Merge pull request #8 from rse-ops/add/snakemake

add snakemake tutorial example workflow

snakemake/atacseq/Dockerfile

@@ -0,0 +1,30 @@
+ARG flux_restful_tag=latest
+FROM ghcr.io/flux-framework/flux-restful-api:${flux_restful_tag}
+
+# docker build -t snakemake .
+# command: snakemake --cores 1 --flux 
+# workdir: /workflow
+
+USER root
+RUN apt-get update
+RUN DEBIAN_FRONTEND="noninteractive" apt-get -y install \
+    python3 \
+    python3-pip \
+    curl \
+    && apt-get clean \
+    && apt-get autoremove \
+    && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+# Wrappers to ensure we source the mamba environment!
+RUN git clone --depth 1 https://github.com/snakemake/snakemake-tutorial-data /workflow
+WORKDIR /workflow
+
+# This wraps the existing entrypoint
+COPY ./setup.sh ./Snakefile ./
+RUN mkdir ./scripts && /bin/bash setup.sh
+COPY ./scripts/plot-quals.py ./scripts/plot-quals.py
+
+# This is probably cheating a bit :)
+# instead of altering the entrypoint to active the environment!
+ENV PATH=/root/micromamba/envs/snakemake/bin:$PATH
+WORKDIR /code

snakemake/atacseq/README.md

@@ -0,0 +1,78 @@
+# Flux Snakemake Example
+
+This is an example container where you can build (optional) and run
+the [Snakemake tutorial workflow](https://snakemake.readthedocs.io/en/stable/tutorial/tutorial.html):
+
+```bash
+$ docker build -t snakemake .
+```
+
+or with a tag for the restful API:
+
+```bash
+$ docker build --no-cache --build-arg app="latest" -t snakemake .
+```
+
+## Running the Workflow
+
+### RESTFul API and Interface
+
+To use the Flux RESTFul API and interface:
+
+```
+$ docker run -it -p 5000:5000 snakemake
+```
+
+Requiring a Flux user/token (fluxuser and 12345)
+
+```bash
+$ docker run -it --env require_auth=true -p 5000:5000 snakemake
+```
+
+And then enter the fluxuser and 123456 as the user and token, and try submitting a job to
+the examples like:
+
+```console
+# Potential command and workdir
+# command: snakemake --cores 1 --flux 
+# workdir: /workflow
+```
+
+![img/submit.png](img/submit.png)
+
+And then browse to the table and click on the ID to see the log.
+
+![img/log.png](img/log.png)
+
+You can also try using the [RESTFul API](https://flux-framework.org/flux-restful-api/getting_started/user-guide.html#getting-started-user-guide--page-root). Have fun!
+
+### Manual
+
+Or just shell into the container:
+
+```bash
+$ docker run -it --entrypoint bash snakemake
+```
+
+Activate the environment:
+
+```bash
+$ micromamba shell init --shell=bash --prefix=~/micromamba
+$ source /root/.bashrc
+$ eval $(micromamba shell hook --shell=bash)
+$ micromamba activate snakemake
+```
+
+And then start the flux instance:
+
+```bash
+$ flux start --test-size=4
+```
+
+And go to the snakemake workflow, and run it with Flux!
+
+```bash
+$ cd /workflow
+$ snakemake --cores 1 --flux
+```
+That's it! 

snakemake/atacseq/Snakefile

@@ -0,0 +1,56 @@
+SAMPLES = ["A", "B"]
+
+
+rule all:
+    input:
+        "plots/quals.svg"
+
+
+rule bwa_map:
+    input:
+        "data/genome.fa",
+        "data/samples/{sample}.fastq"
+    output:
+        "mapped_reads/{sample}.bam"
+    shell:
+        "bwa mem {input} | samtools view -Sb - > {output}"
+
+
+rule samtools_sort:
+    input:
+        "mapped_reads/{sample}.bam"
+    output:
+        "sorted_reads/{sample}.bam"
+    shell:
+        "samtools sort -T sorted_reads/{wildcards.sample} "
+        "-O bam {input} > {output}"
+
+
+rule samtools_index:
+    input:
+        "sorted_reads/{sample}.bam"
+    output:
+        "sorted_reads/{sample}.bam.bai"
+    shell:
+        "samtools index {input}"
+
+
+rule bcftools_call:
+    input:
+        fa="data/genome.fa",
+        bam=expand("sorted_reads/{sample}.bam", sample=SAMPLES),
+        bai=expand("sorted_reads/{sample}.bam.bai", sample=SAMPLES)
+    output:
+        "calls/all.vcf"
+    shell:
+        "bcftools mpileup -f {input.fa} {input.bam} | "
+        "bcftools call -mv - > {output}"
+
+
+rule plot_quals:
+    input:
+        "calls/all.vcf"
+    output:
+        "plots/quals.svg"
+    script:
+        "scripts/plot-quals.py"

snakemake/atacseq/scripts/plot-quals.py

@@ -0,0 +1,9 @@
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+from pysam import VariantFile
+
+quals = [record.qual for record in VariantFile(snakemake.input[0])]
+plt.hist(quals)
+
+plt.savefig(snakemake.output[0])

snakemake/atacseq/setup.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+set -eEu -o pipefail
+
+# Setup the mamba environment with snakedeploy
+curl -Ls https://micro.mamba.pm/api/micromamba/linux-64/latest | tar -xvj bin/micromamba
+mv bin/micromamba /usr/local/bin && rmdir bin
+which micromamba
+micromamba create --prefix snakemake -f environment.yaml
+micromamba shell init --shell=bash --prefix=~/micromamba

snakemake/atacseq/uptodate.yaml

@@ -0,0 +1,7 @@
+dockerbuild:
+
+  build_args:
+    flux_restful_tag:
+      key: app
+      versions:
+       - latest