michaelbarton

+ TASK=merge
++ fetch_task_from_taskfile.sh /usr/local/share/Taskfile merge
+ CMD=' production_pipeline_merged_reads.sh ${READS} ${CONTIGS}'
++ biobox_args.sh 'select(has("fastq")) | .fastq | map(.value) | join(",")'
+ READS=/bbx/mount/n5ERGV8O49Zk88yXlx4Vk51Q4/661e5b3077313052c79383ea12f7e0a2aaea0e93ec405f9c96619038e981553d.fq.gz
+ CONTIGS=/bbx/output/contigs.fa
++ grep MemTotal: /proc/meminfo
++ tr -s ' '
++ cut -f 2 -d ' '
+ MEM_IN_KB=32946432

michaelbarton

```{r}

library(lme4)

null <- glm.nb(gene_l1_norm ~ 1, data = data)
genome_null <- glm.nb(gene_l1_norm ~ biological_source_name, data = data)

n_misassemblies <- glm.nb(gene_l1_norm ~ n_misassemblies, data = data)
n_misassemblies_genome <- glmer.nb(gene_l1_norm ~ n_misassemblies + (1|biological_source_name), data = data)

michaelbarton

[
    {
        "abandon_library": 0,
        "data_usable": 1,
        "id": "PMO00001",
        "jira_msg": "This library appears to be incorrectly scoped for the given project type. Please check the project parameters.",
        "lab_action": "No Lab Action",
        "segment_msg": "This library appears to be incorrectly scoped. Please check the project parameters.",
        "sow_item": "Needs PMO Attention",
        "type": "project"

michaelbarton

Needs bitly/data_hacks

pip install --user data_hacks

michaelbarton

Quick Start Guide

The following is a step by step example of how to build a docker image that complies to the "bioboxes" standard which means only a small amount of code should have to be changed in order build customized assembly docker images. All the steps required to build and run a docker image should be included here but you should consult "bioboxes.org" for details.

If you use the minia assembler as an example, and follow these steps, you should be able to build and run the minia image without changing any code.

michaelbarton

#!/usr/bin/env Rscript

# Assume that the libraries are installed in "../vendor/r/"
# Adjust this path to the relative path between the script
# and the packrat directory

set_package_environment <- function(args){
  dir  <- dirname(sub("--file=", "", args[grep("--file", args)]))
  libs <- file.path(dir, "..", "vendor", "r", "packrat", "lib", "*", "*")
  .libPaths(c(.libPaths(), libs))

michaelbarton

++ mktemp -d
+ TMP_DIR=/tmp/tmp.jL0YC9HdH6
+ cd /tmp/tmp.jL0YC9HdH6
+ PROC=default
++ cut -f 2 -d :
++ egrep '^default:' /Procfile
+ CMD=' minia -in /inputs/reads.fq.gz -kmer-size 55 -abundance 5 -out genome'
+ [[ -z  minia -in /inputs/reads.fq.gz -kmer-size 55 -abundance 5 -out genome ]]
+ eval minia -in /inputs/reads.fq.gz -kmer-size 55 -abundance 5 -out genome
++ minia -in /inputs/reads.fq.gz -kmer-size 55 -abundance 5 -out genome

michaelbarton

++ mktemp -d
+ TMP_DIR=/tmp/tmp.5CiDif8NjP
+ cd /tmp/tmp.5CiDif8NjP
+ PROC=default
++ cut -f 2 -d :
++ egrep '^default:' /Procfile
+ CMD=' gatb -p /inputs/reads.fq.gz --multik -o genome '
+ [[ -z  gatb -p /inputs/reads.fq.gz --multik -o genome  ]]
+ eval gatb -p /inputs/reads.fq.gz --multik -o genome
++ gatb -p /inputs/reads.fq.gz --multik -o genome

michaelbarton

bind-key        C-a last-window
bind-key        C-c run-shell "tmux show-buffer | reattach-to-user-namespace pbcopy"
bind-key        C-o rotate-window
bind-key        C-v run-shell "reattach-to-user-namespace pbpaste | tmux load-buffer - && tmux paste-buffer"
bind-key        C-z suspend-client
bind-key      Space copy-mode
bind-key          ! break-pane
bind-key          " split-window
bind-key          # list-buffers
bind-key          $ command-prompt -I #S "rename-session '%%'"

michaelbarton

Introduction

Purpose

The purpose of this document is provide a detailed specification for developers to write community-standardised bioinformatics containers. The audience of this document are bioinformaticians writing bioinformatics code that can be shared interchangeably using Linux containers. This document will describe the interfaces that a developer may expect to be available when the container is run.