Last active
December 19, 2015 00:48
-
-
Save dgrapov/5871064 to your computer and use it in GitHub Desktop.
Check for key word in PubMed article titles
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
#Check pubmed article titles for a given year for a keyword (using partial matching). | |
library(XML) | |
library(stringr) | |
#get PubMed Ids for all journals for a given year | |
getPubMedIds<-function(year=2013, max=100){ | |
#max = maximum results to return | |
url<-paste0("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=",year,"[PDAT]&RetMax=",max) | |
tmp<-readLines(url) | |
doc<-xmlParse(tmp) | |
unlist(xmlToList(doc)$IdList) | |
} | |
# get article Titles | |
getArticleTitle<-function(id){ | |
unlist(sapply(1:length(id), function(i,pb = txtProgressBar(min = 0, max = length(id), style = 3)){ | |
url<-paste0("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=",id[i],"&retmode=XML&rettype=abstract") | |
setTxtProgressBar(pb, i) | |
tmp<-readLines(url) | |
xml.data <- xmlParse(tmp) | |
xmlToList(xml.data)$PubmedArticle$MedlineCitation$Article$ArticleTitle | |
})) | |
} | |
# Check title for query term and return term | |
checkGetTerm<-function(obj,term){ | |
#obj is the object to check as a character vector | |
#term is the query to do fuzzy matching on | |
unlist(sapply(1:length(obj), function(i){ | |
tmp<-unlist(strsplit(obj[i]," ")) | |
id<-c(1:length(tmp))[!is.na(str_extract(tmp, term))] | |
tmp[id] | |
})) | |
} | |
#EXAMPLE | |
#-------------------- | |
#Get Article IDs | |
id<-getPubMedIds(year=2013, max=100) | |
#get article titles | |
obj<-getArticleTitle(id) | |
#check for term | |
checkGetTerm(obj,term="omics") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment