Description: using classes of commons-cli instead of unpackaged ones Author: Pierre Gruet Forwarded: not-needed Last-Update: 2021-07-31 --- a/goby-distribution/src/main/java/org/campagnelab/goby/algorithmic/algorithm/dmr/EstimatedDistribution.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/algorithmic/algorithm/dmr/EstimatedDistribution.java @@ -19,7 +19,7 @@ package org.campagnelab.goby.algorithmic.algorithm.dmr; import org.campagnelab.goby.algorithmic.algorithm.FenwickTree; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import it.unimi.dsi.fastutil.ints.IntArrayList; import it.unimi.dsi.fastutil.io.BinIO; import it.unimi.dsi.fastutil.objects.ObjectArrayList; @@ -240,68 +240,113 @@ } public static void main(final String[] args) throws IOException { - boolean printDensity = CLI.isKeywordGiven(args, "--print-density"); - boolean printObservations = CLI.isKeywordGiven(args, "--print-observations"); - String filename = CLI.getOption(args, "-f", null); - String outputFilename = CLI.getOption(args, "-o", "out.tsv"); - PrintWriter outWriter = new PrintWriter(new FileWriter(outputFilename)); - if (printDensity) { - EstimatedDistribution estimated = null; - - try { - estimated = load(filename); - String statName = estimated.getStatAdaptor().statName(); - System.out.println("Statistic=" + statName); - System.out.println("binning strategy=" + estimated.getBinningStrategy().getName()); - int index = 0; - outWriter.println("midPointSumTotal\tsumTotal range\t" + statName + "\tcount-at-" + statName); - final BinningStrategy binningStrategy = estimated.getBinningStrategy(); - for (final FenwickTree tree : estimated.densitities) { - if (tree != null) { - int low = binningStrategy.getLowerBound(index); - int high = binningStrategy.getUpperBound(index); - - int midPointSumTotal = binningStrategy.getMidpoint(index); - System.out.printf("low=%d high=%d midPoint=%d %n", low, high, midPointSumTotal); - final long maxCumulative = tree.getCumulativeCount(tree.size() - 2); - for (int scaledStatistic = 0; scaledStatistic < tree.size() - 1; scaledStatistic++) { - final long cumulativeCountAt = tree.getCumulativeCount(scaledStatistic); - final long cumulativeCountAfter = tree.getCumulativeCount(scaledStatistic + 1); - - outWriter.printf("%d\t[%d-%d]\t%g\t%d%n", midPointSumTotal, binningStrategy.getLowerBound(index), - binningStrategy.getUpperBound(index), estimated.unscale(scaledStatistic), cumulativeCountAfter - cumulativeCountAt); - if (cumulativeCountAfter == maxCumulative) { - break; + Options options = new Options(); + + Option pDensity = new Option("printDensity", "print-density", false, "print density"); + pDensity.setRequired(false); + options.addOption(pDensity); + + Option pObservations = new Option("printObservations", "print-observations", false, "print observations"); + pObservations.setRequired(false); + options.addOption(pObservations); + + Option fname = new Option("filename", "filename", true, "filename"); + fname.setRequired(false); + options.addOption(fname); + + Option o = new Option("o", "o", true, "output filename"); + o.setRequired(false); + options.addOption(o); + + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + String filename; + String outputFilename; + boolean printDensity; + boolean printObservations; + + try { + cmd = parser.parse(options, args); + printDensity = cmd.hasOption("printDensity"); + + printObservations = cmd.hasOption("printObservations"); + + if (cmd.hasOption("f")) { + filename = cmd.getOptionValue("f"); + } + else { + filename = null; + } + + if (cmd.hasOption("o")) { + outputFilename = cmd.getOptionValue("o"); + } + else { + outputFilename = new String("out.tsv"); + } + + PrintWriter outWriter = new PrintWriter(new FileWriter(outputFilename)); + if (printDensity) { + EstimatedDistribution estimated = null; + + try { + estimated = load(filename); + String statName = estimated.getStatAdaptor().statName(); + System.out.println("Statistic=" + statName); + System.out.println("binning strategy=" + estimated.getBinningStrategy().getName()); + int index = 0; + outWriter.println("midPointSumTotal\tsumTotal range\t" + statName + "\tcount-at-" + statName); + final BinningStrategy binningStrategy = estimated.getBinningStrategy(); + for (final FenwickTree tree : estimated.densitities) { + if (tree != null) { + int low = binningStrategy.getLowerBound(index); + int high = binningStrategy.getUpperBound(index); + + int midPointSumTotal = binningStrategy.getMidpoint(index); + System.out.printf("low=%d high=%d midPoint=%d %n", low, high, midPointSumTotal); + final long maxCumulative = tree.getCumulativeCount(tree.size() - 2); + for (int scaledStatistic = 0; scaledStatistic < tree.size() - 1; scaledStatistic++) { + final long cumulativeCountAt = tree.getCumulativeCount(scaledStatistic); + final long cumulativeCountAfter = tree.getCumulativeCount(scaledStatistic + 1); + + outWriter.printf("%d\t[%d-%d]\t%g\t%d%n", midPointSumTotal, binningStrategy.getLowerBound(index), + binningStrategy.getUpperBound(index), estimated.unscale(scaledStatistic), cumulativeCountAfter - cumulativeCountAt); + if (cumulativeCountAfter == maxCumulative) { + break; + } } } - } - index++; + index++; + } + outWriter.close(); + } catch (Exception e) { + e.printStackTrace(); + System.exit(1); } - outWriter.close(); - } catch (Exception e) { - e.printStackTrace(); - System.exit(1); - } - } - if (printObservations) { + } + if (printObservations) { - EstimatedDistribution estimated = null; + EstimatedDistribution estimated = null; - try { - estimated = load(filename); - String statName = estimated.getStatAdaptor().statName(); - outWriter.println("tscaled-" + statName + "\t" + statName + "\tcovariates\n"); - for (final Observation observation : estimated.getObservations()) { - outWriter.printf("%d\t%d\t%g\t%s%n", observation.scaledStatistic, - estimated.unscale(observation.scaledStatistic), IntArrayList.wrap(observation.covariates)); + try { + estimated = load(filename); + String statName = estimated.getStatAdaptor().statName(); + outWriter.println("tscaled-" + statName + "\t" + statName + "\tcovariates\n"); + for (final Observation observation : estimated.getObservations()) { + outWriter.printf("%d\t%d\t%g\t%s%n", observation.scaledStatistic, + estimated.unscale(observation.scaledStatistic), IntArrayList.wrap(observation.covariates)); + } + outWriter.close(); + } catch (ClassNotFoundException e) { + e.printStackTrace(); + System.exit(1); } - outWriter.close(); - } catch (ClassNotFoundException e) { - e.printStackTrace(); - System.exit(1); } + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); } } --- a/goby-distribution/src/main/java/org/campagnelab/goby/cli/FoldChangeForExonPairs.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/cli/FoldChangeForExonPairs.java @@ -19,7 +19,7 @@ package org.campagnelab.goby.cli; import edu.cornell.med.icb.io.TSVReader; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import java.io.FileReader; import java.io.FileNotFoundException; @@ -46,38 +46,109 @@ } private void process(String[] args) throws FileNotFoundException { - String inputFilenames = CLI.getOption(args, "--data", "expression-data.tsv,expression-data2.tsv"); - String pairsFilename = CLI.getOption(args, "--pairs", "pairs.tsv"); - String log2AverageId = CLI.getOption(args, "--group", "average log2_RPKM group UHR(BUQ)"); - String outputFilename = CLI.getOption(args, "--output", "/data/gc-weights/exons/out.tsv"); - String averageCountId = CLI.getOption(args, "--threshold-id", "average count group Brain"); - int thresholdValue = CLI.getIntOption(args, "--threshold-value", 20); - - // String groupB= CLI.getOption(args,"-2","average RPKM group UHR(BUQ)"); - int log2AverageColumnIndex = -1; - Object2DoubleMap exonExpressionData; - - - ObjectArrayList pairs = loadPairs(pairsFilename); - PrintWriter