BOL

#Convert #FASTQ to FASTA and set bases of #quality lower than 20 to N $ seqtk seq -aQ64 -q20 -n N IN.fastq > OUT.fasta

Multiline to singleline covert. $ awk '/^>/ {printf("%s%s\t",(N>0?"\n":""),$0);N++;next;} {printf("%s",$0);} END {printf("\n");}' < input.fa #Multi #Single #Convert #awk

for i in $(ls *.ab1); do convert_trace -out_format scf < $i > ${i%.ab1*}.scf; done #Convert #AB12SCF #SCF #AB1

(smrttools) ➜ allBam for i in *.bam; do bamtools convert -format fasta -in $i -out $i.fasta; done #Convert #fasta

Tab file to FASTA file $ awk '{print ">"$1"\n"$2}' allSeq_tm.txt > allSeq_tm.fa #Fasta #Tab #Convert #Tab2Fasta

BAM2BED conversion bamToBed -i overall_exp_genome_rep1.bam > alignment.bed #Bed #bam #bamToBed #convert

Multifasta to singleline fasta. $ awk '/^>/ {printf("\n%s\n",$0);next; } { printf("%s",$0);} END {printf("\n");}' < file.fa #Multi #Single #Fasta #Convert

perl -e '$/="\n>"; while (<>) { s/>//g; my ($id, $seq) = split /\n/; print ">$_" if length $seq; }' < all_p_ctg.fasta > all_p_ctg_corrected.fasta #Convert #Fasta #Zero

#Convert a #multi-line #fasta to a #singleline #fasta $ awk '!/^>/ { printf "%s", $0; n = "\n" } /^>/ { print n $0; n = "" } END { printf "%s", n }' sample1.fa > sample1_singleline.fa

sed -i -e '/^+/,/^\@/{/^+/!{/^\@/!d}}; /^+/ d; s/@/>/g' OUTPUT.fastq > out.fa #Convert

Convert 2bit to psl $ blat myAssembly.2bit -oneOff=0 -noHead myQueryContigSeqs.fa myHits.psl #Convert #psl #2bit #blat

Convert fasta to 2bit $ faToTwoBit myAssembly.fa myAssembly.2bit #Fasta #2bit #Convert

Convert lowercase letter to N:$ sed -e '/^>/! s/[[:lower:]]/N/g' in.fasta > out.fasta #Convert #Lowercase #Fasta #N

#Convert #fasta file to uppercase/lowercase, without altering the annotation line $ awk '{ if ($0 !~ />/) {print toupper($0)} else {print $0} }' name.fasta

Fastq 2 fasta. $ sed -n '1~4s/^@/>/p;2~4p' test.fastq > test.fasta #fastq #fasta #convert