Cacher is the code snippet organizer for pro developers

for R1 in *_R1_001.fastq.gz; do 

sample=`basename $R1 _R1_001.fastq.gz`; 
R2=${sample}_R2_001.fastq.gz; 
subj=$(echo ${sample:0:5} | sed 's/_//g'); 
dir=$(pwd); 
echo $subj ${dir}/$R1 ${dir}/$R2 >> ../fastq_list.txt; 
done

#Print substring of a column
cat FILE | awk ' { print $1, $2 = substr($2, 1, 15), $3, $4, $5, $6 }'

paste -d' ' <(awk -F':' '{ print $1 }' SCZ.CLOZUK_rsFiltered.txt) <(awk '{ print $2,$3,$4,$5,$6,$7,$8,$9 }' SCZ.CLOZUK_rsFiltered.txt) > out.txt

# subselects file by columns which match pattern
for i in {1..22}; do
	echo $i
	FILE=PsychEncode_CNS.${i}.annot
	pattern="gene"
	awk -vp="$pattern" 'NR==1{for(i=1; i<=NF; i++) if ($i~p) {a[i]++;} }  { for (i in a) printf "%s\t", $i; printf "\n"}' $FILE  > geneMods/geneMods_PEC.${i}.annot
done



for i in {1..22}; do
	echo $i
	paste -d' ' <(awk ' { print $1, $2, $3, $4 }' CNS.${i}.annot) geneMods/geneMods_PEC.${i}.annot > geneMods/geneMods_PEC.${i}.annot.final
done

nproc --all

#courtesy: Sep

add_col="$SAMPLE $TPM"
## use process substitution to paste new column into file
paste datSalmon.csv <(echo $add_col | tr " " "\n") > temp.csv  ## 1 value per line

#Add 'chr' to VCF file if necessary

awk '{if($0 !~ /^#/) print "chr"$0; else print $0}' all-panctx-merged.vcf > all-panctx-merged_chr.vcf