Created
January 19, 2012 02:19
-
-
Save leipzig/1637248 to your computer and use it in GitHub Desktop.
When can we expect the last damn microarray?
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
library("plyr") | |
library("XML") | |
library("ggplot2") | |
#Concatenate SQL-style | |
concat<-function(...,sep="",collapse=NULL){ | |
strings<-list(...) | |
#NULL, NA | |
if( | |
all(unlist(llply(strings,length))>0) | |
&& | |
all(!is.na(unlist(strings))) | |
){ | |
do.call("paste", c(strings, list(sep = sep, collapse = collapse))) | |
}else{ | |
NULL | |
} | |
} | |
getCount<-function(term){function(year){ | |
nihUrl<-concat("http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=",term,"+",year,"[pdat]") | |
#cleanurl<-gsub('\\]','%5D',gsub('\\[','%5B',x=url)) | |
#http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=microarray%5btitle%5d+2003%5bpdat%5d | |
xml<-xmlTreeParse(URLencode(nihUrl),isURL=TRUE) | |
#Data Mashups in R, pg17 | |
as.numeric(xmlValue(xml$doc$children$eSearchResult$children$Count$children$text)) | |
}} | |
years<-1995:2011 | |
df<-data.frame(type="obs",year=years, | |
mic=sapply(years,function(x){do.call(getCount('microarray[title]'),list(x))}), | |
ngs=sapply(years,function(x){do.call(getCount('"next generation sequencing"[title] OR "high-throughput sequencing"[title]'),list(x))}) | |
) | |
#97 is a fair start | |
df<-subset(df,year>=1997) | |
mdf<-melt(df,id.vars=c("type","year"),variable_name="citation") | |
c<-ggplot(mdf,aes(x=year)) | |
p<-c+geom_point(aes(y=value,color=citation),size=3) + | |
ylab("papers") + | |
stat_smooth(aes(y=value,color=citation),data=subset(mdf,citation=="mic"),method="loess") + | |
scale_x_continuous(breaks=seq(from=1997,to=2011,by=2)) | |
print(p) | |
#Return 0 for negative elements | |
# noNeg(c(3,2,1,0,-1,-2,2)) | |
# [1] 3 2 1 0 0 0 2 | |
noNeg<-function(v){sapply(v,function(x){max(x,0)})} | |
#Return up to the first negative/zero element inclusive | |
# toZeroNoNeg(c(3,2,1,0,-1,-2,2)) | |
# [1] 3 2 1 0 | |
toZeroNoNeg<-function(v){noNeg(v)[1:firstZero(noNeg(v))]} | |
#return index of first zero | |
firstZero<-function(v){which(noNeg(v)==0)[1]} | |
#let's peer into the future | |
df.lo.mic<-loess(mic ~ year,df,control=loess.control(surface="direct")) | |
#when will it stop? | |
mic_predict<-as.integer(predict(df.lo.mic,data.frame(year=2012:2020),se=FALSE)) | |
zero_year<-2011+firstZero(mic_predict) | |
cat(concat("LOESS projects ",sum(toZeroNoNeg(mic_predict))," more damn microarray papers.")) | |
cat(concat("The last damn microarray paper is projected to be in ",(zero_year-1),".")) | |
#predict ngs growth | |
df.lo.ngs<-loess(ngs ~ year,df,control=loess.control(surface="direct")) | |
ngs_predict<-as.integer(predict(df.lo.ngs,data.frame(year=2012:zero_year),se=FALSE)) | |
pred_df<-data.frame(type="pred",year=c(2012:zero_year),mic=toZeroNoNeg(mic_predict),ngs=ngs_predict) | |
df2<-rbind(df,pred_df) | |
mdf2<-melt(df2,id.vars=c("type","year"),variable_name="citation") | |
c2<-ggplot(mdf2,aes(x=year)) | |
p2<-c2+geom_point(aes(y=value,color=citation,shape=type),size=3) + | |
ylab("papers") + | |
scale_y_continuous(breaks=seq(from=0,to=1600,by=200))+ | |
scale_x_continuous(breaks=seq(from=1997,to=zero_year,by=2)) | |
print(p2) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
thanks for your tips.
I have created this repository that includes the Data Mashups in R code using the wretched Yahoo! BOSS API. This includes the supplemental census and shapefiles that have gone missing:
https://github.com/leipzig/datamashupsinr