BOL

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

Genome in a Bottle http://jimb.stanford.edu/giab/ #GIAB #Genome

perl -pe 's/[^AGTC\n]/N/gi unless m/>/;' /media/urbe/TOSHIBALAB/falconUnzip/SSPACED_P2/scaffolds.fasta > /media/urbe/TOSHIBALAB/falconUnzip/SSPACED_P2/scaffolds_corrected.fasta #Remove #Non-ATCG

#Zero coverage regions ~/Tools/bedtools2/bin/bedtools genomecov -ibam PvsH_aln_sorted.bam -bga | awk '$4==0' > ZERO_coverage_regions.txt

Sed illegal charters from fasta. $ sed '/^[^>]/ s/[^AGTC]/N/gi' < seq.fa #fasta #otherthanATGC #replace #sed #Linux #illegal

export PERL5LIB=/home/foobar/code #SetPath #Perl

Count the contigs length in index fasta file with samtools. $ awk '{s+=$2}END{print s}' scaffolds.fasta.fai #Fasta #Index #Length #Count #Size #Samtools

Genome in a Bottle (GIAB) http://jimb.stanford.edu/giab/ #Genome #Consortium #GIAB

#Scientific #converter https://www.rapidtables.com/convert/number/scientific-notation-converter.html

Genome Assembly: #Scaffolding Guided by Related Genomes https://www.duo.uio.no/bitstream/handle/10852/37431/Furenes_Master.pdf?sequence=1

To upgrade the perl in Linux $ sudo cpan; cpan[1]> upgrade #Perl #Upgrade #Linux #Ubuntu

Phased the genome http://pb-falcon.readthedocs.io/en/latest/_downloads/Kingan_DiploidGenome_ECUGM2017_BFX.pdf #Falcon #Unzip #PPT

#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

Finding coding regions in DNA sequences http://genome.crg.es/courses/Lisbon04/exercises/day2/Perl_programming/index.html #Perl #Genes #Script