Examples with BioSequence ubic.gemma.model.genome.biosequence.BioSequence used on opensource projects

Example 86 with BioSequence

use of ubic.gemma.model.genome.biosequence.BioSequence in project Gemma by PavlidisLab.

the class NcbiGeneConverter method getChromosomeDetails.

private void getChromosomeDetails(NCBIGene2Accession acc, Gene gene) {
    Chromosome chrom = gene.getPhysicalLocation().getChromosome();
    BioSequence chromSeq = BioSequence.Factory.newInstance();
    chromSeq.setName(acc.getGenomicNucleotideAccession());
    chromSeq.setType(SequenceType.WHOLE_CHROMOSOME);
    chromSeq.setTaxon(gene.getTaxon());
    DatabaseEntry dbe = DatabaseEntry.Factory.newInstance();
    dbe.setExternalDatabase(NcbiGeneConverter.genBank);
    dbe.setAccession(acc.getGenomicNucleotideAccession());
    dbe.setAccessionVersion(acc.getGenomicNucleotideAccessionVersion());
    chromSeq.setSequenceDatabaseEntry(dbe);
    try {
        FieldUtils.writeField(chrom, "sequence", chromSeq, true);
    } catch (IllegalAccessException e) {
        e.printStackTrace();
    }
}

Example 87 with BioSequence

use of ubic.gemma.model.genome.biosequence.BioSequence in project Gemma by PavlidisLab.

the class FastaParser method parseOneRecord.

@Override
public Object parseOneRecord(String record) {
    if (StringUtils.isBlank(record))
        return null;
    Matcher matcher = pattern.matcher(record);
    Collection<BioSequence> bioSequences = this.parseHeader(matcher);
    if (bioSequences.size() == 0) {
        return null;
    }
    StringBuilder sequence = new StringBuilder();
    while (matcher.find()) {
        // skip comments.
        if (matcher.group(1).startsWith(";"))
            continue;
        sequence.append(matcher.group(1));
    }
    if (sequence.length() == 0) {
        return null;
    }
    for (BioSequence bioSequence : bioSequences) {
        bioSequence.setLength((long) sequence.length());
        bioSequence.setIsApproximateLength(false);
        bioSequence.setSequence(sequence.toString());
    }
    return bioSequences;
}

Example 88 with BioSequence

use of ubic.gemma.model.genome.biosequence.BioSequence in project Gemma by PavlidisLab.

the class SimpleFastaCmd method getSequencesFromFastaCmdOutput.

private Collection<BioSequence> getSequencesFromFastaCmdOutput(Process pr) throws IOException {
    try (final InputStream is = new BufferedInputStream(pr.getInputStream());
        InputStream err = pr.getErrorStream()) {
        final FastaParser parser = new FastaParser();
        ParsingStreamConsumer<BioSequence> sg = new ParsingStreamConsumer<>(parser, is);
        GenericStreamConsumer gsc = new GenericStreamConsumer(err);
        sg.start();
        gsc.start();
        try {
            int exitVal = pr.waitFor();
            // Makes sure results are flushed.
            Thread.sleep(200);
            SimpleFastaCmd.log.debug(// often nonzero if some sequences are not found.
            "fastacmd exit value=" + exitVal);
            return parser.getResults();
        } catch (InterruptedException e) {
            throw new RuntimeException(e);
        }
    }
}

Example 89 with BioSequence

use of ubic.gemma.model.genome.biosequence.BioSequence in project Gemma by PavlidisLab.

the class ProbeSequenceParser method parse.

@Override
public void parse(InputStream is) throws IOException {
    if (is == null)
        throw new IllegalArgumentException("InputStream was null");
    try (BufferedReader br = new BufferedReader(new InputStreamReader(is))) {
        StopWatch timer = new StopWatch();
        timer.start();
        int nullLines = 0;
        String line;
        int linesParsed = 0;
        while ((line = br.readLine()) != null) {
            BioSequence newItem = this.parseOneLine(line);
            if (++linesParsed % Parser.PARSE_ALERT_FREQUENCY == 0 && timer.getTime() > LineParser.PARSE_ALERT_TIME_FREQUENCY_MS) {
                String message = "Parsed " + linesParsed + " lines ";
                log.info(message);
                timer.reset();
                timer.start();
            }
            if (newItem == null) {
                nullLines++;
            }
        }
        log.info("Parsed " + linesParsed + " lines. " + (nullLines > 0 ? nullLines + " yielded no parse result (they may have been filtered)." : ""));
    }
}

Example 90 with BioSequence

use of ubic.gemma.model.genome.biosequence.BioSequence in project Gemma by PavlidisLab.

the class ArrayDesignPersister method persistArrayDesignCompositeSequenceAssociations.

private ArrayDesign persistArrayDesignCompositeSequenceAssociations(ArrayDesign arrayDesign) {
    int numElements = arrayDesign.getCompositeSequences().size();
    if (numElements == 0)
        return arrayDesign;
    AbstractPersister.log.info("Filling in or updating sequences in composite seqences for " + arrayDesign);
    int persistedBioSequences = 0;
    int numElementsPerUpdate = this.numElementsPerUpdate(arrayDesign.getCompositeSequences());
    for (CompositeSequence compositeSequence : arrayDesign.getCompositeSequences()) {
        if (!this.isTransient(compositeSequence)) {
            // in case of retry (not used?)
            continue;
        }
        compositeSequence.setId(null);
        compositeSequence.setArrayDesign(arrayDesign);
        BioSequence biologicalCharacteristic = compositeSequence.getBiologicalCharacteristic();
        BioSequence persistedBs = this.persistBioSequence(biologicalCharacteristic);
        compositeSequence.setBiologicalCharacteristic(persistedBs);
        if (++persistedBioSequences % numElementsPerUpdate == 0 && numElements > 1000) {
            AbstractPersister.log.info(persistedBioSequences + "/" + numElements + " compositeSequence sequences examined for " + arrayDesign);
        }
    }
    if (persistedBioSequences > 0) {
        AbstractPersister.log.info("Total of " + persistedBioSequences + " compositeSequence sequences examined for " + arrayDesign);
    }
    return arrayDesign;
}