Mercurial > repos > davidvanzessen > report_clonality_igg
comparison RScript.r @ 24:5454af6fece1 draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Fri, 23 Jan 2015 03:06:43 -0500 |
| parents | 5f0597a3fd8b |
| children | ea5c2a2cc1f3 |
comparison
equal
deleted
inserted
replaced
| 23:5f0597a3fd8b | 24:5454af6fece1 |
|---|---|
| 582 mean(P3D.nt.nb, na.rm=T) + | 582 mean(P3D.nt.nb, na.rm=T) + |
| 583 mean(P5J.nt.nb, na.rm=T))), | 583 mean(P5J.nt.nb, na.rm=T))), |
| 584 by=c("Sample")]) | 584 by=c("Sample")]) |
| 585 write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) | 585 write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) |
| 586 } | 586 } |
| 587 | |
| 588 # ---------------------- AA composition in CDR3 ---------------------- | |
| 589 | |
| 590 AACDR3 = PRODF[,c("Sample", "CDR3.Seq")] | |
| 591 | |
| 592 TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample]) | |
| 593 | |
| 594 AAfreq = list() | |
| 595 | |
| 596 for(i in 1:nrow(TotalPerSample)){ | |
| 597 sample = TotalPerSample$Sample[i] | |
| 598 AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), "")))) | |
| 599 AAfreq[[i]]$Sample = sample | |
| 600 } | |
| 601 | |
| 602 AAfreq = ldply(AAfreq, data.frame) | |
| 603 AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T) | |
| 604 AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100) | |
| 605 | |
| 606 | |
| 607 AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI") | |
| 608 AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE) | |
| 609 | |
| 610 AAfreq = AAfreq[!is.na(AAfreq$order.aa),] | |
| 611 | |
| 612 AAfreqplot = ggplot(AAfreq) | |
| 613 AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' ) | |
| 614 AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) | |
| 615 AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) | |
| 616 AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) | |
| 617 AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) | |
| 618 AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage") | |
| 619 | |
| 620 png("AAComposition.png",width = 1280, height = 720) | |
| 621 AAfreqplot | |
| 622 dev.off() | |
| 623 write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T) | |
| 624 | |
| 625 |