SamStudio8

---
title: "Samposium v1"
url: "/v1/"
layout: "old_archive"
---

This listing enumerates the posts from the previous iteration of Samposium.
Posts range between long rambling posts about my PhD that I never expected anyone to read, and things that I did to distract myself from finishing my PhD that I hoped people would read.
Each link will take you to a static snapshot of the decommissioned Wordpress post.

SamStudio8

#!/usr/bin/env bash
# Name subset_xam
# Description Safely subset a BAM (or CRAM) with samtools+picard
# Author @samstudio8
# Date 2022-11-01
# Version 1.0.3
PICARD_JAR=${PICARD_JAR:-}
xam=$1
ref=$2
seq=$3

SamStudio8

# Nicer syntax but leads to ugly job names,
# and doesn't work when variables strings are long
# See https://gitlab.com/gitlab-org/gitlab/-/issues/362262
my-job:
  extends: base-job
  parallel:
    matrix:
      - OWLS: 1
        CATS: 0
      - OWLS: 0

SamStudio8

#!/usr/bin/env python3
import sys
import subprocess

p = subprocess.Popen("git ls-files --others --exclude-standard", shell=True, stdout=subprocess.PIPE)
out, err = p.communicate()

migrations = []
for unchecked_rp in out.decode('UTF-8').split('\n'):
    if "migrations" in unchecked_rp:

SamStudio8

#!/usr/bin/env nextflow

params.testdir = "/cephfs/covid/software/sam/nf-test/"

params.fofn_single = [params.testdir, 'samples.csv'].join('/')
single_manifest_ch = Channel
    .fromPath(params.fofn_single)  // open say, a CSV
    .splitCsv(header:true)         // split text stream into CSV records
    .map { row-> file(row.path) }  // coerce the record and return a file for each line
    .collect()                     // emit all items as one

SamStudio8

# kraken2-microbial database
## Monday 3rd September 2018
## s.nicholls.1

KDB=$1

kraken2-build --download-taxonomy --threads 24 --db $KDB

kraken2-build --download-library archaea --db $KDB
kraken2-build --download-library bacteria --db $KDB

SamStudio8

#!/bin/bash

USER_ID=${LOCAL_USER_ID:-9001}

echo "starting with UID : $USER_ID"

echo "creating RAMPART user"
useradd --shell /bin/bash -u $USER_ID -o -c "" -m rampart

echo "raising RAMPART on $CLIENT $SERVER"

SamStudio8

rm counties.*
rm *csv

# England ######################################################################
curl -O -J -L https://www.registers.service.gov.uk/registers/local-authority-eng/download-csv

# https://www.datadictionary.nhs.uk/data_dictionary/nhs_business_definitions/l/local_authority_de.asp?
# A Local Authority, in relation to England is:
## a County Council
awk -F',' '$6=="CTY" {print $7}' local-authority-eng.csv >> counties.eng.ls

SamStudio8

import argparse
import sys
import random
import numpy as np

import pysam

parser = argparse.ArgumentParser(description="A very very very bad read generator.")
parser.add_argument("shred", type=int)
parser.add_argument("fasta")

SamStudio8

library(tidyverse)

assemblies=read_tsv('kraken_summary.bond.tsv')

short_name <- c(
  "Bacillus subtilis" = "bs",
  "Cryptococcus neoformans" = "cn",
  "Enterococcus faecalis" = "ef",
  "Escherichia coli" = "ec",
  "Lactobacillus fermentum" = "lf",