Results for "awk"
Bio-Scripts
Transpose the file coordinates and plot dendrogram in R
#Save this as tr.awk { for (i=1; i2659 days ago
Download the genome from NCBI using bash script/command
...efseq/fungi/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...nk/bacteria/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...seq/archaea/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...nvertebrate/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...2574 days ago
Unzip all the genome file and remove all fasta header except first one
#!/bin/bash gzip -d *.gz FILES=$(pwd)/* for f in $FILES do echo "Processing $f file..." if [[ $f =~ \.fna$ ]]; then awk ' /^>/ && FNR > 1 {next} {print $0} ' $f | s...2573 days ago
Download the gff files from NCBI using bash script/command
...efseq/fungi/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...nk/bacteria/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...seq/archaea/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...nvertebrate/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}...2565 days ago
Download genomes in batch from NCBI
curl 'ftp://ftp.ncbi.nlm.nih.gov/genomes/genbank/bacteria/assembly_summary.txt' | awk '{FS="\t"} !/^#/ {print $20}' | sed -r 's|(ftp://ftp.ncbi.nlm.nih.gov/genomes/all/)(GCA/)([0-9]{3}/)([0-9]{3}/)([0-9]{3}/)(GCA_.+)|\1\2\3\4\5\6/\6_genomic.fna.gz|' > genomic_file2305 days ago
- ...- |cut -f 1, 2| sed 's/@/>/'g | tr -s "/t" "/n" > OUTFILE.fasta #awk cat infile.fq | awk '{if(NR%4==1) {printf(">%s\n"...> file.fa #seqtk seqtk seq -a input.fastq > output.fasta #Bioawk bioawk -c fastx '{print ">"$...
892 days ago
- zero=$(bedtools genomecov -ibam BAM -g hg38.fasta -bga | awk '$4==0 {bpCountZero+=($3-$2)} {print bpCountZero}' | tail -1) nonzero=$(bedtools genomecov -ibam BAM -g hg38.fasta -bga | awk '$4>0 {bpCountNonZero+=($3-$2)} {print bpCountNonZero}' | tail -1) percent=$(bc
2252 days ago
- ...N_COVERAGE_DEPTH or higher samtools mpileup mapping_result_sorted.bam | awk -v X="${MIN_COVERAGE_DEPTH}"...2876 # get length of reference genome bowtie2-inspect -s refgenome | awk '{ FS = "\t" } ; BEGIN{L=0};...
2252 days ago
Bash oneliner to extract all ids from a multifasta file
#List of ids - one per line in allIds.txt $ awk 'BEGIN{while((getline0)l[">"$1]=1}/^>/{f=!l[$1]}f' seq.fa # You can play with this f=!l[$1 ] if wanted to extract or not extract the ids1580 days ago
- ...end=$3 samtools depth deduped_MA605.bam > deduped_MA605.coverage awk '$1 == $chr {print $0}' deduped_MA605.coverage > chr1_MA605.coverage #awk '$1 == 2 {print $0}' deduped_...
2046 days ago
