zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

My parallel version of TranscriptToInfo now emits 'chr start end' instead of 'chr:start-end' for records so that 1) they can be easily sorted in coordinate order (allowing me to emit records out of order if I choose) and 2) the file can be tabix indexed (when we stop finding 'critical' bugs in that code). 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@4218 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
ebanks 2010-09-07 05:20:40 +00:00
parent fe2a0bb3a6
commit 5d0d9c7dce
4 changed files with 84 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
java/src/org/broadinstitute/sting/gatk/refdata/features/annotator/AnnotatorInputTableCodec.java
View File

@ -29,6 +29,7 @@ import java.io.File;
import java.io.FileInputStream; import java.io.FileInputStream;
import java.io.IOException; import java.io.IOException;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.StringTokenizer;
import org.apache.log4j.Logger; import org.apache.log4j.Logger;
import org.broad.tribble.Feature; import org.broad.tribble.Feature;
@ -72,12 +73,17 @@ public class AnnotatorInputTableCodec implements FeatureCodec<AnnotatorInputTabl
@Override @Override
public Feature decodeLoc(String line) { public Feature decodeLoc(String line) {
int tabIndex = line.indexOf(DELIMITER); StringTokenizer st = new StringTokenizer(line, DELIMITER);
if(tabIndex <= 0) { if ( st.countTokens() < 1 )
throw new CodecLineParsingException("Couldn't parse GenomeLoc out the following line because line.indexOf(DELIMITER) returned " + tabIndex + ".\nLine: " + line); throw new CodecLineParsingException("Couldn't parse GenomeLoc out of the following line because there aren't enough tokens.\nLine: " + line);
}
GenomeLoc loc = GenomeLocParser.parseGenomeLoc(line.substring(0, tabIndex)); GenomeLoc loc;
return new AnnotatorInputTableFeature(loc.getContig(), (int) loc.getStart(), (int) loc.getStop()); String chr = st.nextToken();
if ( chr.indexOf(":") != -1 )
loc = GenomeLocParser.parseGenomeInterval(chr);
else
loc = GenomeLocParser.createGenomeLoc(chr, Integer.valueOf(st.nextToken()), Integer.valueOf(st.nextToken()));
return new AnnotatorInputTableFeature(loc.getContig(), (int)loc.getStart(), (int)loc.getStop());
} }
@ -99,18 +105,20 @@ public class AnnotatorInputTableCodec implements FeatureCodec<AnnotatorInputTabl
feature.putColumnValue(header.get(i), values.get(i)); feature.putColumnValue(header.get(i), values.get(i));
} }
final GenomeLoc loc = GenomeLocParser.parseGenomeLoc(values.get(0)); //GenomeLocParser.parseGenomeInterval(values.get(0)); - TODO switch to this GenomeLoc loc;
if ( values.get(0).indexOf(":") != -1 )
loc = GenomeLocParser.parseGenomeInterval(values.get(0));
else
loc = GenomeLocParser.createGenomeLoc(values.get(0), Integer.valueOf(values.get(1)), Integer.valueOf(values.get(2)));
//parse the location //parse the location
feature.setChr(loc.getContig()); feature.setChr(loc.getContig());
feature.setStart((int) loc.getStart()); feature.setStart((int)loc.getStart());
feature.setEnd((int) loc.getStop()); feature.setEnd((int)loc.getStop());
return feature; return feature;
} }
/** /**
* Returns the header. * Returns the header.
* @param source * @param source

4
java/src/org/broadinstitute/sting/gatk/walkers/annotator/genomicannotator/GenomicAnnotation.java
View File

@ -51,7 +51,9 @@ import org.broadinstitute.sting.utils.StingException;
*/ */
public class GenomicAnnotation implements InfoFieldAnnotation { public class GenomicAnnotation implements InfoFieldAnnotation {
public static final String CHRPOS_COLUMN = "chrpos"; public static final String CHR_COLUMN = "chr";
public static final String START_COLUMN = "start";
public static final String END_COLUMN = "end";
public static final String HAPLOTYPE_REFERENCE_COLUMN = "haplotypeReference"; public static final String HAPLOTYPE_REFERENCE_COLUMN = "haplotypeReference";
public static final String HAPLOTYPE_ALTERNATE_COLUMN = "haplotypeAlternate"; public static final String HAPLOTYPE_ALTERNATE_COLUMN = "haplotypeAlternate";
public static final String HAPLOTYPE_STRAND_COLUMN = "haplotypeStrand"; public static final String HAPLOTYPE_STRAND_COLUMN = "haplotypeStrand";

124
java/src/org/broadinstitute/sting/gatk/walkers/annotator/genomicannotator/TranscriptToGenomicInfo.java
View File

@ -82,34 +82,47 @@ public class TranscriptToGenomicInfo extends RodWalker<Integer, Integer> impleme
private final char[] ALLELES = {'A','C','G','T'}; private final char[] ALLELES = {'A','C','G','T'};
/** Output columns */ /** Output columns */
private final String OUTPUT_CHRPOS = GenomicAnnotation.CHRPOS_COLUMN; private static final String[] GENOMIC_ANNOTATION_COLUMNS = {
private final String OUTPUT_HAPLOTYPE_REFERENCE = GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN; GenomicAnnotation.CHR_COLUMN,
private final String OUTPUT_HAPLOTYPE_ALTERNATE = GenomicAnnotation.HAPLOTYPE_ALTERNATE_COLUMN; GenomicAnnotation.START_COLUMN,
private final String OUTPUT_HAPLOTYPE_STRAND = GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN; GenomicAnnotation.END_COLUMN,
GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN,
GenomicAnnotation.HAPLOTYPE_ALTERNATE_COLUMN,
GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN };
private final String OUTPUT_IN_CODING_REGION = "inCodingRegion"; //eg. true private static final String OUTPUT_IN_CODING_REGION = "inCodingRegion"; //eg. true
private static final String OUTPUT_FRAME = "frame"; //eg. 0,1,2
private final String OUTPUT_FRAME = "frame"; //eg. 0,1,2 private static final String OUTPUT_POSITION_TYPE = "positionType"; //eg. utr5, cds, utr3, intron, intergenic
private final String OUTPUT_POSITION_TYPE = "positionType"; //eg. utr5, cds, utr3, intron, intergenic private static final String OUTPUT_MRNA_COORD = "mrnaCoord"; //1-based offset within the transcript
private static final String OUTPUT_SPLICE_DISTANCE = "spliceDist"; //eg. integer, bp to nearest exon/intron boundary
private final String OUTPUT_MRNA_COORD = "mrnaCoord"; //1-based offset within the transcript private static final String OUTPUT_CODON_NUMBER = "codonCoord"; //eg. 20
private static final String OUTPUT_REFERENCE_CODON = "referenceCodon";
private final String OUTPUT_SPLICE_DISTANCE = "spliceDist"; //eg. integer, bp to nearest exon/intron boundary private static final String OUTPUT_REFERENCE_AA = "referenceAA";
private static final String OUTPUT_VARIANT_CODON = "variantCodon";
private final String OUTPUT_CODON_NUMBER = "codonCoord"; //eg. 20 private static final String OUTPUT_VARIANT_AA = "variantAA";
private final String OUTPUT_REFERENCE_CODON = "referenceCodon"; private static final String OUTPUT_CHANGES_AMINO_ACID = "changesAA"; //eg. true
private final String OUTPUT_REFERENCE_AA = "referenceAA"; private static final String OUTPUT_FUNCTIONAL_CLASS = "functionalClass"; //eg. missense
private final String OUTPUT_VARIANT_CODON = "variantCodon"; private static final String OUTPUT_CODING_COORD_STR = "codingCoordStr";
private final String OUTPUT_VARIANT_AA = "variantAA"; private static final String OUTPUT_PROTEIN_COORD_STR = "proteinCoordStr";
private static final String OUTPUT_SPLICE_INFO = "spliceInfo"; //(eg "splice-donor -4", or "splice-acceptor 3") for the 10bp surrounding each exon/intron boundary
private final String OUTPUT_CHANGES_AMINO_ACID = "changesAA"; //eg. true private static final String OUTPUT_UORF_CHANGE = "uorfChange"; // (eg +1 or -1, indicating the addition or interruption of an ATG trinucleotide in the annotated utr5)
private final String OUTPUT_FUNCTIONAL_CLASS = "functionalClass"; //eg. missense private static final String[] TRANSCRIPT_COLUMNS = {
OUTPUT_POSITION_TYPE,
private final String OUTPUT_CODING_COORD_STR = "codingCoordStr"; OUTPUT_FRAME,
private final String OUTPUT_PROTEIN_COORD_STR = "proteinCoordStr"; OUTPUT_MRNA_COORD,
OUTPUT_CODON_NUMBER,
private final String OUTPUT_SPLICE_INFO = "spliceInfo"; //(eg "splice-donor -4", or "splice-acceptor 3") for the 10bp surrounding each exon/intron boundary OUTPUT_SPLICE_DISTANCE,
private final String OUTPUT_UORF_CHANGE = "uorfChange"; // (eg +1 or -1, indicating the addition or interruption of an ATG trinucleotide in the annotated utr5) OUTPUT_REFERENCE_CODON,
OUTPUT_REFERENCE_AA,
OUTPUT_VARIANT_CODON,
OUTPUT_VARIANT_AA,
OUTPUT_CHANGES_AMINO_ACID,
OUTPUT_FUNCTIONAL_CLASS,
OUTPUT_CODING_COORD_STR,
OUTPUT_PROTEIN_COORD_STR,
OUTPUT_IN_CODING_REGION,
OUTPUT_SPLICE_INFO,
OUTPUT_UORF_CHANGE };
//This list specifies the order of output columns in the big table. //This list specifies the order of output columns in the big table.
private final List<String> outputColumnNames = new LinkedList<String>(); private final List<String> outputColumnNames = new LinkedList<String>();
@ -150,6 +163,10 @@ public class TranscriptToGenomicInfo extends RodWalker<Integer, Integer> impleme
} }
} }
// sanity check
if ( transcriptsDataSource == null )
throw new IllegalStateException("No rod bound to " + ROD_NAME + " found in rod sources");
final ArrayList<String> header; final ArrayList<String> header;
try { try {
header = AnnotatorInputTableCodec.readHeader(transcriptsDataSource.getReferenceOrderedData().getFile()); header = AnnotatorInputTableCodec.readHeader(transcriptsDataSource.getReferenceOrderedData().getFile());
@ -157,37 +174,15 @@ public class TranscriptToGenomicInfo extends RodWalker<Integer, Integer> impleme
