Last active
August 29, 2015 14:14
-
-
Save crazyhottommy/18c3796c87b04ba1422f to your computer and use it in GitHub Desktop.
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
# search pubmed contains "glioblastoma enhancer" | |
$esearch -db pubmed -query "glioblastoma enhancer" | |
<ENTREZ_DIRECT> | |
<Db>pubmed</Db> | |
<WebEnv>NCID_1_539964707_130.14.18.34_9001_1422280320_2091337226_0MetA0_S_MegaStore_F_1</WebEnv> | |
<QueryKey>1</QueryKey> | |
<Count>97</Count> | |
<Step>1</Step> | |
</ENTREZ_DIRECT> | |
# search pubmed with title contains "glioblastoma enhancer" returned 0 count | |
$esearch -db pubmed -query "glioblastoma enhancer [TITL]" | |
<ENTREZ_DIRECT> | |
<Db>pubmed</Db> | |
<WebEnv>NCID_1_23683635_130.14.22.215_9001_1422280849_1465220088_0MetA0_S_MegaStore_F_1</WebEnv> | |
<QueryKey>1</QueryKey> | |
<Count>0</Count> | |
<Step>1</Step> | |
</ENTREZ_DIRECT> | |
#fetch the abstract | |
$esearch -db pubmed -query "glioblastoma enhancer" | efetch -format abstract > glioblastoma.txt | |
#check the abstracts | |
$ less -S glioblastoma.txt | |
# how many papers? | |
$cat glioblastoma.txt | grep PMID | wc -l | |
97 | |
# fetch the protein sequences of human CTCF | |
$esearch -db protein -query "Homo sapiens [ORGN] AND CTCF[GENE]" | efetch -format fasta > CTCF_protein.fa | |
# fetch the nucleotide sequences of human CTCF | |
$esearch -db nucleotide -query "Homo sapiens [ORGN] AND CTCF[GENE]" | efetch -format fasta > CTCF_nucleotide.fa | |
# in genebank format | |
$esearch -db nucleotide -query "Homo sapiens [ORGN] AND CTCF[GENE]" | efetch -format gb > CTCF_nucleotide.gb | |
# From a biostar post https://www.biostars.org/p/92671/ | |
#Given a Gene ID, download the aminoacid sequences of the corresponding Proteins, keeping only the reviewed entries (e.g. no putative, predicted sequences): | |
$esearch -db gene -query "1234[id]" | elink -target protein | efilter -query "REVIEWED[FILTER]"| efetch -format fasta | |
#Given a file containing a list of Gene IDs (one per line), download all the entries in tabular format: | |
$esearch -db gene -query $(paste -s -d ',' mygenes.ids) | efetch -format tabular > mygenes.details.txt | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment