Examples with SeqMonkException uk.ac.babraham.SeqMonk.SeqMonkException used on opensource projects

Example 11 with SeqMonkException

use of uk.ac.babraham.SeqMonk.SeqMonkException in project SeqMonk by s-andrews.

the class SeqMonkParser method parseGenome.

/**
 * Parses the genome line.
 *
 * @param sections The tab split sections from the genome line
 * @throws SeqMonkException
 */
private void parseGenome(String[] sections) throws Exception {
    if (sections.length != 3) {
        throw new SeqMonkException("Genome line didn't contain 3 sections");
    }
    if (!sections[0].equals("Genome")) {
        throw new SeqMonkException("First line of file was not the genome description");
    }
    // If we have a multi genome then sections 1 and 2 will be sub-divided with bar characters
    String[] speciesStrings = sections[1].split("\\|");
    String[] assemblyStrings = sections[2].split("\\|");
    if (speciesStrings.length != assemblyStrings.length) {
        throw new SeqMonkException("Got different number of species and assembly names from '" + sections[1] + "' and '" + sections[2] + "'");
    }
    File[] files = new File[speciesStrings.length];
    for (int g = 0; g < speciesStrings.length; g++) {
        try {
            files[g] = new File(SeqMonkPreferences.getInstance().getGenomeBase().getAbsoluteFile() + "/" + speciesStrings[g] + "/" + assemblyStrings[g]);
        } catch (FileNotFoundException e) {
            throw new SeqMonkException("Couldn't find the folder which should contain the genome files.  Please check your file preferences.");
        }
        if (!files[g].exists()) {
            // The user doesn't have this genome - yet...
            // If the user has lost network connection or is using a custom genome
            // this can generate errors which we don't want to put up a crash reporter
            // for.  We therefore disable the crash reporter in our progress dialog and
            // we'll have custom code in our exceptionReceived method to handle these
            // cases nicely.
            // This variable is only used for error messages
            genomeToLoad = speciesStrings[g] + " " + assemblyStrings[g];
            GenomeDownloader d = new GenomeDownloader();
            d.addProgressListener(this);
            ProgressDialog pd = new ProgressDialog(application, "Downloading genome...");
            pd.setIgnoreExceptions(true);
            d.addProgressListener(pd);
            // Bit of a hack here, since we don't know the size of the genome
            // being downloaded we have to put an approximate value in so the
            // progress bar does something sensible.
            d.downloadGenome(speciesStrings[g], assemblyStrings[g], 25000000, true);
            pd.requestFocus();
            pauseWhilstLoadingGenome = true;
            while (pauseWhilstLoadingGenome) {
                if (exceptionReceived != null)
                    throw exceptionReceived;
                // This sleep *has* to be left in place.  If it doesn't then this thread gets
                // deadlocked and the flag is never reset once the new genome is downloaded
                // and the processing of the downloaded genome never starts.
                Thread.sleep(200);
            }
            if (exceptionReceived != null) {
                // Do we need to say we cancelled?
                return;
            }
        }
    }
    GenomeParser parser = new GenomeParser();
    parser.addProgressListener(this);
    parser.parseGenome(files);
    while (!genomeLoaded) {
        if (exceptionReceived != null)
            throw exceptionReceived;
        try {
            Thread.sleep(1000);
        } catch (InterruptedException ie) {
        }
    }
}

Example 12 with SeqMonkException

use of uk.ac.babraham.SeqMonk.SeqMonkException in project SeqMonk by s-andrews.

the class SeqMonkParser method parseDisplayPreferences.

/**
 * Parses the display preferences.
 *
 * @param sections The tab split initial display preferences line
 * @throws SeqMonkException
 * @throws IOException Signals that an I/O exception has occurred.
 */
private void parseDisplayPreferences(String[] sections) throws SeqMonkException, IOException {
    int linesToParse;
    try {
        linesToParse = Integer.parseInt(sections[1]);
    } catch (Exception e) {
        throw new SeqMonkException("Couldn't see the number of display preference lines to parse");
    }
    String[] prefs;
    for (int i = 0; i < linesToParse; i++) {
        prefs = br.readLine().split("\\t");
        if (prefs[0].equals("DataZoom")) {
            DisplayPreferences.getInstance().setMaxDataValue(Double.parseDouble(prefs[1]));
        } else if (prefs[0].equals("ScaleMode")) {
            DisplayPreferences.getInstance().setScaleType(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("DisplayMode")) {
            DisplayPreferences.getInstance().setDisplayMode(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("ReplicateExpansion")) {
            DisplayPreferences.getInstance().setReplicateSetExpansion(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("Variation")) {
            DisplayPreferences.getInstance().setVariation(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("CurrentView")) {
            DisplayPreferences.getInstance().setLocation(application.dataCollection().genome().getChromosome(prefs[1]).chromosome(), SequenceRead.packPosition(Integer.parseInt(prefs[2]), Integer.parseInt(prefs[3]), Location.UNKNOWN));
        } else if (prefs[0].equals("ReadDensity")) {
            DisplayPreferences.getInstance().setReadDensity(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("SplitMode")) {
            DisplayPreferences.getInstance().setReadDisplay(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("QuantitationColour")) {
            DisplayPreferences.getInstance().setColourType(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("Gradient")) {
            DisplayPreferences.getInstance().setGradient(Integer.parseInt(prefs[1]));
        } else if (prefs[0].equals("InvertGradient")) {
            if (prefs[1].equals("1")) {
                DisplayPreferences.getInstance().setInvertGradient(true);
            } else {
                DisplayPreferences.getInstance().setInvertGradient(false);
            }
        } else if (prefs[0].equals("GraphType")) {
            DisplayPreferences.getInstance().setGraphType(Integer.parseInt(prefs[1]));
        } else {
            throw new SeqMonkException("Didn't know how to process display preference '" + prefs[0] + "'");
        }
    }
}

Example 13 with SeqMonkException

use of uk.ac.babraham.SeqMonk.SeqMonkException in project SeqMonk by s-andrews.

the class VisibleStoresParser method processHiCDataStore.

private DataSet processHiCDataStore(DataStore store) throws SeqMonkException {
    int extendBy = prefs.extendReads();
    boolean reverse = prefs.reverseReads();
    boolean removeStrand = prefs.removeStrandInfo();
    PairedDataSet newData = new PairedDataSet(store.name() + "_reimport", "Reimported from " + store.name(), prefs.removeDuplicates(), prefs.hiCDistance(), prefs.hiCIgnoreTrans());
    // Now process the data
    Chromosome[] chrs = dataCollection().genome().getAllChromosomes();
    for (int c = 0; c < chrs.length; c++) {
        progressUpdated("Processing " + store.name() + " chr " + chrs[c].name(), c, chrs.length);
        // We make the call to get exportable reads so we don't duplicate reads
        // when we export things
        HiCHitCollection hitCollection = ((HiCDataStore) store).getExportableReadsForChromosome(chrs[c]);
        String[] localChromosomes = hitCollection.getChromosomeNamesWithHits();
        for (int c2 = 0; c2 < localChromosomes.length; c2++) {
            Chromosome localChromosome = SeqMonkApplication.getInstance().dataCollection().genome().getChromosome(localChromosomes[c2]).chromosome();
            long[] sourceReads = hitCollection.getSourcePositionsForChromosome(localChromosomes[c2]);
            long[] hitReads = hitCollection.getHitPositionsForChromosome(localChromosomes[c2]);
            for (int r = 0; r < sourceReads.length; r++) {
                if (cancel) {
                    progressCancelled();
                    return null;
                }
                if (downsample && downsampleProbabilty < 1) {
                    if (Math.random() > downsampleProbabilty) {
                        continue;
                    }
                }
                if ((!(reverse || removeStrand)) && extendBy == 0 && (!filterByFeature)) {
                    // Just add them as they are
                    newData.addData(chrs[c], sourceReads[r]);
                    newData.addData(localChromosome, hitReads[r]);
                }
                Feature[] features = null;
                if (filterByFeature) {
                    features = collection.genome().annotationCollection().getFeaturesForType(chrs[c], featureType);
                    Arrays.sort(features);
                }
                int currentFeaturePostion = 0;
                if (filterByFeature) {
                    // See if we're comparing against the right feature
                    while (SequenceRead.start(sourceReads[r]) > features[currentFeaturePostion].location().end() && currentFeaturePostion < (features.length - 1)) {
                        currentFeaturePostion++;
                    }
                    // Test to see if we overlap
                    if (SequenceRead.overlaps(sourceReads[r], features[currentFeaturePostion].location().packedPosition())) {
                        if (excludeFeature)
                            continue;
                    } else {
                        if (!excludeFeature)
                            continue;
                    }
                }
                int sourceStart = SequenceRead.start(sourceReads[r]);
                int sourceEend = SequenceRead.end(sourceReads[r]);
                int sourceStrand = SequenceRead.strand(sourceReads[r]);
                int hitStart = SequenceRead.start(sourceReads[r]);
                int hitEend = SequenceRead.end(hitReads[r]);
                int hitStrand = SequenceRead.strand(hitReads[r]);
                if (reverse) {
                    if (sourceStrand == Location.FORWARD) {
                        sourceStrand = Location.REVERSE;
                    } else if (sourceStrand == Location.REVERSE) {
                        sourceStrand = Location.FORWARD;
                    }
                    if (hitStrand == Location.FORWARD) {
                        hitStrand = Location.REVERSE;
                    } else if (hitStrand == Location.REVERSE) {
                        hitStrand = Location.FORWARD;
                    }
                }
                if (removeStrand) {
                    sourceStrand = Location.UNKNOWN;
                    hitStrand = Location.UNKNOWN;
                }
                if (extendBy > 0) {
                    if (sourceStrand == Location.FORWARD) {
                        sourceEend += extendBy;
                    } else if (sourceStrand == Location.REVERSE) {
                        sourceStart -= extendBy;
                    }
                    if (hitStrand == Location.FORWARD) {
                        hitEend += extendBy;
                    } else if (hitStrand == Location.REVERSE) {
                        hitStart -= extendBy;
                    }
                }
                // We also don't allow readings which are beyond the end of the chromosome
                if (sourceEend > chrs[c].length()) {
                    int overrun = sourceEend - chrs[c].length();
                    progressWarningReceived(new SeqMonkException("Reading position " + sourceEend + " was " + overrun + "bp beyond the end of chr" + chrs[c].name() + " (" + chrs[c].length() + ")"));
                    continue;
                }
                if (hitEend > localChromosome.length()) {
                    int overrun = hitEend - SeqMonkApplication.getInstance().dataCollection().genome().getChromosome(localChromosomes[c2]).chromosome().length();
                    progressWarningReceived(new SeqMonkException("Reading position " + hitEend + " was " + overrun + "bp beyond the end of chr" + localChromosome.name() + " (" + chrs[c].length() + ")"));
                    continue;
                }
                // We can now make the new readings
                long sourceRead = SequenceRead.packPosition(sourceStart, sourceEend, sourceStrand);
                long hitRead = SequenceRead.packPosition(hitStart, hitEend, hitStrand);
                if (!prefs.isHiC()) {
                    // HiC additions are deferred until we know the other end is OK too.
                    newData.addData(chrs[c], sourceRead);
                    newData.addData(localChromosome, hitRead);
                }
            }
        }
    }
    return newData;
}

Example 14 with SeqMonkException

use of uk.ac.babraham.SeqMonk.SeqMonkException in project SeqMonk by s-andrews.

the class BAMFileParser method getPairedEndRead.

/**
 * Gets a paired end read.  This method assumes that it will only be passed reads which map
 * to the reverse strand since these are the ones which contain enough information to
 * unambiguously locate both ends of the pair.
 *
 * @param sections The tab split sections from the SAM file
 * @param flag The binary flag field
 * @return The read which was read
 * @throws SeqMonkException
 */
private SequenceReadWithChromosome getPairedEndRead(SAMRecord samRecord) throws SeqMonkException {
    int strand;
    int start;
    int end;
    if (!samRecord.getReadNegativeStrandFlag()) {
        throw new SeqMonkException("Read passed to parse pair was not on the negative strand");
    }
    if (samRecord.getMateNegativeStrandFlag()) {
        throw new SeqMonkException("Ignored discordantly stranded read pair");
    }
    end = samRecord.getAlignmentEnd();
    start = samRecord.getMateAlignmentStart();
    if (start > end) {
        throw new SeqMonkException("Ignored discordantly stranded read pair");
    }
    if (samRecord.getFirstOfPairFlag()) {
        strand = Location.REVERSE;
    } else {
        strand = Location.FORWARD;
    }
    if ((end - start) + 1 > pairedEndDistance) {
        throw new SeqMonkException("Distance between ends " + ((end - start) + 1) + " was larger than cutoff (" + pairedEndDistance + ")");
    }
    ChromosomeWithOffset c;
    try {
        c = dataCollection().genome().getChromosome(samRecord.getReferenceName());
    } catch (Exception e) {
        throw new SeqMonkException(e.getLocalizedMessage());
    }
    start = c.position(start);
    end = c.position(end);
    // We also don't allow readings which are beyond the end of the chromosome
    if (end > c.chromosome().length()) {
        int overrun = end - c.chromosome().length();
        throw new SeqMonkException("Reading position " + end + " was " + overrun + "bp beyond the end of chr" + c.chromosome().name() + " (" + c.chromosome().length() + ")");
    }
    if (start < 1) {
        throw new SeqMonkException("Reading position " + start + " was before the start of chr" + c.chromosome().name() + " (" + c.chromosome().length() + ")");
    }
    // We can now make the new reading
    SequenceReadWithChromosome read = new SequenceReadWithChromosome(c.chromosome(), SequenceRead.packPosition(start, end, strand));
    return read;
}

Example 15 with SeqMonkException

use of uk.ac.babraham.SeqMonk.SeqMonkException in project SeqMonk by s-andrews.

the class BedPEFileParser method run.

/* (non-Javadoc)
	 * @see java.lang.Runnable#run()
	 */
public void run() {
    // System.err.println("Started parsing BED files");
    int extendBy = prefs.extendReads();
    try {
        File[] probeFiles = getFiles();
        DataSet[] newData = new DataSet[probeFiles.length];
        for (int f = 0; f < probeFiles.length; f++) {
            BufferedReader br;
            if (probeFiles[f].getName().toLowerCase().endsWith(".gz")) {
                br = new BufferedReader(new InputStreamReader(new GZIPInputStream(new FileInputStream(probeFiles[f]))));
            } else {
                br = new BufferedReader(new FileReader(probeFiles[f]));
            }
            String line;
            if (prefs.isHiC()) {
                newData[f] = new PairedDataSet(probeFiles[f].getName(), probeFiles[f].getCanonicalPath(), prefs.removeDuplicates(), prefs.hiCDistance(), prefs.hiCIgnoreTrans());
            } else {
                newData[f] = new DataSet(probeFiles[f].getName(), probeFiles[f].getCanonicalPath(), prefs.removeDuplicates());
            }
            int lineCount = 0;
            // Now process the file
            while ((line = br.readLine()) != null) {
                if (cancel) {
                    br.close();
                    progressCancelled();
                    return;
                }
                // Ignore blank lines
                if (line.trim().length() == 0)
                    continue;
                // System.err.println(line);
                // Thread.sleep(200);
                ++lineCount;
                if (lineCount % 100000 == 0) {
                    progressUpdated("Read " + lineCount + " lines from " + probeFiles[f].getName(), f, probeFiles.length);
                }
                String[] sections = line.split("\t");
                // Check to see if we've got enough data to work with
                if (sections.length < 6) {
                    progressWarningReceived(new SeqMonkException("Not enough data from line '" + line + "'"));
                    // Skip this line...
                    continue;
                }
                // move on quickly.
                if (sections[0].equals(".") || sections[3].equals("."))
                    continue;
                int strand1;
                int start1;
                int end1;
                int strand2;
                int start2;
                int end2;
                try {
                    // The start is zero indexed so we need to add 1 to get genomic positions
                    start1 = Integer.parseInt(sections[1]) + 1;
                    start2 = Integer.parseInt(sections[4]) + 1;
                    // The end is zero indexed, but not included in the feature position so
                    // we need to add one to get genomic coordinates, but subtract one to not
                    // include the final base.
                    end1 = Integer.parseInt(sections[2]);
                    end2 = Integer.parseInt(sections[5]);
                    // End must always be later than start
                    if (start1 > end1) {
                        progressWarningReceived(new SeqMonkException("End position1 " + end1 + " was lower than start position " + start1));
                        int temp = start1;
                        start1 = end1;
                        end1 = temp;
                    }
                    if (start2 > end2) {
                        progressWarningReceived(new SeqMonkException("End position2 " + end2 + " was lower than start position " + start2));
                        int temp = start2;
                        start2 = end2;
                        end2 = temp;
                    }
                    if (sections.length >= 10) {
                        if (sections[8].equals("+")) {
                            strand1 = Location.FORWARD;
                        } else if (sections[8].equals("-")) {
                            strand1 = Location.REVERSE;
                        } else if (sections[8].equals(".")) {
                            strand1 = Location.UNKNOWN;
                        } else {
                            progressWarningReceived(new SeqMonkException("Unknown strand character '" + sections[8] + "' marked as unknown strand"));
                            strand1 = Location.UNKNOWN;
                        }
                        if (sections[9].equals("+")) {
                            strand2 = Location.FORWARD;
                        } else if (sections[9].equals("-")) {
                            strand2 = Location.REVERSE;
                        } else if (sections[9].equals(".")) {
                            strand2 = Location.UNKNOWN;
                        } else {
                            progressWarningReceived(new SeqMonkException("Unknown strand character '" + sections[9] + "' marked as unknown strand"));
                            strand2 = Location.UNKNOWN;
                        }
                    // if (extendBy > 0) {
                    // if (strand==Location.REVERSE) {
                    // start -=extendBy;
                    // }
                    // else if (strand==Location.FORWARD) {
                    // end+=extendBy;
                    // }
                    // }
                    } else {
                        strand1 = Location.UNKNOWN;
                        strand2 = Location.UNKNOWN;
                    }
                } catch (NumberFormatException e) {
                    progressWarningReceived(new SeqMonkException("Location " + sections[0] + "-" + sections[1] + " was not an integer"));
                    continue;
                }
                try {
                    ChromosomeWithOffset c1 = dataCollection().genome().getChromosome(sections[0]);
                    // We also don't allow readings which are beyond the end of the chromosome
                    start1 = c1.position(start1);
                    end1 = c1.position(end1);
                    if (end1 > c1.chromosome().length()) {
                        int overrun = end1 - c1.chromosome().length();
                        progressWarningReceived(new SeqMonkException("Reading position " + end1 + " was " + overrun + "bp beyond the end of chr" + c1.chromosome().name() + " (" + c1.chromosome().length() + ")"));
                        continue;
                    }
                    ChromosomeWithOffset c2 = dataCollection().genome().getChromosome(sections[3]);
                    // We also don't allow readings which are beyond the end of the chromosome
                    start2 = c2.position(start2);
                    end2 = c2.position(end2);
                    if (end2 > c2.chromosome().length()) {
                        int overrun = end2 - c2.chromosome().length();
                        progressWarningReceived(new SeqMonkException("Reading position " + end2 + " was " + overrun + "bp beyond the end of chr" + c2.chromosome().name() + " (" + c2.chromosome().length() + ")"));
                        continue;
                    }
                    // add them.  There's nothing clever to do.
                    if (prefs.isHiC()) {
                        long read1 = SequenceRead.packPosition(start1, end1, strand1);
                        newData[f].addData(c1.chromosome(), read1);
                        long read2 = SequenceRead.packPosition(start2, end2, strand2);
                        newData[f].addData(c2.chromosome(), read2);
                    } else {
                        // If they're on different chromosomes then we kick them out
                        if (!c1.chromosome().name().equals(c2.chromosome().name())) {
                            progressWarningReceived(new SeqMonkException("Paried reads were on different chromosomes - discarding"));
                            continue;
                        }
                        if (strand1 == Location.FORWARD && strand2 != Location.REVERSE) {
                            progressWarningReceived(new SeqMonkException("Invalid strand orientation - discarding"));
                            continue;
                        }
                        if (strand1 == Location.REVERSE && strand2 != Location.FORWARD) {
                            progressWarningReceived(new SeqMonkException("Invalid strand orientation - discarding"));
                            continue;
                        }
                        // If they're too far apart we kick them out
                        int start = 1;
                        int end = 0;
                        // We take the strand from read1
                        int strand = strand1;
                        if (strand == Location.FORWARD) {
                            start = start1;
                            end = end2;
                        } else if (strand == Location.REVERSE) {
                            start = start2;
                            end = end1;
                        } else if (strand == Location.UNKNOWN) {
                            start = Math.min(start1, start2);
                            end = Math.max(end1, end2);
                        }
                        if (end <= start) {
                            progressWarningReceived(new SeqMonkException("Incorrectly oriented reads - discarding"));
                            continue;
                        }
                        if ((end - start) + 1 > prefs.pairDistanceCutoff()) {
                            progressWarningReceived(new SeqMonkException("Distance between reads too great (" + (((end - start) + 1) - prefs.pairDistanceCutoff()) + ")"));
                            continue;
                        }
                        long read = SequenceRead.packPosition(start, end, strand);
                        newData[f].addData(c1.chromosome(), read);
                    }
                } catch (IllegalArgumentException iae) {
                    progressWarningReceived(iae);
                } catch (SeqMonkException sme) {
                    progressWarningReceived(sme);
                    continue;
                }
            }
            // We're finished with the file.
            br.close();
            // Cache the data in the new dataset
            progressUpdated("Caching data from " + probeFiles[f].getName(), f, probeFiles.length);
            newData[f].finalise();
        }
        processingFinished(newData);
    } catch (Exception ex) {
        progressExceptionReceived(ex);
        return;
    }
}