SimRead

#!/bin/bash
#####################################################################################################################
#					WORK SPACE AND DOWNLOAD GENOME REFERENCE			    	    #
#						  BY: FRANCISCO ASCUE						    #
#					email: francisco.ascue131@gmail.com					    #
#####################################################################################################################

normal=$'\e[0m'
bold=$(tput bold)                         # make colors bold/bright
red="$bold$(tput setaf 1)"                # bright red text
green=$(tput setaf 2)                     # dim green text
fawn=$(tput setaf 3); beige="$fawn"       # dark yellow text
yellow="$bold$fawn"                       # bright yellow text
darkblue=$(tput setaf 4)                  # dim blue text
blue="$bold$darkblue"                     # bright blue text
purple=$(tput setaf 5); magenta="$purple" # magenta text
pink="$bold$purple"                       # bright magenta text
darkcyan=$(tput setaf 6)                  # dim cyan text
cyan="$bold$darkcyan"                     # bright cyan text
gray=$(tput setaf 7)                      # dim white text
darkgray="$bold"$(tput setaf 0)           # bold black = dark gray text
white="$bold$gray"                        # bright white text



usage="$(basename "$0") -- Program to create simulation reads for illumina sequencing in GNU/Linux. 

program maintended at https://github.com/FranciscoAscue/Minicurso_transcriptomica/blob/master/SimRead

usage: $(basename "$0") -n <project> -g <N.A. NCBI> -r <20000> -f <fastqfile>

where:
    -h 			Show this help text
    -n  <name>		Name of project
    -g 	<N.A. NCBI>	N.A. of reference genome
    -r  <number>	Number of reads simulated
    -f  <str>		Name of fastq files
    -s  <number>	set the seed value (default: 42)
    -m	<float>		Rate of mutation of reference genome
    -e	<float>		Rate of error sequencing simulation"

## defaults

seed=42
PJT="Project"
GF=""
reads=3000
name="file"
rmutation=0
rerror=0.001

## getopts

while getopts ':h:n:g:r:f:m:e:' option; do
  case "$option" in
    h) echo "${cyan}$usage"
       exit
       ;;
    n) PJT="$OPTARG";;
    g) GF="$OPTARG";;
    r) reads=$OPTARG
       ;;
    f) name="$OPTARG";;
    m) rmutation=$OPTARG;;
    e) rerror=$OPTARG;;
    :) printf "missing argument for -%s\n" "$OPTARG" >&2
       echo "$usage" >&2
       exit 1
       ;;
   \?) printf "illegal option: -%s\n" "$OPTARG" >&2
       echo "$usage" >&2
       exit 1
       	;;
  esac
done
shift $((OPTIND - 1))



echo "${green}started at `date`${normal}"

echo "${cyan}-------------------------------------------------------------"
echo "--------------CREATE WORKING DIRECTORY------------------"
echo "-------------------------------------------------------------"
echo ""
echo "── $PJT/
   │   └── data/                   	<- Folder to store reads and references files
   │       ├── reads/               	<- Reads illumina simulated
   │           ├──file_1.fastq           <- Forward read
   │           ├──file_2.fastq           <- Reverse read
   │           
   │       ├── reference/                <- Host genomes files (.fasta)
   │           ├──NA_NCBI.fasta          <- NCBI download fasta file
   │  
   │   └── results/              	<- Folder to store data generated during processing steps
   │  
   │   └── scripts/                   	<- Folder to store scripts for data processing
           ├── logs/        		<- Results logs during processing steps
 ${normal}"
echo ""

mkdir -p $PJT/{data/{reads,reference},results,scripts/logs}
echo "${blue}-------------------------------------------------------------"
echo "--------------DOWNLOAD GENOME REFERENCE------------------"
echo "-------------------------------------------------------------"
echo "${normal}"
### Download reference genome
echo "${fawn}"

esearch -db nucleotide -query "$GF" | esummary | sed "s/></\n/g" | sed "s/>/\t/g" | sed "s/</\t/g" | awk 'NR>=6&&NR<=41'

echo ""
esearch -db nucleotide -query "$GF" | efetch -format fasta > $PJT/data/reference/${GF}.fasta

echo "${red}-------------------------------------------------------------"
echo "--------------READS ILLUMINA SIMULATION------------------"
echo "-------------------------------------------------------------${normal}"
echo "${green}"

### Reads simulation
echo "wgsim -1151 -2151 -d300 -r"${rmutation}" -e"${rerror}" -N"${reads}" -R0 -X0 ${GF}.fastq ${name}_1.fastq ${name}_2.fasta"

wgsim -1151 -2151 -d300 -r"${rmutation}" -e"${rerror}" -N"${reads}" -R0 -X0 $PJT/data/reference/${GF}.fasta $PJT/data/reads/${name}_1.fastq $PJT/data/reads/${name}_2.fastq

for i in 0.01 0.005 0.001
do
	wgsim -1151 -2151 -d300 -e${i} -N"${reads}" -R0 -X0 $PJT/data/reference/${GF}.fasta $PJT/data/reads/${i}_1.fastq $PJT/data/reads/${i}_2.fastq
	cat $PJT/data/reads/${i}_1.fastq >> $PJT/data/reads/${name}_1.fastq
	cat $PJT/data/reads/${i}_2.fastq >> $PJT/data/reads/${name}_2.fastq
	rm $PJT/data/reads/${i}_1.fastq $PJT/data/reads/${i}_2.fastq
done


echo "total reads simulated"
echo "(forward and reverse)"

cat $PJT/data/reads/${name}_1.fastq $PJT/data/reads/${name}_2.fastq | echo $((`wc -l`/4))

echo "${purple}"

echo "Finished at `date`"