OverlapDetector<Gene> load() {
final OverlapDetector<Gene> overlapDetector = new OverlapDetector<Gene>(0, 0);
final int expectedColumns = RefFlatColumns.values().length;
final TabbedTextFileWithHeaderParser parser =
new TabbedTextFileWithHeaderParser(refFlatFile, RefFlatColumnLabels);
final Map<String, List<TabbedTextFileWithHeaderParser.Row>> refFlatLinesByGene =
new HashMap<String, List<TabbedTextFileWithHeaderParser.Row>>();
for (final TabbedTextFileWithHeaderParser.Row row : parser) {
final int lineNumber =
parser.getCurrentLineNumber(); // getCurrentLineNumber returns the number of the next line
if (row.getFields().length != expectedColumns) {
throw new AnnotationException(
"Wrong number of fields in refFlat file " + refFlatFile + " at line " + lineNumber);
}
final String geneName = row.getField(RefFlatColumns.GENE_NAME.name());
final String transcriptName = row.getField(RefFlatColumns.TRANSCRIPT_NAME.name());
final String transcriptDescription = geneName + ":" + transcriptName;
final String chromosome = row.getField(RefFlatColumns.CHROMOSOME.name());
if (!isSequenceRecognized(chromosome)) {
LOG.debug(
"Skipping " + transcriptDescription + " due to unrecognized sequence " + chromosome);
} else {
List<TabbedTextFileWithHeaderParser.Row> transcriptLines = refFlatLinesByGene.get(geneName);
if (transcriptLines == null) {
transcriptLines = new ArrayList<TabbedTextFileWithHeaderParser.Row>();
refFlatLinesByGene.put(geneName, transcriptLines);
}
transcriptLines.add(row);
}
}
int longestInterval = 0;
int numIntervalsOver1MB = 0;
for (final List<TabbedTextFileWithHeaderParser.Row> transcriptLines :
refFlatLinesByGene.values()) {
try {
final Gene gene = makeGeneFromRefFlatLines(transcriptLines);
overlapDetector.addLhs(gene, gene);
if (gene.length() > longestInterval) longestInterval = gene.length();
if (gene.length() > 1000000) ++numIntervalsOver1MB;
} catch (AnnotationException e) {
LOG.debug(e.getMessage() + " -- skipping");
}
}
LOG.debug(
"Longest gene: " + longestInterval + "; number of genes > 1MB: " + numIntervalsOver1MB);
return overlapDetector;
}
private Gene makeGeneFromRefFlatLines(
final List<TabbedTextFileWithHeaderParser.Row> transcriptLines) {
final String geneName = transcriptLines.get(0).getField(RefFlatColumns.GENE_NAME.name());
final String strandStr = transcriptLines.get(0).getField(RefFlatColumns.STRAND.name());
final boolean negative = strandStr.equals("-");
final String chromosome = transcriptLines.get(0).getField(RefFlatColumns.CHROMOSOME.name());
// Figure out the extend of the gene
int start = Integer.MAX_VALUE;
int end = Integer.MIN_VALUE;
for (final TabbedTextFileWithHeaderParser.Row row : transcriptLines) {
start = Math.min(start, row.getIntegerField(RefFlatColumns.TX_START.name()) + 1);
end = Math.max(end, row.getIntegerField(RefFlatColumns.TX_END.name()));
}
final Gene gene = new Gene(chromosome, start, end, negative, geneName);
for (final TabbedTextFileWithHeaderParser.Row row : transcriptLines) {
if (!strandStr.equals(row.getField(RefFlatColumns.STRAND.name()))) {
throw new AnnotationException("Strand disagreement in refFlat file for gene " + geneName);
}
if (!chromosome.equals(row.getField(RefFlatColumns.CHROMOSOME.name()))) {
throw new AnnotationException(
"Chromosome disagreement("
+ chromosome
+ " != "
+ row.getField(RefFlatColumns.CHROMOSOME.name())
+ ") in refFlat file for gene "
+ geneName);
}
// This adds it to the Gene also
final Transcript tx = makeTranscriptFromRefFlatLine(gene, row);
}
return gene;
}