output = new PrintWriter(outputFilename); - output.printf("experiment\texonId1\texonId2\tlog2RpkmExon1-log2RpkmExon2%n"); - for (String inputFilename : inputFilenames.split("[,]")) { - - System.out.println("Processing " + inputFilename); - exonExpressionData = loadData(inputFilename, log2AverageId, averageCountId, thresholdValue); - System.out.println("Size: " + exonExpressionData.size()); - System.out.println("Writing data.."); - for (Pair pair : pairs) { - //calculate log2 RPKM exonId1 - exonId2: - if (exonExpressionData.containsKey(pair.exonId1) && exonExpressionData.containsKey(pair.exonId2)) { - double log2FoldChangeExons = exonExpressionData.get(pair.exonId1) - exonExpressionData.get(pair.exonId2); - output.printf("%s\t%s\t%s\t%g%n", FilenameUtils.getBaseName(inputFilename), - pair.exonId1, pair.exonId2, log2FoldChangeExons); - } + Options options = new Options(); + + Option oData = new Option("data", "data", true, "data"); + oData.setRequired(false); + options.addOption(oData); + + Option oPairs = new Option("pairs", "pairs", true, "pairs"); + oPairs.setRequired(false); + options.addOption(oPairs); + + Option oGroup = new Option("group", "group", true, "group"); + oGroup.setRequired(false); + options.addOption(oGroup); + + Option oOutput = new Option("output", "output", true, "output"); + oOutput.setRequired(false); + options.addOption(oOutput); + + Option oThresId = new Option("thresholdId", "threshold-id", true, "threshold id"); + oThresId.setRequired(false); + options.addOption(oThresId); + + Option oThresVal = new Option("thresholdVal", "threshold-value", true, "threshold value"); + oThresVal.setRequired(false); + options.addOption(oThresVal); + + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + String inputFilenames; + String pairsFilename; + String log2AverageId; + String outputFilename; + String averageCountId; + int thresholdValue; + + try { + cmd = parser.parse(options, args); + if (cmd.hasOption("data")) { + inputFilenames = cmd.getOptionValue("data"); + } + else { + inputFilenames = new String("expression-data.tsv,expression-data2.tsv"); + } + if (cmd.hasOption("pairs")) { + pairsFilename = cmd.getOptionValue("pairs"); + } + else { + pairsFilename = new String("pairs.tsv"); + } + if (cmd.hasOption("group")) { + log2AverageId = cmd.getOptionValue("group"); + } + else { + log2AverageId = new String("average log2_RPKM group UHR(BUQ)"); + } + if (cmd.hasOption("output")) { + outputFilename = cmd.getOptionValue("output"); + } + else { + outputFilename = new String("/data/gc-weights/exons/out.tsv"); + } + if (cmd.hasOption("thresholdId")) { + averageCountId = cmd.getOptionValue("thresholdId"); + } + else { + averageCountId = new String("average count group Brain"); + } + if (cmd.hasOption("thresholdVal")) { + thresholdValue = Integer.parseInt(cmd.getOptionValue("thresholdVal")); + } + else { + thresholdValue = 20; } - } + // String groupB= CLI.getOption(args,"-2","average RPKM group UHR(BUQ)"); + int log2AverageColumnIndex = -1; + Object2DoubleMap exonExpressionData; + + + ObjectArrayList pairs = loadPairs(pairsFilename); + PrintWriter output = new PrintWriter(outputFilename); + output.printf("experiment\texonId1\texonId2\tlog2RpkmExon1-log2RpkmExon2%n"); + for (String inputFilename : inputFilenames.split("[,]")) { + + System.out.println("Processing " + inputFilename); + exonExpressionData = loadData(inputFilename, log2AverageId, averageCountId, thresholdValue); + System.out.println("Size: " + exonExpressionData.size()); + System.out.println("Writing data.."); + for (Pair pair : pairs) { + //calculate log2 RPKM exonId1 - exonId2: + if (exonExpressionData.containsKey(pair.exonId1) && exonExpressionData.containsKey(pair.exonId2)) { + double log2FoldChangeExons = exonExpressionData.get(pair.exonId1) - exonExpressionData.get(pair.exonId2); + output.printf("%s\t%s\t%s\t%g%n", FilenameUtils.getBaseName(inputFilename), + pair.exonId1, pair.exonId2, log2FoldChangeExons); + } + + } + } + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); + } } private ObjectArrayList loadPairs(String pairsFilename) throws FileNotFoundException { --- a/goby-distribution/src/main/java/org/campagnelab/goby/cli/PlantIndels.