sp00nman

# Credits to Michael Schuster for this useful onliner
# find . -name '*.fastq' finds all fastqs in current directory
# -print --> print the processed files
# -exec gzip --best {} --> the gzip command for each file; gzips the file (keeps timestamp) and removes the orginial
# \ --> escapes the semicolon from bash
# ; --> end of exec command line
find . -name '*.fastq' -print -exec gzip --best {} \;

sp00nman

Introduction to linux command line/ipython/git/R for bioinformatics:

• https://github.com/biom262/biom262-2016
• https://github.com/ricket-sjtu/bi028
• https://github.com/YeoLab/single-cell-bioinformatics/
• https://github.com/YeoLab/single-cell-bioinformatics/tree/master/notebooks
• https://github.com/ltminty/Bioinformatics-and-R/blob/master/Rbioinformatics.ipynb

RNA-seq:

• https://github.com/Caroldm/RNA-Seq-Tutorial---Jupyter-notebook/blob/master/RNAseq%20tutorial.ipynb

sp00nman

#! /usr/bin/env Rscript

suppressPackageStartupMessages(expr = library(package = "rtracklayer"))

reference_granges <- import(con ='file1.gtf')
reference_frame <- unique(x = data.frame(
  ensembl_gene_id = reference_granges$gene_id,
  ensembl_transcript_id = reference_granges$transcript_id,
  stringsAsFactors = FALSE))
rm(reference_granges)

sp00nman

#!/bin/bash

BED_FILE=$1

sort -k1,1 -k2,2n $BED_FILE >${BED_FILE}_sorted.bed

## format
#chr1  12
#chr2  56
#chr10 13

sp00nman

# Gist kindly provided by M.Schuster (https://github.com/mkschuster)

rsync \
    --verbose \
    --recursive \
    --delete \
    --times \
    --rsh 'ssh' \
    --exclude '*~' \
    --exclude '.DS_Store' \

sp00nman

#Example_input.bed
#ENST00000456328 1 + 11868 14409 11868 11868 3 11868,12612,13220, 12227,12721,14409, DDX11L1

awk '{chrom=$2; gsub(chrom,"chr"chrom,$2)}{print $0}' Example_input.bed >Example_output.bed

#Example_output.bed
#ENST00000456328 chr1 + 11868 14409 11868 11868 3 11868,12612,13220, 12227,12721,14409, DDX11L1

sp00nman

#!/bin/bash

# UPD...unique patient ID; file with UPDs
# eg. H_0047C\nH_0060A\nH_0062D\n... \n newline separated
UPD=$1 

# SPATH...search path
SPATH=$2

# FEXTENSION...file extension to search for [eg. .fastq.gz]

sp00nman

#!/bin/awk -f

BEGIN{OFS="\t"}
{ start[NR]=$4; 
  end[NR]=$5; 
  strand[NR]=$7; 
  ID[NR]=$11; 
  chr[NR]=$1; 
  ens[NR]=$9; 
  symb[NR]=$10} 

sp00nman

awk -F"\t" 'NR==FNR {f1[$2]=$0;next}($4 in f1){print $0"\t"f1[$4]}' file1 file2

sp00nman

# resource: http://seqanswers.com/forums/showthread.php?t=4914
# Calculate length for each transcript for a GTF file
awk -F"\t" '
$3=="exon" 
    {
        ID=substr($9, length($9)-16, 15); 
        L[ID]+=$5-$4+1
    } 
END{
    for(i in L)