Antonio Fernandez-Guerra genomewalker

genomewalker / example_workflow.sh

Last active September 27, 2017 13:13

Tiny script to create aminoacid sequences with different types of mutations

	# Example for N. maritimus
	# First we generate a set of mutants
	python generate_mutants.py -g GCF_000018465.1_ASM1846v1_protein.faa -n 3 -o nmarit

	# We label our seeds or references
	awk '{if ($0 ~ /^>/) {print $1"_ref"}else{print $0}}' ../GCF_000018465.1_ASM1846v1_protein.faa > nmarit_aa_ref.fasta

	# Concatenate mutants and references
	cat nmarsub.fasta nmarins.fasta nmardel.fasta nmarall.fasta nmarit_aa_ref.fasta > nmarit_all_aa.fasta

genomewalker / source_rmd.R

Created February 20, 2017 10:24 — forked from noamross/source_rmd.R

Source an RMD file

	#' Source the R code from an knitr file, optionally skipping plots
	#'
	#' @param file the knitr file to source
	#' @param skip_plots whether to make plots. If TRUE (default) sets a null graphics device
	#'
	#' @return This function is called for its side effects
	#' @export
	source_rmd = function(file, skip_plots = TRUE) {
	temp = tempfile(fileext=".R")
	knitr::purl(file, output=temp)

genomewalker / OSD_primer_collection.txt

Last active April 5, 2016 08:30

genomewalker / fa2sto.sh

Last active January 22, 2016 08:23

	#!/bin/bash

	# We need one fasta file export with the aligned sequences and another with the SS SAI filter
	ALIGN=${1}
	OFILE=${1/.fasta/.stk}

	# Creating the first part of the file
	# we need to linearize the fasta file
	awk '
	BEGIN{

genomewalker / get_orf_coverage_from_bam-coAssembly.awk

Last active August 29, 2015 14:26

	#Read a hist file from bedtools coverage -hist and create a coverage per orf file.
	#Coverage per each gene is calculated as: coverage_orfA = sum(depth_of_coverage * fraction_covered)
	{
	if ($0 i ~ /^all/){
	next;
	}else{
	split($4,a,"_");
	b=$1"_"$6"_"$2+1"_"$3"_orf-"a[2]"\t"$13;
	c[b]=c[b] + ($11*$14)
	}