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/cli/PlantIndels.java @@ -19,7 +19,7 @@ package org.campagnelab.goby.cli; import org.campagnelab.goby.parsers.FastaParser; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import it.unimi.dsi.lang.MutableString; import java.io.*; @@ -40,26 +40,128 @@ private int numIndels; public static void main(final String args[]) throws IOException { - final String fastaReference = CLI.getOption(args, "-r", null); - final String outputFilename = CLI.getOption(args, "-o", "out.fq"); - final String regionIndelTruth = CLI.getOption(args, "-t", "indel-truth.tsv"); - // reference sequence to use - final String refChoice = CLI.getOption(args, "-c", "22"); - int from = CLI.getIntOption(args, "-s", 0); - int to = CLI.getIntOption(args, "-e", 0); - if (to < from) { - System.err.println("argument to -e must be larger than argument to -s"); - System.exit(1); - } - final int indelLength = CLI.getIntOption(args, "-l", 3); + Options options = new Options(); + + Option oR = new Option("r", "r", true, "r"); + oR.setRequired(false); + options.addOption(oR); + + Option oO = new Option("o", "o", true, "o"); + oO.setRequired(false); + options.addOption(oO); + + Option oT = new Option("t", "t", true, "t"); + oT.setRequired(false); + options.addOption(oT); + + Option oC = new Option("c", "c", true, "c"); + oC.setRequired(false); + options.addOption(oC); + + Option oS = new Option("s", "s", true, "s"); + oS.setRequired(false); + options.addOption(oS); + + Option oE = new Option("e", "e", true, "e"); + oE.setRequired(false); + options.addOption(oE); + + Option oL = new Option("l", "l", true, "l"); + oL.setRequired(false); + options.addOption(oL); + + Option oM = new Option("m", "m", true, "m"); + oM.setRequired(false); + options.addOption(oM); + + Option oRd = new Option("readDeletion", "read-deletion", false, "readDeletion"); + oRd.setRequired(false); + options.addOption(oRd); + + Option oN = new Option("n", "n", true, "n"); + oN.setRequired(false); + options.addOption(oN); + + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + final String fastaReference; + final String outputFilename; + final String regionIndelTruth; + // reference sequence to use + final String refChoice; + int from; + int to; + final int indelLength; PlantIndels processor = new PlantIndels(); - processor.outputFilename = outputFilename; - processor.insert = !CLI.isKeywordGiven(args, "--read-deletion"); - processor.numIndels=CLI.getIntOption(args,"-n",5); - processor.process(refChoice, fastaReference, from, to, indelLength, regionIndelTruth); + try { + cmd = parser.parse(options, args); + if (cmd.hasOption("r")) { + fastaReference = cmd.getOptionValue("r"); + } + else { + fastaReference = null; + } + if (cmd.hasOption("o")) { + outputFilename = cmd.getOptionValue("o"); + } + else { + outputFilename = new String("out.fq"); + } + if (cmd.hasOption("t")) { + regionIndelTruth = cmd.getOptionValue("t"); + } + else { + regionIndelTruth = new String("indel-truth.tsv"); + } + if (cmd.hasOption("c")) { + refChoice = cmd.getOptionValue("c"); + } + else { + refChoice = new String("22"); + } + if (cmd.hasOption("s")) { + from = Integer.parseInt(cmd.getOptionValue("s")); + } + else { + from = 0; + } + if (cmd.hasOption("e")) { + to = Integer.parseInt(cmd.getOptionValue("e")); + } + else { + to = 0; + } + + if (to < from) { + System.err.println("argument to -e must be larger than argument to -s"); + System.exit(1); + } + + if (cmd.hasOption("l")) { + indelLength = Integer.parseInt(cmd.getOptionValue("l")); + } + else { + indelLength = 3; + } + + processor.outputFilename = outputFilename; + processor.insert = !cmd.hasOption("readDeletion"); + + if (cmd.hasOption("n")) { + processor.numIndels = Integer.parseInt(cmd.getOptionValue("n")); + } + else { + processor.numIndels = 5; + } + + processor.process(refChoice, fastaReference, from, to, indelLength, regionIndelTruth); + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); + } } public void process(String refChoice, String fastaReference, int from, int to, int indelLength, String regionIndelTruth) throws IOException { --- a/goby-distribution/src/main/java/org/campagnelab/goby/cli/SimulateBisulfiteReads.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/cli/SimulateBisulfiteReads.java @@ -20,7 +20,7 @@ import org.campagnelab.goby.reads.QualityEncoding; import org.campagnelab.goby.parsers.FastaParser; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import it.unimi.dsi.fastutil.doubles.DoubleArrayList; import it.unimi.dsi.fastutil.doubles.DoubleIterator; import it.unimi.dsi.fastutil.doubles.DoubleList; @@ -72,32 +72,152 @@ public static void main(String[] args) throws IOException { - String fastaReference = CLI.getOption(args, "-r", null); - String outputFilename = CLI.getOption(args, "-o", "out.fq"); - String regionTrueRates = CLI.getOption(args, "-t", "true-methylation.tsv"); + Options options = new Options(); + + Option oR = new Option("r", "r", true, "r"); + oR.setRequired(false); + options.addOption(oR); + + Option oO = new Option("o", "o", true, "o"); + oO.setRequired(false); + options.addOption(oO); + + Option oT = new Option("t", "t", true, "t"); + oT.setRequired(false); + options.addOption(oT); + + Option oC = new Option("c", "c", true, "c"); + oC.setRequired(false); + options.addOption(oC); + + Option oS = new Option("s", "s", true, "s"); + oS.setRequired(false); + options.addOption(oS); + + Option oE = new Option("e", "e", true, "e"); + oE.setRequired(false); + options.addOption(oE); + + Option oL = new Option("l", "l", true, "l"); + oL.setRequired(false); + options.addOption(oL); + + Option oM = new Option("m", "m", true, "m"); + oM.setRequired(false); + options.addOption(oM); + + Option oBs = new Option("bisulfite", "bisulfite", false, "bisulfite"); + oBs.setRequired(false); + options.addOption(oBs); + + Option oStrand = new Option("strand", "strand", true, "strand"); + oStrand.setRequired(false); + options.addOption(oStrand); + + Option oN = new Option("n", "n", true, "n"); + oN.setRequired(false); + options.addOption(oN); + + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + String fastaReference; + String outputFilename; + String regionTrueRates; // reference sequence to use - String refChoice = CLI.getOption(args, "-c", "22"); - int from = CLI.getIntOption(args, "-s", 0); - int to = CLI.getIntOption(args, "-e", 0); - if (to < from) { - System.err.println("argument to -e must be larger than argument to -s"); - System.exit(1); - } - int readLength = CLI.getIntOption(args, "-l", 50); - String methylationRateFilename = CLI.getOption(args, "-m", "methylation-rates.tsv"); + String refChoice; + int from; + int to; + int readLength; + String methylationRateFilename; + String strandChoice; SimulateBisulfiteReads processor = new SimulateBisulfiteReads(); - final boolean bisulfite = CLI.isKeywordGiven(args, "--bisulfite"); - String strandChoice = CLI.getOption(args, "--strand", "both"); + final boolean bisulfite; - processor.configure(bisulfite, strandChoice); - processor.bisulfiteTreatment = bisulfite; - processor.readLength = readLength; - processor.outputFilename = outputFilename; - processor.regionTrueRates = regionTrueRates; - processor.numRepeats = CLI.getIntOption(args, "-n", 10000); - - processor.process(refChoice, fastaReference, from, to, methylationRateFilename); + try { + cmd = parser.parse(options, args); + if (cmd.hasOption("r")) { + fastaReference = cmd.getOptionValue("r"); + } + else { + fastaReference = null; + } + if (cmd.hasOption("o")) { + outputFilename = cmd.getOptionValue("o"); + } + else { + outputFilename = new String("out.fq"); + } + if (cmd.hasOption("t")) { + regionTrueRates = cmd.getOptionValue("t"); + } + else { + regionTrueRates = new String("true-methylation.tsv"); + } + if (cmd.hasOption("c")) { + refChoice = cmd.getOptionValue("c"); + } + else { + refChoice = new String("22"); + } + if (cmd.hasOption("s")) { + from = Integer.parseInt(cmd.getOptionValue("s")); + } + else { + from = 0; + } + if (cmd.hasOption("e")) { + to = Integer.parseInt(cmd.getOptionValue("e")); + } + else { + to = 0; + } + + if (to < from) { + System.err.println("argument to -e must be larger than argument to -s"); + System.exit(1); + } + + if (cmd.hasOption("l")) { + readLength = Integer.parseInt(cmd.getOptionValue("l")); + } + else { + readLength = 50; + } + if (cmd.hasOption("m")) { + methylationRateFilename = cmd.getOptionValue("c"); + } + else { + methylationRateFilename = new String("methylation-rates.tsv"); + } + + bisulfite = cmd.hasOption("biSulfite"); + + if (cmd.hasOption("strand")) { + strandChoice = cmd.getOptionValue("strang"); + } + else { + strandChoice = new String("both"); + } + + processor.configure(bisulfite, strandChoice); + processor.bisulfiteTreatment = bisulfite; + processor.readLength = readLength; + processor.outputFilename = outputFilename; + processor.regionTrueRates = regionTrueRates; + + if (cmd.hasOption("n")) { + processor.numRepeats = Integer.parseInt(cmd.getOptionValue("n")); + } + else { + processor.numRepeats = 10000; + } + + processor.process(refChoice, fastaReference, from, to, methylationRateFilename); + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); + } } public void configure(boolean bisulfite, String strandChoice) { --- a/goby-distribution/src/main/java/org/campagnelab/goby/methylation/MethylSimilarityScan.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/methylation/MethylSimilarityScan.java @@ -20,7 +20,7 @@ import org.campagnelab.goby.cli.DoInParallel; import edu.cornell.med.icb.io.TSVReader; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import it.unimi.dsi.fastutil.floats.FloatArrayList; import it.unimi.dsi.fastutil.ints.*; import it.unimi.dsi.fastutil.io.BinIO; @@ -63,40 +63,92 @@ } private void process(String[] args) throws IOException { - String inputFilename = CLI.getOption(args, "-i", "/data/lister/mc_h1.tsv"); - this.windowWidths = CLI.getOption(args, "-w", "10"); - this.maxBestHits = CLI.getIntOption(args, "-h", 100); - String outputFilename = CLI.getOption(args, "-o", "out.tsv"); - final MethylationData data = load(inputFilename); - File outputFile = new File(outputFilename); - boolean outputFileExists = outputFile.exists(); -// append: - PrintWriter output = new PrintWriter(new FileWriter(outputFilename, true)); + Options options = new Options(); - if (!outputFileExists) { - output.write("windowSize\tlocation\tchromosome\tforward strand start\tforward strand end\treverse strand start\treverse strand end\teffective window size\tstatistic\n"); - } - for (String windowWidthString : windowWidths.split("[,]")) { - final int windowWidth = Integer.parseInt(windowWidthString); - System.out.println("Processing window size=" + windowWidth); - final HitBoundedPriorityQueue hits = new HitBoundedPriorityQueue(maxBestHits); - DoInParallel scan = new DoInParallel() { - @Override - public void action(DoInParallel forDataAccess, String chromosome, int loopIndex) { - compareStrands(hits, data, windowWidth, new MutableString(chromosome)); - } - }; + Option oI = new Option("i", "i", true, "i"); + oI.setRequired(false); + options.addOption(oI); + + Option oW = new Option("w", "w", true, "w"); + oW.setRequired(false); + options.addOption(oW); + + Option oH = new Option("h", "h", true, "h"); + oH.setRequired(false); + options.addOption(oH); + + Option oO = new