Created
June 16, 2012 18:42
-
-
Save fjossinet/2942223 to your computer and use it in GitHub Desktop.
Select CDS by keyword in all E. coli genomes
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 | |
query=$1 | |
genome_ids=$(wget -qO - "http://www.ncbi.nlm.nih.gov/genome/genomes/167?&subset=complete&limit=refseq" | grep 'title="chromosome">Chr' | sed -E 's/.+(NC_.+|NZ_.+)/\1/' | cut -d \< -f 1) | |
for genome_id in $genome_ids | |
do | |
wget -qO - "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=$genome_id&rettype=gb&retmode=xml" > genome.xml | |
gene_ids=$(xmllint --xpath "//GBFeature[GBFeature_key[.='CDS'] and GBFeature_quals/GBQualifier[GBQualifier_name[.='product'] and GBQualifier_value[contains(.,\"$query\")]]]" genome.xml | grep "GI:" | sed -E 's/.+GI:(.+)<.+/\1/') | |
for gene_id in $gene_ids | |
do | |
wget -qO - "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nucleotide&id=$gene_id&rettype=fasta" | grep "^>" | cut -d \> -f 2 | |
done | |
done | |
rm genome.xml |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment