Skip to content

Instantly share code, notes, and snippets.

@fbreitwieser

fbreitwieser/get_all_viral_sequences.sh

Last active October 24, 2017 17:46
Show Gist options
  • Save fbreitwieser/4eab4c063bfa173a80ad0d19ae0555cd to your computer and use it in GitHub Desktop.
Save fbreitwieser/4eab4c063bfa173a80ad0d19ae0555cd to your computer and use it in GitHub Desktop.
Download ZIP
Raw
get_all_viral_sequences.sh
#!/bin/bash
# Possible formats: fasta, xml, gb
function dl_nuc {
FMT=$1
TERM=$2
ESEARCH_URL="https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
URL_PARAMS=`curl -g "$ESEARCH_URL?db=nuccore&usehistory=y&retmax=1&retmode=json&term=$TERM" | grep -e 'querykey' -e 'webenv' | sed -e 's/^ *"querykey": "/query_key=/' -e 's/^ *"webenv": "/WebEnv=/' -e 's/",//' | paste -sd\&`
curl "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=nuccore&query_key=1&$URL_PARAMS&rettype=fasta"
}
refseq_viruses="Viruses[Organism]+AND+srcdb_refseq[PROP]+NOT+wgs[PROP]+NOT+cellular+organisms[ORGN]+NOT+AC_000001%3AAC_999999[PACC]"
refseq_neighbors="Viruses[Organism]+NOT+cellular+organisms[ORGN]+NOT+wgs[PROP]+NOT+AC_000001:AC_999999[pacc]+NOT+gbdiv+syn[prop]+AND+nuccore+genome+samespecies[Filter]"
refseq_viruses_plus_neighbors="Viruses[Organism]+NOT+cellular+organisms[ORGN]+NOT+wgs[PROP]+NOT+AC_000001:AC_999999[pacc]+NOT+gbdiv+syn[prop]+AND+(srcdb_refseq[PROP]+OR+nuccore+genome+samespecies[Filter])"
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment