view kmersvm/prcurve.xml @ 4:18e2ebf5ff19 draft

Uploaded

<tool id="PR Curve" name="Plot Precision-Recall Curve">
	<description>using kmerSVM predictions</description>
	<command interpreter="sh">r_wrapper.sh $script_file</command>
	<inputs>
		<param format="tabular" name="cvpred_data" type="data" label="CV Predictions"/>
	</inputs>
	<outputs>
		<data format="png" name="PR_curve" from_work_dir="prcurve.png" />
	</outputs>

	<configfiles>
		<configfile name="script_file">

			rm(list = objects() )

			########## calculate auprc #########
			auPRC &lt;- function (perf) {
				rec &lt;- [e-mail]
				prec &lt;- [e-mail]
				result &lt;- list()
				for (i in 1:length([e-mail])) {
				result[i] &lt;- list(sum((rec[[i]][2:length(rec[[i]])] - rec[[i]][2:length(rec[[i]])-1])*prec[[i]][-1]))
				}
				return(result)
			}

			########## plot ROC and PR-Curve #########
			prcurve &lt;- function(x) {
				sink(NULL,type="message")
				options(warn=-1)
				suppressMessages(suppressWarnings(library('ROCR')))
				svmresult &lt;- data.frame(x)
				colnames(svmresult) &lt;- c("Seqid","Pred","Label", "CV")

				linewd &lt;- 1
				wd &lt;- 4
				ht &lt;- 4
				fig.nrows &lt;- 1 
				fig.ncols &lt;- 1
				pt &lt;- 10
				cex.general &lt;- 1 
				cex.lab &lt;- 0.9
				cex.axis &lt;- 0.9
				cex.main &lt;- 1.2
				cex.legend &lt;- 0.8


				png("prcurve.png", width=wd*fig.ncols, height=ht*fig.nrows, unit="in", res=100)

				par(xaxs="i", yaxs="i", mar=c(3.5,3.5,2,2)+0.1, mgp=c(2,0.8,0), mfrow=c(fig.nrows, fig.ncols))

				CVs &lt;- unique(svmresult[["CV"]])
				preds &lt;- list()
				labs &lt;- list()
				auc &lt;- c()
				for(i in 1:length(CVs)) {
					preds[i] &lt;- subset(svmresult, CV==(i-1), select=c(Pred))
					labs[i] &lt;- subset(svmresult, CV==(i-1), select=c(Label))
				}

				pred &lt;- prediction(preds, labs)
				perf_prc &lt;- performance(pred, 'prec', 'rec')

				prcs &lt;- auPRC(perf_prc)
				avgprc &lt;- 0

				for(j in 1:length(CVs)) {
					avgprc &lt;- avgprc + prcs[[j]]
				}        

				avgprc &lt;- avgprc/length(CVs)

				plot(perf_prc, colorize=T, main="P-R curve", spread.estimate="stderror",
				xlab="Recall", ylab="Precision", cex.lab=1.2, xlim=c(0,1), ylim=c(0,1))
				text(0.2, 0.1, paste("AUC=", format(avgprc, digits=3, nsmall=3)))

				dev.off()
			}

			############## main function #################
			d &lt;- read.table("${cvpred_data}")

			prcurve(d)

		</configfile>
	</configfiles>

	<help>
	
**Note**

This tool is based on the ROCR library.  If you use this tool please cite:
		
Tobias Sing, Oliver Sander, Niko Beerenwinkel, Thomas Lengauer.
ROCR: visualizing classifier performance in R.
Bioinformatics 21(20):3940-3941 (2005).  
        
----

**What it does**

Takes as input cross-validation predictions and calculates Precision-Recall(PR) Curve and its area under curve(AUC).

----

**Results**

PR Curve: Precision Recall Curve. Compares number of true positives (recall; same as sensitivity) to the number of true positives relative to the total number sequences classified as positive (precision). 

Area Under the PR Curve.

<!--
**Example**

.. image:: ./static/images/sample_roc_chen.png
-->
	</help>
</tool>