polish: add args, polish all process
This commit is contained in:
parent
d639d38659
commit
74c2dde71e
1 changed files with 221 additions and 23 deletions
244
batch.sh
244
batch.sh
|
|
@ -1,44 +1,242 @@
|
||||||
|
#!/bin/bash
|
||||||
|
|
||||||
### Environment Setting
|
### Environment Setting
|
||||||
|
|
||||||
|
pkgver=0.0.1
|
||||||
DirRaw=00_raw
|
DirRaw=00_raw
|
||||||
DirQcTrim=01_fastp
|
DirQcTrim=01_fastp
|
||||||
DirAssembly=02_spades
|
DirAssembly=02_spades
|
||||||
|
DirFasta=03_contig
|
||||||
|
DirMap=04_map
|
||||||
|
DirPre=05_pre
|
||||||
|
DirSplit=06_split
|
||||||
|
DirMerge=07_merge
|
||||||
|
DirAlign=08_align
|
||||||
|
|
||||||
|
PathSplitfsata=~/Downloads/PhD/wes/splitfasta-cpp
|
||||||
|
PathMacse=/usr/share/java/macse.jar
|
||||||
|
PathSortdiamond=/home/guoyi/Downloads/PhD/wes/sortdiamond
|
||||||
|
|
||||||
|
HELP=false
|
||||||
|
|
||||||
### Get some arrays
|
### Get some arrays
|
||||||
|
|
||||||
cd $DirRaw
|
ARGS=$(getopt -o c:,f:,h,l:,m:,r:,t: --long contig:,functions:,help,list:,memory:,reference:,threads: -n 'batch.sh' -- "$@")
|
||||||
|
if [ $? != 0 ]; then
|
||||||
|
echo "Failed to parse options." >&2
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
eval set -- "$ARGS"
|
||||||
|
|
||||||
readarray -t full_names < <(ls | awk -F '_' '{print $1 "_" $2 "_" $3 "_" $4}' | uniq)
|
while true; do
|
||||||
readarray -t species_names < <(ls | awk -F '_' '{print $2 "_" $3}' | uniq)
|
case "$1" in
|
||||||
readarray -t output_names < <(ls | awk -F '_' '{print $2 "_" $3 "_" $4}' | uniq)
|
-c|--contig)
|
||||||
|
case "$2" in
|
||||||
|
"") ARG_C='scaffolds'; shift 2 ;;
|
||||||
|
*) ARG_C=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
-f|--functions)
|
||||||
|
case "$2" in
|
||||||
|
"") ARG_F='all'; shift 2 ;;
|
||||||
|
*) ARG_F=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
-h|--help)
|
||||||
|
echo -e "\t\t\t\t\tExon Phylogeny Pipeline\n \
|
||||||
|
Version: $pkgver\n \
|
||||||
|
License: GPL-3.0-only\n \
|
||||||
|
Author: Guoyi Zhang\n \
|
||||||
|
-c\t--contig\tcontings type: scaffolds or contigs\n \
|
||||||
|
-f\t--functions\tfunctions type (optional): all clean assembly fasta map pre\n \
|
||||||
|
-h\t--help\thelp: show this information\n \
|
||||||
|
-l\t--list\tlist file path\n \
|
||||||
|
-m\t--memory\tmemory settings (optional, default 16 GB)\n \
|
||||||
|
-r\t--reference\treference genome path\n \
|
||||||
|
-t\t--threads\tthreads setting (optional, default 8 threads)\n \
|
||||||
|
for example: bash $0 -c scaffolds -f all -l list -r Reference.exons.aa.fas \n"
|
||||||
|
HELP=true
|
||||||
|
shift ;;
|
||||||
|
-l|--list)
|
||||||
|
case "$2" in
|
||||||
|
"") shift 2 ;;
|
||||||
|
*) ARG_L=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
-m|--memory)
|
||||||
|
case "$2" in
|
||||||
|
"") ARG_M=16; shift 2 ;;
|
||||||
|
*) ARG_M=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
-r|--reference)
|
||||||
|
case "$2" in
|
||||||
|
"") shift 2 ;;
|
||||||
|
*) ARG_R=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
-t|--threads)
|
||||||
|
case "$2" in
|
||||||
|
"") ARG_T=8; shift 2 ;;
|
||||||
|
*) ARG_T=$2; shift 2 ;;
|
||||||
|
esac ;;
|
||||||
|
--) shift; break ;;
|
||||||
|
*) echo "Internal error!"; exit 1 ;;
|
||||||
|
esac
|
||||||
|
done
|
||||||
|
|
||||||
cd ..