throw new StingException("Failed when attempting to read header from file: " + transcriptsDataSource.getReferenceOrderedData().getFile(), e); throw new StingException("Failed when attempting to read header from file: " + transcriptsDataSource.getReferenceOrderedData().getFile(), e);
} }
for(String columnName : GENE_NAME_COLUMNS) { for ( String columnName : GENE_NAME_COLUMNS ) {
if(!header.contains(columnName)) { if ( !header.contains(columnName) )
throw new StingException("The column name '" + columnName + "' provided to -n doesn't match any of the column names in: " + transcriptsDataSource.getReferenceOrderedData().getFile()); throw new StingException("The column name '" + columnName + "' provided to -n doesn't match any of the column names in: " + transcriptsDataSource.getReferenceOrderedData().getFile());
}
} }
//init outputColumnNames list //init outputColumnNames list
outputColumnNames.addAll( Arrays.asList(new String[] { OUTPUT_CHRPOS,OUTPUT_HAPLOTYPE_REFERENCE,OUTPUT_HAPLOTYPE_ALTERNATE,OUTPUT_HAPLOTYPE_STRAND,}) ); outputColumnNames.addAll(Arrays.asList(GENOMIC_ANNOTATION_COLUMNS));
outputColumnNames.addAll( Arrays.asList(GENE_NAME_COLUMNS) ); outputColumnNames.addAll(Arrays.asList(GENE_NAME_COLUMNS));
outputColumnNames.addAll( Arrays.asList(new String[] { outputColumnNames.addAll(Arrays.asList(TRANSCRIPT_COLUMNS));
OUTPUT_POSITION_TYPE,
OUTPUT_FRAME,
OUTPUT_MRNA_COORD,
OUTPUT_CODON_NUMBER,
OUTPUT_SPLICE_DISTANCE,
OUTPUT_REFERENCE_CODON,
OUTPUT_REFERENCE_AA,
OUTPUT_VARIANT_CODON,
OUTPUT_VARIANT_AA,
OUTPUT_CHANGES_AMINO_ACID,
OUTPUT_FUNCTIONAL_CLASS,
OUTPUT_CODING_COORD_STR,
OUTPUT_PROTEIN_COORD_STR,
OUTPUT_IN_CODING_REGION,
OUTPUT_SPLICE_INFO,
OUTPUT_UORF_CHANGE,
}) );
//init OUTPUT_HEADER_LINE //init OUTPUT_HEADER_LINE
StringBuilder outputHeaderLine = new StringBuilder(); StringBuilder outputHeaderLine = new StringBuilder();
@ -459,15 +454,16 @@ public class TranscriptToGenomicInfo extends RodWalker<Integer, Integer> impleme
final int intronStart = (intronStart_5prime < intronEnd_5prime ? intronStart_5prime : intronEnd_5prime) ; final int intronStart = (intronStart_5prime < intronEnd_5prime ? intronStart_5prime : intronEnd_5prime) ;
final int intronEnd = (intronEnd_5prime > intronStart_5prime ? intronEnd_5prime : intronStart_5prime); final int intronEnd = (intronEnd_5prime > intronStart_5prime ? intronEnd_5prime : intronStart_5prime);
outputLineFields.clear(); outputLineFields.clear();
outputLineFields.put(OUTPUT_CHRPOS, parsedTranscriptRod.txChrom + ":" + intronStart + "-" + intronEnd); outputLineFields.put(GenomicAnnotation.CHR_COLUMN, parsedTranscriptRod.txChrom);
outputLineFields.put(OUTPUT_HAPLOTYPE_REFERENCE, Character.toString( '*' ) ); outputLineFields.put(GenomicAnnotation.START_COLUMN, String.valueOf(intronStart));
outputLineFields.put(OUTPUT_HAPLOTYPE_ALTERNATE, Character.toString( '*' ) ); outputLineFields.put(GenomicAnnotation.END_COLUMN, String.valueOf(intronEnd));
outputLineFields.put(OUTPUT_HAPLOTYPE_STRAND, positiveStrand ? "+" : "-"); outputLineFields.put(GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN, Character.toString( '*' ) );
outputLineFields.put(GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN, Character.toString( '*' ) );
outputLineFields.put(GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN, positiveStrand ? "+" : "-");
for(int i = 0; i < GENE_NAME_COLUMNS.length; i++) { for(int i = 0; i < GENE_NAME_COLUMNS.length; i++) {
outputLineFields.put(GENE_NAME_COLUMNS[i], parsedTranscriptRod.geneNames[i] ); outputLineFields.put(GENE_NAME_COLUMNS[i], parsedTranscriptRod.geneNames[i] );
} }
outputLineFields.put(OUTPUT_POSITION_TYPE, positionType.toString() ); outputLineFields.put(OUTPUT_POSITION_TYPE, positionType.toString() );
if ( isProteinCodingTranscript ) if ( isProteinCodingTranscript )
@ -566,10 +562,12 @@ public class TranscriptToGenomicInfo extends RodWalker<Integer, Integer> impleme
} }
//compute simple OUTPUT fields. //compute simple OUTPUT fields.
outputLineFields.put(OUTPUT_CHRPOS, parsedTranscriptRod.txChrom + ":" + txCoord_5to3); outputLineFields.put(GenomicAnnotation.CHR_COLUMN, parsedTranscriptRod.txChrom);
outputLineFields.put(OUTPUT_HAPLOTYPE_REFERENCE, Character.toString( haplotypeReference ) ); outputLineFields.put(GenomicAnnotation.START_COLUMN, String.valueOf(txCoord_5to3));
outputLineFields.put(OUTPUT_HAPLOTYPE_ALTERNATE, Character.toString( haplotypeAlternate ) ); outputLineFields.put(GenomicAnnotation.END_COLUMN, String.valueOf(txCoord_5to3));
outputLineFields.put(OUTPUT_HAPLOTYPE_STRAND, positiveStrand ? "+" : "-"); outputLineFields.put(GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN, Character.toString( haplotypeReference ) );
outputLineFields.put(GenomicAnnotation.HAPLOTYPE_ALTERNATE_COLUMN, Character.toString( haplotypeAlternate ) );
outputLineFields.put(GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN, positiveStrand ? "+" : "-");
for(int i = 0; i < GENE_NAME_COLUMNS.length; i++) { for(int i = 0; i < GENE_NAME_COLUMNS.length; i++) {
outputLineFields.put(GENE_NAME_COLUMNS[i], parsedTranscriptRod.geneNames[i] ); outputLineFields.put(GENE_NAME_COLUMNS[i], parsedTranscriptRod.geneNames[i] );
} }

