTAINER Jonn Smith <[email protected]>

# Make sure we don't need to interact with any package installations:
ARG DEBIAN_FRONTEND=noninteractive

# Set the working directory to /
WORKDIR /

################################################################################
# Install system packages:

# Make sure we can actually talk to package repos:
RUN apt-get update
RUN apt-get install -y apt-utils
RUN apt-get -y upgrade

RUN apt-get update && apt-get -y upgrade

# Development / prereqs for building software:
# Utilities / tools:
# Get libcurses:
# install gsutil requirements:
RUN apt-get -y install make gcc g++ autoconf sudo && \
apt-get -y install git bash vim time bc sed perl wget curl bzip2 man unzip && \
apt-get -y install liblzma-dev libbz2-dev libncurses5-dev libncursesw5-dev && \
apt-get --allow-releaseinfo-change update && \
apt install -y curl git-lfs time datamash

# Install python:
RUN apt-get install -y python python3 python3-pip

# Setup crcmodc for gsutil:
RUN apt-get install -y gcc python3-dev python3-setuptools && \
pip3 uninstall -y crcmod && \
pip3 install --no-cache-dir -U crcmod

# install gsutil:
RUN curl https://sdk.cloud.google.com | bash

# Get Java:
# Install OpenJDK-8
RUN apt-get update && \
apt-get install -y openjdk-11-jdk && \
apt-get install -y ant && \
apt-get clean

# Fix certificate issues
RUN apt-get update && \
apt-get install ca-certificates-java && \
apt-get clean && \
update-ca-certificates -f

# Setup JAVA_HOME -- useful for docker commandline
ENV JAVA_HOME /usr/lib/jvm/java-11-openjdk-amd64/
RUN export JAVA_HOME

# Get snPEff
RUN wget https://snpeff.blob.core.windows.net/versions/snpEff_latest_core.zip && \
unzip snpEff_latest_core.zip

# Get tabix (for bgzip):
RUN apt-get install -y tabix

################################################################################
# Final runtime configuration:
# Let's start at the root:
WORKDIR /

17 changes: 17 additions & 0 deletions docker/lr-functional-annotation/Makefile
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
IMAGE_NAME = lr-functional-annotation
VERSION = 0.0.1

TAG1 = us.gcr.io/broad-dsp-lrma/$(IMAGE_NAME):$(VERSION)
TAG2 = us.gcr.io/broad-dsp-lrma/$(IMAGE_NAME):latest

all: | build push

build:
docker build -t $(TAG1) -t $(TAG2) .

build_no_cache:
docker build --no-cache -t $(TAG1) -t $(TAG2) .

push:
docker push $(TAG1)
docker push $(TAG2)
33 changes: 33 additions & 0 deletions docker/lr-malaria/Dockerfile
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
FROM continuumio/miniconda3:22.11.1

MAINTAINER Jonn Smith

# Set the resolver to libmamba:
RUN conda update -y -n base conda && \
conda install -y -c conda-forge conda-pack libmamba && \
conda config --set solver libmamba && \
conda clean --all --yes

# copy other resources
COPY ./environment.yml /

# install conda packages
RUN conda env create -f /environment.yml && conda clean -a
ENV PATH=/root/google-cloud-sdk/bin/:${PATH}

# install gsutil
RUN apt-get --allow-releaseinfo-change update
RUN apt install -y curl git-lfs time datamash
RUN curl https://sdk.cloud.google.com | bash

# Setup crcmodc for gsutil:
RUN apt-get install -y gcc python3-dev python3-setuptools && \
pip3 uninstall -y crcmod && \
pip3 install --no-cache-dir -U crcmod

# copy python scripts
COPY python/* /python_scripts/
RUN chmod +x /python_scripts/*

# activate conda environment
RUN echo "source activate lr-malaria" > ~/.bashrc
17 changes: 17 additions & 0 deletions docker/lr-malaria/Makefile
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
IMAGE_NAME = lr-malaria
VERSION = 0.0.1

TAG1 = us.gcr.io/broad-dsp-lrma/$(IMAGE_NAME):$(VERSION)
TAG2 = us.gcr.io/broad-dsp-lrma/$(IMAGE_NAME):latest

all: | build push

build:
docker build -t $(TAG1) -t $(TAG2) .

build_no_cache:
docker build --no-cache -t $(TAG1) -t $(TAG2) .

push:
docker push $(TAG1)
docker push $(TAG2)
22 changes: 22 additions & 0 deletions docker/lr-malaria/environment.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
name: lr-malaria
channels:
- default
- bioconda
- anaconda
dependencies:
- python=3.6
- cython
- pip
- pip:
- numpy
- scipy
- pandas
- seaborn
- statsmodels
- networkx
- matplotlib
- patsy
- openpyxl
- scikit-learn
- numpyencoder
- tqdm
Loading

0 comments on commit 35a109c

Please sign in to comment.