|
### Get and check some arguments
|
||||||
|
|
||||||
length_fn=${#full_names[@]}
|
if [ "$HELP" = false ]; then
|
||||||
length_sn=${#species_names[@]}
|
if [ -z "$ARG_L" ]; then
|
||||||
length_on=${#output_names[@]}
|
echo "List argument can't be empty"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
### Check the arrays
|
readarray -t full_names < "$ARG_L"
|
||||||
|
length_fn=${#full_names[@]}
|
||||||
if [ $length_fn -ne $length_sn ] || [ $length_fn -ne $length_on ] || [ $length_sn -ne $length_on ]
|
|
||||||
then
|
|
||||||
echo "Please check the amount number of arrays"
|
|
||||||
exit 0
|
|
||||||
fi
|
fi
|
||||||
|
|
||||||
### Quality control && Trimming
|
### Quality control && Trimming
|
||||||
|
|
||||||
mkdir -p $DirQcTrim
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "clean" ]; then
|
||||||
|
|
||||||
for (( i=0; i<$length_fn; i++ )); do
|
## Prepare
|
||||||
fastp -i $DirRaw/${full_names[$i]}_R1.fastq.gz -I $DirRaw/${full_names[$i]}_R2.fastq.gz -j ${species_names[$i]}.json -h ${species_names[$i]}.html -o $DirQcTrim/${output_names[$i]}_R1.fastq.gz -O $DirQcTrim/${output_names[$i]}_R2.fastq.gz -w 4
|
mkdir -p $DirQcTrim
|
||||||
done
|
|
||||||
|
## Quality control and trimming using fastp
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
fastp -i $DirRaw/${full_names[$i]}_R1.fastq.gz -I $DirRaw/${full_names[$i]}_R2.fastq.gz -j $DirQcTrim/${full_names[$i]}.json -h $DirQcTrim/${full_names[$i]}.html -o $DirQcTrim/${full_names[$i]}_R1.fastq.gz -O $DirQcTrim/${full_names[$i]}_R2.fastq.gz -w $ARG_T
|
||||||
|
done
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
### De novo assembly
|
### De novo assembly
|
||||||
|
|
||||||
mkdir -p $DirAssembly
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "assembly" ]; then
|
||||||
|
|
||||||
|
## Prepare
|
||||||
|
mkdir -p $DirAssembly
|
||||||
|
|
||||||
|
## De novo assembly using spades
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
mkdir -p $DirAssembly/${full_names[$i]}
|
||||||
|
spades.py --pe1-1 $DirQcTrim/${full_names[$i]}_R1.fastq.gz --pe1-2 $DirQcTrim/${full_names[$i]}_R2.fastq.gz -t $ARG_T -m $ARG_M --careful --phred-offset 33 -o $DirAssembly/${full_names[$i]}
|
||||||
|
# -k 96,107,117,127 \
|
||||||
|
done
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
|
### Moving scaffords or Contigs out
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "fasta" ]; then
|
||||||
|
|
||||||
|
## Check if the contigs type is specified
|
||||||
|
if [ -z "$ARG_C" ] ; then
|
||||||
|
echo "Argument of contig type missing."
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
## Prepare
|
||||||
|
mkdir -p $DirFasta
|
||||||
|
|
||||||
|
## Move the assemblied fasta file to the folder
|
||||||
|
if [ "$ARG_C" = "scaffolds" ] || [ "$ARG_C" = "contigs" ] ; then
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
cp $DirAssembly/${full_names[$i]}/$ARG_C.fasta $DirFasta/$ARG_C/${full_names[$i]}.fasta
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
|
### Mapping
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "map" ]; then
|
||||||
|
|
||||||
|
## Check if the reference or contigs type is specified
|
||||||
|
if [ -z "$ARG_R" ] || [ -z "$ARG_C" ] ; then
|
||||||
|
echo "Argument of reference or contig type missing."
