Last active
August 29, 2015 14:20
-
-
Save kdiverson/1cbc5ecfba170f5b4666 to your computer and use it in GitHub Desktop.
run LMAT
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hit_total=`awk '{total += $3} END {print total}' *fastsummary.species` | |
nohit_total=`awk '{total += $2} END {print total}' *nomatchsum` | |
total=(($hit_total + $nohit_total)) | |
human=`awk '{if ($4==9606) {print $3} }' *fastsummary.species` | |
echo (($human / $total)) | |
hit_total=`awk '{total += $3} END {print total}' *fastsummary.species`; nohit_total=`awk '{total += $2} END {print total}' *nomatchsum`; total=(($hit_total + $nohit_total)); human=`awk '{if ($4==9606) {print $3} }' *fastsummary.species`; echo (($human / $total)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
export LMAT_DIR=/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/runtime_inputs | |
LMAT_BIN=/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin | |
SEQTK=/mnt/EXT/Schloss-data/kiverson/seqtk/seqtk | |
LMAT_DB=/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/kML+Human.v4-14.20.g10.db | |
OUT_DIR=tmp | |
SINGLE_BASE=A7221349_6_TAAGGCGA-TAGATCGC_L003 | |
R1=A7221349_6_TAAGGCGA-TAGATCGC_L003_R1_001.fastq | |
R2=A7221349_6_TAAGGCGA-TAGATCGC_L003_R2_001.fastq | |
BASE=A7221349_6_TAAGGCGA-TAGATCGC_L003_001 | |
##### | |
run_lmat() { | |
$LMAT_BIN/merge_fastq_reads_with_N_separator.pl <(zcat $R1) <(zcat $R2) | $SEQTK seq -A -q 10 -n N - $BASE.q10mask.fasta | |
$LMAT_BIN/run_rl.sh --db_file=$LMAT_DB --query_file=$BASE.q10mask.fasta --odir=$OUT_DIR --threads=8 | |
rm $BASE.q10mask.fasta | |
rm *.out | |
} | |
#$LMAT_BIN/merge_fastq_reads_with_N_separator.pl $R1 $R2 $BASE.fastq | |
#$SEQTK seq -A -q 10 -n N $BASE.fastq > $BASE.q10mask.fasta | |
#above comands combined here | |
workingdir=`pwd` | |
sampledir=${workingdir##/*} | |
sample=${sampledir#*_} | |
count=`ls *R1*.gz | wc -l` | |
for ((k=1; k<=$count; k++)) | |
do | |
R1=*R1_00${k}.fastq.gz | |
R2=*R2_00${k}.fastq.gz | |
BASE=${sample}_00${k} | |
$OUT_DIR=$BASE_out | |
quicksubmit """ | |
$LMAT_BIN/merge_fastq_reads_with_N_separator.pl <(zcat $R1) <(zcat $R2) | $SEQTK seq -A -q 10 -n N - $BASE.q10mask.fasta &&\ | |
$LMAT_BIN/run_rl.sh --db_file=$LMAT_DB --query_file=$BASE.q10mask.fasta --odir=$OUT_DIR --threads=8 &&\ | |
rm $BASE.q10mask.fasta &&\ | |
rm *.out""" | |
done | |
for i in {1..8} | |
do | |
R1=A7221366_6_CGTACTAG-TATCCTCT_L002_R1_00$i.fastq.gz | |
R2=A7221366_6_CGTACTAG-TATCCTCT_L002_R2_00$i.fastq.gz | |
BASE=A7221366_6_CGTACTAG-TATCCTCT_L002_00$i | |
quicksubmit """ | |
$LMAT_BIN/merge_fastq_reads_with_N_separator.pl <(zcat $R1) <(zcat $R2) | $SEQTK seq -A -q 10 -n N - $BASE.q10mask.fasta &&\ | |
$LMAT_BIN/run_rl.sh --db_file=$LMAT_DB --query_file=$BASE.q10mask.fasta --odir=$OUT_DIR --threads=8 &&\ | |
rm $BASE.q10mask.fasta &&\ | |
rm *.out""" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
run KML | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/merge_fastq_reads_with_N_separator.pl A7221349_6_TAAGGCGA-TAGATCGC_L003_R1_001.fastq A7221349_6_TAAGGCGA-TAGATCGC_L003_R2_001.fastq A7221349_6_TAAGGCGA-TAGATCGC_L003_001.fastq | |
/mnt/EXT/Schloss-data/kiverson/seqtk/seqtk seq -A -q 10 -n N A7221349_6_TAAGGCGA-TAGATCGC_L003_001.fastq > A7221349_6_TAAGGCGA-TAGATCGC_L003_001.q10mask.fasta | |
export LMAT_DIR=/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/runtime_inputs | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/run_rl.sh --db_file=/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/kML+Human.v4-14.20.g10.db --query_file=A7221349_6_TAAGGCGA-TAGATCGC_L003_001.q10mask.fasta --odir=tmp --threads=8 | |
file structure: | |
EPAN12-0099_Batch_[1-6]/Sample_${var}/${var}_${seq}_L00[num]_R[1-2]_00[num].fastq.gz | |
===== | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/merge_fastq_reads_with_N_separator.pl <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R1_002.fastq.gz) <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R2_002.fastq.gz) A7221349_6_TAAGGCGA-TAGATCGC_L003_002.fastq | |
cat A7221349_6_TAAGGCGA-TAGATCGC_L003_002.fastq | /mnt/EXT/Schloss-data/kiverson/seqtk/seqtk seq -A -q 10 -n N - > A7221349_6_TAAGGCGA-TAGATCGC_L003_002.q10mask.fasta | |
===== | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/merge_fastq_reads_with_N_separator.pl <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R1_003.fastq.gz) <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R2_003.fastq.gz) | |
A7221349_6_TAAGGCGA-TAGATCGC_L003_003.fastq | |
==== | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/merge_fastq_reads_with_N_separator.pl <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R1_002.fastq.gz) <(zcat A7221349_6_TAAGGCGA-TAGATCGC_L003_R2_002.fastq.gz) | /mnt/EXT/Schloss-data/kiverson/seqtk/seqtk seq -A -q 10 -n N - > A7221349_6_TAAGGCGA-TAGATCGC_L003_002.q10mask.fasta | |
#=== | |
/mnt/EXT/Schloss-data/kiverson/LMAT-1.2.6/bin/merge_fastq_reads_with_N_separator.pl <(zcat A7221366_6_CGTACTAG-TATCCTCT_L002_R1_001.fastq.gz) <(zcat A7221366_6_CGTACTAG-TATCCTCT_L002_R2_001.fastq.gz) | /mnt/EXT/Schloss-data/kiverson/seqtk/seqtk seq -A -q 10 -n N - > A7221366_6_CGTACTAG-TATCCTCT_L002_001.q10mask.fasta |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment