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();
}
/**
* Load chromosomes from given ID or file name.
*
* @param idOrFile Genome ID or file name where chromosome lengths written
* @return Chromosome lengths
* @throws IOException if chromosome length file not found
*/
public static List<Chromosome> loadChromosomes(String idOrFile) throws IOException {
InputStream is = null;
try {
// Note: to get this to work, had to edit Intellij settings
// so that "?*.sizes" are considered sources to be copied to class path
is = HiCTools.class.getResourceAsStream(idOrFile + ".chrom.sizes");
if (is == null) {
// Not an ID, see if its a file
File file = new File(idOrFile);
if (file.exists()) {
is = new FileInputStream(file);
} else {
throw new FileNotFoundException("Could not find chromosome sizes file for: " + idOrFile);
}
}
List<Chromosome> chromosomes = new ArrayList();
chromosomes.add(0, null); // Index 0 reserved for "whole genome" psuedo-chromosome
Pattern pattern = Pattern.compile("\t");
BufferedReader reader = new BufferedReader(new InputStreamReader(is));
String nextLine;
long genomeLength = 0;
int idx = 1;
while ((nextLine = reader.readLine()) != null) {
String[] tokens = pattern.split(nextLine);
if (tokens.length == 2) {
String name = tokens[0];
int length = Integer.parseInt(tokens[1]);
genomeLength += length;
chromosomes.add(idx, new Chromosome(idx, name, length));
idx++;
} else {
System.out.println("Skipping " + nextLine);
}
}
// Add the "psuedo-chromosome" All, representing the whole genome. Units are in kilo-bases
chromosomes.set(0, new Chromosome(0, "All", (int) (genomeLength / 1000)));
return chromosomes;
} finally {
if (is != null) is.close();
}
}
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();
}