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
## Prepare
|
||||||
|
mkdir -p $DirMap
|
||||||
|
|
||||||
|
## Index reference database
|
||||||
|
cd $DirFasta/$ARG_C
|
||||||
|
diamond makedb --db Reference --in $ARG_R
|
||||||
|
cd -
|
||||||
|
|
||||||
|
## Blastx for mapping DNA sequences to protein reference sequence
|
||||||
|
cd $DirFasta/$ARG_C
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
diamond blastx -d Reference.dmnd -q ${full_names[$i]}.fasta -o ${full_names[$i]}.m8 \
|
||||||
|
--outfmt 6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen gaps ppos qframe qseq
|
||||||
|
# subject: reference; query: align-aimed
|
||||||
|
#1: qseqid: Query Seq-id
|
||||||
|
#2: sseqid: Subject Seq - id
|
||||||
|
#3: pident: Percentage of identical matches
|
||||||
|
#4: length: Alignment length
|
||||||
|
#5: mismatch: Number of mismatches
|
||||||
|
#6: gapopen: Number of gap openings
|
||||||
|
#7: qstart: Start of alignment in query
|
||||||
|
#8: qend: End of alignment in query
|
||||||
|
#9: sstart: Start of alignment in subject
|
||||||
|
#10: send: End of alignment in subject
|
||||||
|
#11: evalue: Expect value
|
||||||
|
#12: bitscore: Bit score
|
||||||
|
#13: qlen: Query sequence length 比对序列长度
|
||||||
|
#14: slen: Subject sequence length
|
||||||
|
#15: gaps: Total number of gaps
|
||||||
|
#16: ppos: Percentage of positive - scoring matches
|
||||||
|
#17: qframe: Query frame (frames in ECPP.sh)
|
||||||
|
#18: qseq: Aligned part of query sequence
|
||||||
|
|
||||||
|
done
|
||||||
|
cd -
|
||||||
|
|
||||||
|
mv $DirFasta/$ARG_C/*.m8 $DirMap
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "pre" ]; then
|
||||||
|
mkdir -p $DirPre
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
$PathSortdiamond $DirMap/${full_names[$i]}.m8 $DirPre/${full_names[$i]}.fasta
|
||||||
|
done
|
||||||
|
fi
|
||||||
|
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "split" ]; then
|
||||||
|
mkdir -p $DirSplit
|
||||||
|
cd $DirPre
|
||||||
|
for (( i=0; i<$length_fn; i++ )); do
|
||||||
|
$PathSplitfsata ${full_names[$i]}.fasta
|
||||||
|
done
|
||||||
|
find . -mindepth 1 -maxdepth 1 -type d -exec mv {} ../$DirSplit \;
|
||||||
|
cd -
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "merge" ]; then
|
||||||
|
|
||||||
|
mkdir -p $DirMerge
|
||||||
|
cd $DirSplit
|
||||||
|
for genes in $(ls)
|
||||||
|
do
|
||||||
|
cd $genes
|
||||||
|
cat * > ../$genes.fasta
|
||||||
|
cd ..
|
||||||
|
done
|
||||||
|
mv *.fasta ../$DirMerge
|
||||||
|
cd -
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
|
if [ "$ARG_F" = "all" ] || [ "$ARG_F" = "align" ]; then
|
||||||
|
|
||||||
|
mkdir -p $DirAlign
|
||||||
|
mkdir -p $DirAlign/AA && mkdir -p $DirAlign/NT
|
||||||
|
cd $DirMerge
|
||||||
|
for genes in $(ls | sed "s@.fasta@@g")
|
||||||
|
do
|
||||||
|
java -jar $PathMacse -prog alignSequences -seq ${genes}.fasta -out_AA ../$DirAlign/AA/$genes.fasta -out_NT ../$DirAlign/NT/$genes.fasta
|
||||||
|
done
|
||||||
|
cd -
|
||||||
|
|
||||||
|
fi
|
||||||
|
|
||||||
for (( i=0; i<$length_fn; i++ )); do
|
|
||||||
mkdir -p $DirAssembly/${species_names[$i]}
|
|
||||||
spades.py --pe1-1 $DirQcTrim/${output_names[$i]}_R1.fastq.gz --pe1-2 $DirQcTrim/${output_names[$i]}_R2.fastq.gz -t 8 -k 97,107,117,127 -m 14 --careful --phred-offset 33 -o $DirAssembly/${species_names[$i]}
|
|
||||||
done
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue