Mercurial > repos > davidvanzessen > mutation_analysis

comparison sequence_overview.r @ 88:d57c624a9aa9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 30 May 2016 10:11:20 -0400
parents fd63f5307962
children 480fdd383fdb
comparison
equal deleted inserted replaced
87:fd63f5307962 88:d57c624a9aa9
21 21
22 dat = merge(sequences, genes, by="Sequence.ID") 22 dat = merge(sequences, genes, by="Sequence.ID")
23 23
24 dat = dat[dat$Sequence.ID %in% merged$Sequence.ID,] 24 dat = dat[dat$Sequence.ID %in% merged$Sequence.ID,]
25 25
26 #dat$seq_conc = paste(dat$CDR1.IMGT, dat$CDR2.IMGT, dat$CDR3.IMGT, dat$FR2.IMGT, dat$FR3.IMGT) 26 dat$seq_conc = paste(dat$CDR1.IMGT, dat$FR2.IMGT, dat$CDR2.IMGT, dat$FR3.IMGT, dat$CDR3.IMGT)
27 dat$seq_conc = paste(dat$CDR1.IMGT, dat$CDR2.IMGT, dat$CDR3.IMGT) 27 #dat$seq_conc = paste(dat$CDR1.IMGT, dat$CDR2.IMGT, dat$CDR3.IMGT)
28 28
29 IDs = dat[,c("Sequence.ID", "seq_conc", "best_match", "Functionality")] 29 IDs = dat[,c("Sequence.ID", "seq_conc", "best_match", "Functionality")]
30 IDs$best_match = as.character(IDs$best_match) 30 IDs$best_match = as.character(IDs$best_match)
31 31
32 #dat = data.frame(data.table(dat)[, list(freq=.N), by=c("best_match", "seq_conc")]) 32 #dat = data.frame(data.table(dat)[, list(freq=.N), by=c("best_match", "seq_conc")])
46 tr = function(val) { capture.output(cat("<tr>", td(val), "</tr>", sep="")) } 46 tr = function(val) { capture.output(cat("<tr>", td(val), "</tr>", sep="")) }
47 make.link = function(id, clss, val) { paste("<a href='", clss, "_", id, ".html'>", val, "</a>", sep="") } 47 make.link = function(id, clss, val) { paste("<a href='", clss, "_", id, ".html'>", val, "</a>", sep="") }
48 tbl = function(df) { res = "<table border='1'>"; for(i in 1:nrow(df)){ res = paste(res, tr(df[i,]), sep=""); }; res = paste(res, "</table>"); } 48 tbl = function(df) { res = "<table border='1'>"; for(i in 1:nrow(df)){ res = paste(res, tr(df[i,]), sep=""); }; res = paste(res, "</table>"); }
49 49
50 cat("<table border='1'>", file=main.html, append=F) 50 cat("<table border='1'>", file=main.html, append=F)
51 cat("<caption>CDR1+CDR2+CDR3+FR2+FR3 sequences that show up more than once</caption>", file=main.html, append=T) 51 cat("<caption>CDR1+FR2+CDR2+FR3+CDR3 sequences that show up more than once</caption>", file=main.html, append=T)
52 cat("<tr><th>Sequence</th><th>Functionality</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T) 52 cat("<tr><th>Sequence</th><th>Functionality</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T)
53 53
54 for(i in 1:nrow(dat)){ 54 for(i in 1:nrow(dat)){
55 ca1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca1",] 55 ca1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca1",]
56 ca2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca2",] 56 ca2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca2",]
123 #ACGT overview 123 #ACGT overview
124 124
125 125
126 126
127 NToverview = genes[,c("Sequence.ID", "best_match")] 127 NToverview = genes[,c("Sequence.ID", "best_match")]
128 sequences$seq = paste(sequences$CDR1.IMGT, sequences$CDR2.IMGT, sequences$FR2.IMGT, sequences$FR3.IMGT, sep="_") 128 sequences$seq = paste(sequences$CDR1.IMGT, sequences$FR2.IMGT, sequences$CDR2.IMGT, sequences$FR3.IMGT, sep="_")
129 129
130 NToverview = merge(NToverview, sequences[,c("Sequence.ID", "seq")], by="Sequence.ID") 130 NToverview = merge(NToverview, sequences[,c("Sequence.ID", "seq")], by="Sequence.ID")
131 131
132 NToverview = NToverview[NToverview$Sequence.ID %in% merged$Sequence.ID,] 132 NToverview = NToverview[NToverview$Sequence.ID %in% merged$Sequence.ID,]
133 133