Option("o", "o", true, "o"); + oO.setRequired(false); + options.addOption(oO); + + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + String inputFilename; + String outputFilename; + + try { + cmd = parser.parse(options, args); + + if (cmd.hasOption("i")) { + inputFilename = cmd.getOptionValue("i"); + } + else { + inputFilename = new String("/data/lister/mc_h1.tsv"); + } + if (cmd.hasOption("w")) { + this.windowWidths = cmd.getOptionValue("w"); + } + else { + this.windowWidths = new String("10"); + } + if (cmd.hasOption("h")) { + this.maxBestHits = Integer.parseInt(cmd.getOptionValue("h")); + } + else { + this.maxBestHits = 100; + } + if (cmd.hasOption("o")) { + outputFilename = cmd.getOptionValue("o"); + } + else { + outputFilename = new String("out.tsv"); + } - try { - scan.execute(true, data.getChromosomeStrings()); - } catch (Exception e) { - e.printStackTrace(); //To change body of catch statement use File | Settings | File Templates. + final MethylationData data = load(inputFilename); + File outputFile = new File(outputFilename); + boolean outputFileExists = outputFile.exists(); + // append: + PrintWriter output = new PrintWriter(new FileWriter(outputFilename, true)); + + + if (!outputFileExists) { + output.write("windowSize\tlocation\tchromosome\tforward strand start\tforward strand end\treverse strand start\treverse strand end\teffective window size\tstatistic\n"); } + for (String windowWidthString : windowWidths.split("[,]")) { + final int windowWidth = Integer.parseInt(windowWidthString); + System.out.println("Processing window size=" + windowWidth); + final HitBoundedPriorityQueue hits = new HitBoundedPriorityQueue(maxBestHits); + DoInParallel scan = new DoInParallel() { + @Override + public void action(DoInParallel forDataAccess, String chromosome, int loopIndex) { + compareStrands(hits, data, windowWidth, new MutableString(chromosome)); + } + }; + + try { + scan.execute(true, data.getChromosomeStrings()); + } catch (Exception e) { + e.printStackTrace(); //To change body of catch statement use File | Settings | File Templates. + } - printResults(hits, windowWidth, data, output); + printResults(hits, windowWidth, data, output); + } + output.close(); + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); } - output.close(); } --- a/goby-distribution/src/main/java/org/campagnelab/goby/modes/PercentMismatchesQualityFilter.java +++ b/goby-distribution/src/main/java/org/campagnelab/goby/modes/PercentMismatchesQualityFilter.java @@ -20,7 +20,7 @@ package org.campagnelab.goby.modes; -import edu.mssm.crover.cli.CLI; +import org.apache.commons.cli.*; import org.apache.commons.lang.StringUtils; import org.campagnelab.goby.alignments.Alignments; import org.campagnelab.goby.alignments.filters.AlignmentQualityFilter; @@ -61,9 +61,30 @@ } public void setParameters(final String parameters) { - final String[] args = StringUtils.defaultString(parameters).split("[',=]"); - qualityThresholdPercent = CLI.getDoubleOption(args, "threshold", 0.05d); - System.err.println("Setting quality threshold to " + qualityThresholdPercent); + final String parametersWithHyphens = StringUtils.replace(parameters, "threshold", "-threshold"); + final String[] args = StringUtils.defaultString(parametersWithHyphens).split("[',=]"); + Options options = new Options(); + + Option threshold = new Option("threshold", "threshold", true, "threshold"); + threshold.setRequired(false); + options.addOption(threshold); + CommandLineParser parser = new DefaultParser(); + CommandLine cmd; + + try { + cmd = parser.parse(options, args); + + if (cmd.hasOption("threshold")) { + qualityThresholdPercent = Double.parseDouble(cmd.getOptionValue("threshold")); + } + else { + qualityThresholdPercent = 0.05d; + } + System.err.println("Setting quality threshold to " + qualityThresholdPercent); + } catch (ParseException e) { + System.out.println(e.getMessage()); + System.exit(1); + } } public void printUsage(final PrintStream out) {