static void calculateEigenvector(String file, String chr, int binsize) throws IOException {
if (!file.endsWith("hic")) {
System.err.println("Only 'hic' files are supported");
System.exit(-1);
}
// Load the expected density function, if it exists.
Map<Integer, DensityFunction> zoomToDensityMap = null;
String densityFile = file + ".densities";
if (FileUtils.resourceExists(densityFile)) {
InputStream is = null;
try {
is = ParsingUtils.openInputStream(densityFile);
zoomToDensityMap = DensityUtil.readDensities(is);
} finally {
if (is != null) is.close();
}
} else {
System.err.println("Densities file doesn't exist");
System.exit(-1);
}
SeekableStream ss = IGVSeekableStreamFactory.getStreamFor(file);
Dataset dataset = (new DatasetReader(ss)).read();
Chromosome[] tmp = dataset.getChromosomes();
Map<String, Chromosome> chromosomeMap = new HashMap<String, Chromosome>();
for (Chromosome c : tmp) {
chromosomeMap.put(c.getName(), c);
}
if (!chromosomeMap.containsKey(chr)) {
System.err.println("Unknown chromosome: " + chr);
System.exit(-1);
}
int zoomIdx = 0;
boolean found = false;
for (; zoomIdx < HiCGlobals.zoomBinSizes.length; zoomIdx++) {
if (HiCGlobals.zoomBinSizes[zoomIdx] == binsize) {
found = true;
break;
}
}
if (!found) {
System.err.println("Unknown bin size: " + binsize);
System.exit(-1);
}
Matrix matrix = dataset.getMatrix(chromosomeMap.get(chr), chromosomeMap.get(chr));
MatrixZoomData zd = matrix.getObservedMatrix(zoomIdx);
final DensityFunction df = zoomToDensityMap.get(zd.getZoom());
double[] eigenvector = zd.computeEigenvector(df, 0);
for (double ev : eigenvector) System.out.print(ev + " ");
System.out.println();
}
public static void main(String[] argv)
throws IOException, CmdLineParser.UnknownOptionException,
CmdLineParser.IllegalOptionValueException {
if (argv.length < 4) {
System.out.println("Usage: hictools pre <options> <inputFile> <outputFile> <genomeID>");
System.out.println(" <options>: -d only calculate intra chromosome (diagonal) [false]");
System.out.println(
" : -o calculate densities (observed/expected), write to file [false]");
System.out.println(" : -t <int> only write cells with count above threshold t [0]");
System.out.println(
" : -c <chromosome ID> only calculate map on specific chromosome");
System.exit(0);
}
Globals.setHeadless(true);
CommandLineParser parser = new CommandLineParser();
parser.parse(argv);
String[] args = parser.getRemainingArgs();
if (args[0].equals("sort")) {
AlignmentsSorter.sort(args[1], args[2], null);
} else if (args[0].equals("pairsToBin")) {
String ifile = args[1];
String ofile = args[2];
String genomeId = args[3];
List<Chromosome> chromosomes = loadChromosomes(genomeId);
AsciiToBinConverter.convert(ifile, ofile, chromosomes);
} else if (args[0].equals("binToPairs")) {
String ifile = args[1];
String ofile = args[2];
AsciiToBinConverter.convertBack(ifile, ofile);
} else if (args[0].equals("printmatrix")) {
if (args.length < 5) {
System.err.println(
"Usage: hictools printmatrix <observed/oe/pearson> hicFile chr1 chr2 binsize");
System.exit(-1);
}
String type = args[1];
String file = args[2];
String chr1 = args[3];
String chr2 = args[4];
String binSizeSt = args[5];
int binSize = 0;
try {
binSize = Integer.parseInt(binSizeSt);
} catch (NumberFormatException e) {
System.err.println("Integer expected. Found: " + binSizeSt);
System.exit(-1);
}
dumpMatrix(file, chr1, chr2, binSize, type);
} else if (args[0].equals("eigenvector")) {
if (args.length < 4) {
System.err.println("Usage: hictools eigenvector hicFile chr binsize");
