Athero.Rmd

---
title: "Athero"
author: "gntem2"
date: "15/01/2020"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

```{r data}

library(pubmed.mineR)
library(lsa)
library(SnowballC)
library(wordcloud)
library(DT)


#create list of words
tdm_wordsA=c("inflammation","residual",             "atherosclerosis", "plaque", "vulnerable",  "carotid artery", "coronary artery", "rupture", "antiplatelet", "gliptin", "ezetimibe", "colchicine","evolocumab","bococizumab","canakinumab", "methotrexate","salsalate", "gout", "statin", "cholesterol", "IMT", "shear stress","fractional flow reserve", "calcification", "hypertension", "diabetes", "obesity" , "stroke","acute coronary syndrome","myocardial infarction","infection","penumonia","microbiota","gut brain") 

#save pubmed search as summary
#atherosclerosis inflammation 
#16/1/20
abstracts=readabs("pubmed_result.txt") 

pmids=abstracts@PMID
gene=gene_atomization(abstracts) #HGNC approved symbol


#summary(gene)

words=word_atomizations(abstracts)
#plot wordcloud


abstract.bodies=abstracts@Abstract
#SentenceToken(abstract.bodies[1])

Myelin=searchabsL(abstracts)
Con=Find_conclusion(abstracts) #conclusion of abstracts


#create list of gene
#take gene data from first column
tdm_wordsG=gene[,1] 

#merge the 2 word lists
tdm_wordsAG=c(tdm_wordsA,tdm_wordsG)

#create term document matrix
tdmAG=tdm_for_lsa(Myelin,tdm_wordsAG)

#plot wordcloud
m <- as.matrix(tdmAG)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 10)


set.seed(1234)
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
          max.words=200, random.order=FALSE, rot.per=0.35, 
          colors=brewer.pal(8, "Dark2"))

barplot(d[1:20,]$freq, las = 2, names.arg = d[1:20,]$word,
        col ="lightblue", main ="Most frequent words",
        ylab = "Word frequencies")


## latent semantic analysis
lsaspace=lsa(tdmAG,dims=dimcalc_share());
newmatrix=as.textmatrix(lsaspace)
associated_words=lapply(tdm_wordsAG,function(x){associate(newmatrix,x,measure="cosine",threshold="0.5")})
names(associated_words)=tdm_wordsAG
associated_words[1:10]
cos_sim_calc(tdmAG) #output file cosimdata.txt #cytoscape
cos=read.table("cossimdata.txt",header=FALSE,sep="\t")
#write.csv(cos, "cossimdata.csv")
```

```{r plot}

library(dplyr)
cos2=na.omit(cos)

library(igraph)
library(ggraph)
library(graphlayouts)

#relavel column
relations <- data.frame(from=cos2[,1], to=cos2[,2],   weight=abs(cos2[,3]))

#remove 0
relations2=relations[-row(relations)[relations == 0],] 

#undirected graph
g.1a <- graph.data.frame(relations2, directed=FALSE)
#V(g.1a)$size<-1
min<-.99 #threshold



#Give the graph lots of room
#opar <- par()$mar; par(mar=rep(3, 4)) 
#plot(g.1a, layout=layout1)

#plot(g.1a, layout=layout1, edge.width=ifelse(E(g.1a)$weight>=min, E(g.1a)$weight, NA)) 

#waltrap community
wc=cluster_walktrap(g.1a) 
modularity(wc)

#ebc<-edge.betweenness.community(g.1a)

#ci<-cluster_infomap(g.1a)


#
#layout1 <- layout.auto(g.1a)
layout1<-layout.lgl(g.1a)
#plot(wc,g.1a, layout=layout1, vertex.size=.5,vertex.label=NA) #remove vertex label

layout2<-layout.fruchterman.reingold(g.1a)
plot(wc,g.1a, layout=layout2) #remove vertex label

V(g.1a)$color<-wc$membership

write.graph(g.1a,"athero.graphml",format = "graphml")


#heatmap
netm <- get.adjacency(g.1a, attr="weight", sparse=F) 
palf <- colorRampPalette(c("gold", "dark orange")) 
#heatmap(netm[,17:1], Rowv = NA, Colv = NA, col = palf(100), scale="none", margins=c(10,10) )

#gephi


``` 

Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.