2
java/src/org/broadinstitute/sting/gatk/walkers/annotator/genomicannotator/TranscriptToInfo.java
View File

@ -92,7 +92,7 @@ public class TranscriptToInfo extends RodWalker<TreeMap<String, String>, TreeMap
private final char[] ALLELES = {'A','C','G','T'}; private final char[] ALLELES = {'A','C','G','T'};
/** Output columns */ /** Output columns */
private final String OUTPUT_CHRPOS = GenomicAnnotation.CHRPOS_COLUMN; private final String OUTPUT_CHRPOS = "chrpos";
private final String OUTPUT_HAPLOTYPE_REFERENCE = GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN; private final String OUTPUT_HAPLOTYPE_REFERENCE = GenomicAnnotation.HAPLOTYPE_REFERENCE_COLUMN;
private final String OUTPUT_HAPLOTYPE_ALTERNATE = GenomicAnnotation.HAPLOTYPE_ALTERNATE_COLUMN; private final String OUTPUT_HAPLOTYPE_ALTERNATE = GenomicAnnotation.HAPLOTYPE_ALTERNATE_COLUMN;
private final String OUTPUT_HAPLOTYPE_STRAND = GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN; private final String OUTPUT_HAPLOTYPE_STRAND = GenomicAnnotation.HAPLOTYPE_STRAND_COLUMN;