Merge branch 'master' of https://github.com/seppinho/mutation-server.git

README.md

@@ -14,9 +14,9 @@ It has been integrated in [mtDNA-Server](https://mtdna-server.uibk.ac.at). For s
 You can run mutserve as a standalone tool starting with CRAM/BAM files and detecting heteroplasmic and homoplasmic sites. By default BAQ is set (``--noBaq`` otherwise).
 
 ```
-wget https://github.com/seppinho/mutserve/releases/download/v1.2.1/mutserve-1.2.1.jar
+wget https://github.com/seppinho/mutserve/releases/download/v1.2.2/mutserve-1.2.2.jar
 
-java -jar mutserve-1.2.1.jar  analyse-local --input <file/folder> --output <filename.vcf / filename.txt> --reference <fasta> --level 0.01
+java -jar mutserve-1.2.2.jar  analyse-local --input <file/folder> --output <filename.vcf / filename.txt> --reference <fasta> --level 0.01
 ```
 To create a VCF file as an output simple specify `--output filename.vcf.gz`. Please use [this reference file](https://raw.githubusercontent.com/seppinho/mutserve/master/files/rCRS.fasta) when using BAQ.
 
@@ -49,9 +49,9 @@ If you want a **VCF** file as an output, please specify `--output filename.vcf.g
 
 ## Performance - Sensitivity and Specificity
 
-If you have a mixture model generated, you can use mutserve for checking precision, specificity and sensitivity. The expected mutations (homoplasmic and heteroplasmic) need to be provided as gold standard in form of a text file, with one column, containing the positions expected. The variant from *analyse-local* are used as input file and length needs to be specified (usually 16,569, but as there are different reference sequence, this can vary as well).
+If you have a mixture model generated, you can use mutserve for checking precision, specificity and sensitivity. The expected mutations (homoplasmic and heteroplasmic) need to be provided as gold standard in form of a text file, with one column, containing the positions expected. The variant from *analyse-local* are used as input file and length needs to be specified (usually 16,569 for human mitochondrial genomes, but as there are different reference sequence, this can vary as well). The value provided in *level* indicates the threshold for heteroplasmic levels to be considered in the analysis.
 ```
-java -jar mutserve-1.2.1.jar  performance --in <variantfile> --gold <expectedmutations> --length <size of reference>
+java -jar mutserve-1.2.2.jar  performance --in <variantfile> --gold <expectedmutations> --length <size of reference> --level <threshold for heteroplasmic levels>
 ```
 
 ## Citation

pom.xml

@@ -4,7 +4,7 @@
 	<modelVersion>4.0.0</modelVersion>
 	<groupId>genepi</groupId>
 	<artifactId>mutserve</artifactId>
-	<version>1.2.1</version>
+	<version>1.2.2</version>
 
 	<properties>
 		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>

src/main/java/genepi/mut/pileup/PileupToolLocal.java

@@ -27,7 +27,7 @@
 
 public class PileupToolLocal extends Tool {
 
-	String version = "v1.2.1";
+	String version = "v1.2.2";
 	String mode = "mtdna";
 	String command;
 

src/main/java/genepi/mut/tools/CalcPrecision.java

@@ -25,6 +25,7 @@ public void createParameters() {
 		addParameter("gold", "expected positions");
 		addParameter("in", "input csv file");
 		addParameter("length", "length of genome/locus", INTEGER);
+		addParameter("level", "heteroplasmy level applied", DOUBLE); 
 
 	}
 
@@ -37,7 +38,8 @@ public void init() {
 	public int run() {
 
 		final String pos = "Pos";
-		final String sampleId= "SampleID";
+		final String sampleId= "ID";
+		final String variantlevel ="VariantLevel";
 
 		Set<Integer> allPos = new TreeSet<Integer>();
 		Set<Integer> goldPos = new TreeSet<Integer>();
@@ -48,6 +50,7 @@ public int run() {
 
 		String gold = (String) getValue("gold");
 		int length= (int)getValue("length");
+		double level = (double) getValue("level");
 
 		CsvTableReader idReader = new CsvTableReader(in, '\t');
 
@@ -90,10 +93,14 @@ public int run() {
 
 				int posSample = variantReader.getInteger(pos);
 
+				double variantlevSample = variantReader.getDouble(variantlevel); 
+
 				if (id.equals(idSample)) {
 
 					int position = posSample;
 
+					if (variantlevSample>level) {
+
 					if (goldPos.contains(position)) {
 						goldPos.remove(position);
 						truePositiveCount++;
@@ -105,6 +112,7 @@ public int run() {
 					}
 
 				}
+				}
 			}
 
 			for (int j = 1; j <= length; j++) {
@@ -138,7 +146,7 @@ public int run() {
 			String spec = df.format(spec2);
 			String prec = df.format(prec2);
 
-			System.out.println(id+"\t"+truePositiveCount+"/"+ (truePositiveCount + falseNegativeCount)+"\t"+falsePositiveCount+"\t"+prec+"\t"+sens+"\t"+spec);
+			System.out.println(id+"\t"+truePositiveCount+" / "+ (truePositiveCount + falseNegativeCount)+"\t"+falsePositiveCount+"\t"+prec+"\t"+sens+"\t"+spec);
 
 		}
 		return 0;