Mercurial > repos > davidvanzessen > mutation_analysis

comparison sequence_overview.r @ 91:5e237c243088 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 03 Jun 2016 10:35:52 -0400
parents f0e8dac22c6e
children b869a126e2c4
comparison
equal deleted inserted replaced
90:f0e8dac22c6e 91:5e237c243088
20 IDs = merged[,c("Sequence.ID", "seq_conc", "best_match", "Functionality")] 20 IDs = merged[,c("Sequence.ID", "seq_conc", "best_match", "Functionality")]
21 IDs$best_match = as.character(IDs$best_match) 21 IDs$best_match = as.character(IDs$best_match)
22 22
23 #dat = data.frame(data.table(dat)[, list(freq=.N), by=c("best_match", "seq_conc")]) 23 #dat = data.frame(data.table(dat)[, list(freq=.N), by=c("best_match", "seq_conc")])
24 24
25 dat = data.frame(table(merged$seq_conc, merged$Functionality)) 25 dat = data.frame(table(merged$seq_conc))
26 #dat = data.frame(table(merged$seq_conc, merged$Functionality))
26 27
27 #dat = dat[dat$Freq > 1,] 28 #dat = dat[dat$Freq > 1,]
28 29
29 names(dat) = c("seq_conc", "Functionality", "Freq") 30 #names(dat) = c("seq_conc", "Functionality", "Freq")
31 names(dat) = c("seq_conc", "Freq")
30 32
31 dat$seq_conc = factor(dat$seq_conc) 33 dat$seq_conc = factor(dat$seq_conc)
32 34
33 dat = dat[order(as.character(dat$seq_conc)),] 35 dat = dat[order(as.character(dat$seq_conc)),]
34 36
41 cat("<table border='1'>", file=main.html, append=F) 43 cat("<table border='1'>", file=main.html, append=F)
42 cat("<caption>CDR1+FR2+CDR2+FR3+CDR3 sequences that show up more than once</caption>", file=main.html, append=T) 44 cat("<caption>CDR1+FR2+CDR2+FR3+CDR3 sequences that show up more than once</caption>", file=main.html, append=T)
43 cat("<tr><th>Sequence</th><th>Functionality</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T) 45 cat("<tr><th>Sequence</th><th>Functionality</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T)
44 46
45 for(i in 1:nrow(dat)){ 47 for(i in 1:nrow(dat)){
46 ca1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca1",] 48 ca1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^ca1", IDs$best_match),]
47 ca2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca2",] 49 ca2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^ca2", IDs$best_match),]
48 50
49 cg1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cg1",] 51 cg1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^cg1", IDs$best_match),]
50 cg2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cg2",] 52 cg2 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^cg2", IDs$best_match),]
51 cg3 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cg3",] 53 cg3 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^cg3", IDs$best_match),]
52 cg4 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cg4",] 54 cg4 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^cg4", IDs$best_match),]
53 55
54 cm = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cm",] 56 cm = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & grepl("^cm", IDs$best_match),]
57 allc = rbind(ca1, ca2, cg1, cg2, cg3, cg4, cm)
55 58
56 classes = c(nrow(ca1), nrow(ca2), nrow(cg1), nrow(cg2), nrow(cg3), nrow(cg4), nrow(cm)) 59 classes = c(nrow(ca1), nrow(ca2), nrow(cg1), nrow(cg2), nrow(cg3), nrow(cg4), nrow(cm))
57 60
58 classes.sum = sum(classes) 61 classes.sum = sum(classes)
59 62
61 next 64 next
62 } 65 }
63 66
64 id = as.numeric(dat[i,"seq_conc"]) 67 id = as.numeric(dat[i,"seq_conc"])
65 68
66 functionality = dat[i,"Functionality"] 69 functionality = paste(unique(allc[,"Functionality"], sep=","))
67 70
68 if(nrow(ca1) > 0){ 71 if(nrow(ca1) > 0){
69 cat(tbl(ca1), file=paste("ca1_", id, ".html", sep="")) 72 cat(tbl(ca1), file=paste("ca1_", id, ".html", sep=""))
70 } 73 }
71 74
102 cg4.html = make.link(id, "cg4", nrow(cg4)) 105 cg4.html = make.link(id, "cg4", nrow(cg4))
103 106
104 cm.html = make.link(id, "cm", nrow(cm)) 107 cm.html = make.link(id, "cm", nrow(cm))
105 108
106 rw = c(as.character(dat[i,"seq_conc"]), as.character(functionality), ca1.html, ca2.html, cg1.html, cg2.html, cg3.html, cg4.html, cm.html) 109 rw = c(as.character(dat[i,"seq_conc"]), as.character(functionality), ca1.html, ca2.html, cg1.html, cg2.html, cg3.html, cg4.html, cm.html)
110 #print(rw)
107 111
108 cat(tr(rw), file=main.html, append=T) 112 cat(tr(rw), file=main.html, append=T)
109 } 113 }
110 114
111 cat("</table>", file=main.html, append=T) 115 cat("</table>", file=main.html, append=T)
130 #NToverview = rbind(NToverview, NTsum) 134 #NToverview = rbind(NToverview, NTsum)
131 135
132 NTresult = data.frame(nt=c("A", "C", "T", "G")) 136 NTresult = data.frame(nt=c("A", "C", "T", "G"))
133 137
134 for(clazz in gene.classes){ 138 for(clazz in gene.classes){
135 NToverview.sub = NToverview[grepl(clazz, paste("^", NToverview$best_match, sep="")),] 139 NToverview.sub = NToverview[grepl(paste("^", clazz, sep=""), NToverview$best_match),]
136 new.col.x = c(sum(NToverview.sub$A), sum(NToverview.sub$C), sum(NToverview.sub$T), sum(NToverview.sub$G)) 140 new.col.x = c(sum(NToverview.sub$A), sum(NToverview.sub$C), sum(NToverview.sub$T), sum(NToverview.sub$G))
137 new.col.y = sum(new.col.x) 141 new.col.y = sum(new.col.x)
138 new.col.z = round(new.col.x / new.col.y * 100, 2) 142 new.col.z = round(new.col.x / new.col.y * 100, 2)
139 143
140 tmp = names(NTresult) 144 tmp = names(NTresult)
156 160
157 print(hotspot.analysis.sum) 161 print(hotspot.analysis.sum)
158 162
159 write.table(hotspot.analysis.sum, hotspot.analysis.sum.file, quote=F, sep=",", row.names=F, col.names=F, na="0") 163 write.table(hotspot.analysis.sum, hotspot.analysis.sum.file, quote=F, sep=",", row.names=F, col.names=F, na="0")
160 164
161 165 write.table(NToverview[,c("Sequence.ID", "best_match", "seq", "A", "C", "G", "T")], NToverview.file, quote=F, sep="\t", row.names=F, col.names=T)
162 write.table(NToverview, NToverview.file, quote=F, sep="\t", row.names=F, col.names=T)
163 166
164 167
165 168
166 169
167 170