opplatek

#!/bin/bash
# 
# Speed up deepTools computeMatrix by splitting the references into smaller chunks and then merging the matrices together
#

positions=5000
threads=12

rnd=$RANDOM

opplatek

#!/usr/bin/python3
#
# Python script for programtic access to Revigo. Run it with (last output file name is optional):
# python3 revigo.py example.csv 9606
# http://revigo.irb.hr/FAQ.aspx -> How do I integrate Revigo with my service or a programming language? -> The advanced job submitting method
#
# Make revigo python virtual env.
#python3 -m venv revigo
#source revigo/bin/activate
#pip install --upgrade pip

opplatek

#
# Splitting vector into smaller chunks by a separator and extracting chunk(s)
#

split_vector <- function (x, sep, column){
#  sapply(x, function(x) strsplit(x, split = sep, fixed = T)[[1]][column], USE.NAMES = F)
  unlist(lapply(x, function(x) strsplit(x, sep, fixed = T)[[1]][column]))
}

# Test

opplatek

# Get all the sequences from fastq.gz
zcat in.fastq.gz | awk 'NR == 2 || NR % 4 == 2'

# Get all the sequence names from fastq.gz
zcat in.fastq.gz | awk 'NR == 1 || NR % 4 == 1'

opplatek

#!/bin/bash
#
# Quickly extract unique read names from SAM/BAM file
# Source: https://www.biostars.org/p/371705/#371748 
#
# This will extract unique read names for all unampped reads (-f 4) from BAM file
# awk is much faster than `sort --parallel=$threads | uniq` because it doesn't have to do the sorting
# On BAM file with 149,909,118 input reads:
# sort | uniq takes (with 12 threads):
#real    1m8.240s

opplatek

#!/usr/bin/python3

import sys

# If intab (input) is defined, read it; if not assume stdin
if intab:
    f = open(intab, "r")
else:
    f = sys.stdin

opplatek

#!/bin/bash
#
# Replace one or more spaces (characters) with sed
# Important: there are two spaces before the * character
# Note: If you don't quote $text, echo will strip multiple spaces to just one
#

text="hello     world"
echo "$text" | sed 's/  */X/g'
#helloXworld

opplatek

#!/bin/bash
#
# Get miRBase hairpin FASTA (multiline, with U instead of T) and reformat it to "normal" reference FASTA
#

wget ftp://mirbase.org/pub/mirbase/21/hairpin.fa.gz # Get the sequence

zcat hairpin.fa.gz | perl -pe '/^>/ ? print "\n" : chomp' \
    | tail -n +2 | sed '/^[^>]/ y/uU/tT/' \
    > hairpin.oneline.fasta # Convert to one-line fasta and replace all Us for Ts

opplatek

#!/bin/bash
#
# Replace first line in a file
#

# Insert first line
echo -e "a\nb" | sed '1i transcript_id\tlength'

# Replace - remove and replace first line
echo -e "a\nb" | tail -n+2 | sed '1i transcript_id\tlength'

opplatek

#!/bin/bash
#
# Quickly remap reads from BAM file to new reference
#
# Source: https://twitter.com/lh3lh3/status/1132756684789768202
# More details: https://janbio.home.blog/2019/05/30/useful-one-liners-collection/
#

samtools collate -uOn128 old-pos-srt.bam tmpxyz \
  | samtools fastq - \