2
+ − 1 <tool id="plot_spades_stats" name="SPAdes stats" version="0.1">
+ − 2 <description>coverage vs. length plot</description>
+ − 3 <requirements>
+ − 4 <requirement type="package">R</requirement>
+ − 5 </requirements>
+ − 6 <command interpreter="bash">r_wrapper.sh $script_file</command>
+ − 7
+ − 8 <inputs>
+ − 9 <param name="input_scaffolds" type="data" format="tabular" label="Scaffold stats"/>
+ − 10 <param name="input_contigs" type="data" format="tabular" label="Contig stats"/>
+ − 11 <param name="length_co" type="integer" value="1000" min="0" label="Length cut-off" help="Contigs with length under that value are shown in red"/>
+ − 12 <param name="coverage_co" type="integer" value="10" min="0" label="Coverage cut-off" help="Contigs with length under that value are shown in red"/>
+ − 13 </inputs>
+ − 14 <configfiles>
+ − 15 <configfile name="script_file">
+ − 16 ## Setup R error handling to go to stderr
+ − 17 options( show.error.messages=F,
+ − 18 error = function () {
+ − 19 cat( geterrmessage(), file=stderr() ); q( "no", 1, F )
+ − 20 } )
+ − 21 files = c("${input_contigs}", "${input_scaffolds}")
+ − 22 types = c("Contigs", "Scaffolds")
+ − 23
+ − 24 ## Start plotting device
+ − 25 png("${out_file}", w=500, h=1000)
+ − 26 par(mfrow=c(2,1))
+ − 27
+ − 28 ## Loop over the two files
+ − 29 for (i in 1:length(types)){
+ − 30 seqs = read.table(files[i], header=FALSE, comment.char="#")
+ − 31 colnames = c("name", "length", "coverage")
+ − 32 names(seqs) = colnames
+ − 33
+ − 34 ## Stats over all sequences
+ − 35 sl_all = sort(seqs\$length, decreasing=TRUE)
+ − 36 cs_all = cumsum(sl_all)
+ − 37 s_all = sum(seqs\$length)
+ − 38 n50_idx_all = which.min(sl_all[cs_all < 0.5*s_all])
+ − 39 n90_idx_all = which.min(sl_all[cs_all < 0.9*s_all])
+ − 40 n50_all = sl_all[n50_idx_all]
+ − 41 n90_all = sl_all[n90_idx_all]
+ − 42
+ − 43 ## Filter short seqs, redo stats
+ − 44 seqs_filt = seqs[seqs\$length >= ${length_co} & seqs\$coverage >= ${coverage_co},]
+ − 45 if (nrow(seqs_filt) > 0){
+ − 46 sl_filt = sort(seqs_filt\$length, decreasing=TRUE)
+ − 47 cs_filt = cumsum(sl_filt)
+ − 48 s_filt = sum(seqs_filt\$length)
+ − 49 n50_idx_filt = which.min(sl_filt[cs_filt < 0.5*s_filt])
+ − 50 n90_idx_filt = which.min(sl_filt[cs_filt < 0.9*s_filt])
+ − 51 n50_filt = sl_filt[n50_idx_filt]
+ − 52 n90_filt = sl_filt[n90_idx_filt]
+ − 53 }
+ − 54 seqs_bad = seqs[seqs\$length < ${length_co} | seqs\$coverage < ${coverage_co},]
+ − 55
+ − 56 ## Length vs coverage
+ − 57 plot(length~coverage, data=seqs, log="xy", type="n", main=paste(types[i], ": coverage vs. length", sep=""), xlab="Coverage", ylab="Length")
+ − 58 if (nrow(seqs_bad) > 0){
+ − 59 points(length~coverage, data=seqs_bad, cex=0.5, col="red")
+ − 60 }
+ − 61 if (nrow(seqs_filt) > 0){
+ − 62 points(length~coverage, data=seqs_filt, cex=0.5, col="black")
+ − 63 }
+ − 64 abline(v=${coverage_co}, h=${length_co}, lty=2, col=grey(0.3))
+ − 65 legend(x="topleft", legend=c("Before/after filtering", paste(c("N50: ", "N90: ", "Median cov.: "), c(n50_all, n90_all, round(median(seqs\$coverage))), rep("/", 3), c(n50_filt, n90_filt, round(median(seqs_filt\$coverage))), sep="")), cex=0.8)
+ − 66 }
+ − 67 dev.off()
+ − 68 </configfile>
+ − 69 </configfiles>
+ − 70 <outputs>
+ − 71 <data format="png" name="out_file" />
+ − 72 </outputs>
+ − 73 <help>
+ − 74 **What it does**
+ − 75
+ − 76 Using the output of SPAdes (a pair of fasta file and stat file for each of the contigs and scaffolds), it produces a coverage vs. contig plot. Each dot represent a contig/scaffold. Given a coverage and a length cutoff, sequences that do not meet those criteria are shown in red. Some statistics are also given (N50, N90, median contig/scaffold length) both before and after filtering.
+ − 77
+ − 78 Use the "filter SPAdes output" tool to actually filter sequences.
+ − 79 </help>
+ − 80 </tool>