}
String file = args[1];
String chr = args[2];
String binSizeSt = args[3];
int binSize = 0;
try {
binSize = Integer.parseInt(binSizeSt);
} catch (NumberFormatException e) {
System.err.println("Integer expected. Found: " + binSizeSt);
System.exit(-1);
}
calculateEigenvector(file, chr, binSize);
} else if (args[0].equals("pre")) {
String genomeId = "";
try {
genomeId = args[3];
} catch (ArrayIndexOutOfBoundsException e) {
System.err.println("No genome ID given");
System.exit(0);
}
List<Chromosome> chromosomes = loadChromosomes(genomeId);
long genomeLength = 0;
for (Chromosome c : chromosomes) {
if (c != null) genomeLength += c.getSize();
}
chromosomes.set(0, new Chromosome(0, "All", (int) (genomeLength / 1000)));
String[] tokens = args[1].split(",");
List<String> files = new ArrayList<String>(tokens.length);
for (String f : tokens) {
files.add(f);
}
Preprocessor preprocessor = new Preprocessor(new File(args[2]), chromosomes);
preprocessor.setIncludedChromosomes(parser.getChromosomeOption());
preprocessor.setCountThreshold(parser.getCountThresholdOption());
preprocessor.setNumberOfThreads(parser.getThreadedOption());
preprocessor.setDiagonalsOnly(parser.getDiagonalsOption());
preprocessor.setLoadDensities(parser.getDensitiesOption());
preprocessor.preprocess(files);
}
}
static void dumpMatrix(String file, String chr1, String chr2, int binsize, String type)
throws IOException {
if (!file.endsWith("hic")) {
System.err.println("Only 'hic' files are supported");
System.exit(-1);
}
// Load the expected density function, if it exists.
Map<Integer, DensityFunction> zoomToDensityMap = null;
if (type.equals("oe") || type.equals("pearson")) {
String densityFile = file + ".densities";
if (FileUtils.resourceExists(densityFile)) {
InputStream is = null;
try {
is = ParsingUtils.openInputStream(densityFile);
zoomToDensityMap = DensityUtil.readDensities(is);
} finally {
if (is != null) is.close();
}
} else {
System.err.println("Densities file doesn't exist, cannot calculate O/E or Pearson's");
System.exit(-1);
}
}
SeekableStream ss = IGVSeekableStreamFactory.getStreamFor(file);
Dataset dataset = (new DatasetReader(ss)).read();
Chromosome[] tmp = dataset.getChromosomes();
Map<String, Chromosome> chromosomeMap = new HashMap<String, Chromosome>();
for (Chromosome c : tmp) {
chromosomeMap.put(c.getName(), c);
}
if (!chromosomeMap.containsKey(chr1)) {
System.err.println("Unknown chromosome: " + chr1);
System.exit(-1);
} else if (!chromosomeMap.containsKey(chr2)) {
System.err.println("Unknown chromosome: " + chr2);
System.exit(-1);
}
if (type.equals("oe") || type.equals("pearson")) {
if (!chr1.equals(chr2)) {
System.err.println("Chromosome " + chr1 + " not equal to Chromosome " + chr2);
System.err.println("Currently only intrachromosomal O/E and Pearson's are supported.");
System.exit(-1);
}
}
int zoomIdx = 0;
boolean found = false;
for (; zoomIdx < HiCGlobals.zoomBinSizes.length; zoomIdx++) {
if (HiCGlobals.zoomBinSizes[zoomIdx] == binsize) {
found = true;
break;
}
}
if (!found) {
System.err.println("Unknown bin size: " + binsize);
}
Matrix matrix = dataset.getMatrix(chromosomeMap.get(chr1), chromosomeMap.get(chr2));
MatrixZoomData zd = matrix.getObservedMatrix(zoomIdx);
if (type.equals("oe") || type.equals("pearson")) {
final DensityFunction df = zoomToDensityMap.get(zd.getZoom());
if (df == null) {
System.err.println("Densities not calculated to this resolution.");
System.exit(-1);
}
zd.dumpOE(df, type.equals("oe"));
} else zd.dump();
}