Example 1 with VDJCObject
use of com.milaboratory.mixcr.basictypes.VDJCObject in project mixcr by milaboratory.
the class FieldExtractors method getFields.
public static synchronized Field[] getFields() {
if (descriptors == null) {
List<Field> descriptorsList = new ArrayList<>();
// Number of targets
descriptorsList.add(new PL_O("-targets", "Export number of targets", "Number of targets", "numberOfTargets") {
@Override
protected String extract(VDJCObject object) {
return Integer.toString(object.numberOfTargets());
}
});
// Best hits
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Hit", "Export best " + l + " hit", "Best " + l + " hit", "best" + l + "Hit") {
@Override
protected String extract(VDJCObject object) {
VDJCHit bestHit = object.getBestHit(type);
if (bestHit == null)
return NULL;
return bestHit.getGene().getName();
}
});
}
// Best gene
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Gene", "Export best " + l + " hit gene name (e.g. TRBV12-3 for TRBV12-3*00)", "Best " + l + " gene", "best" + l + "Gene") {
@Override
protected String extract(VDJCObject object) {
VDJCHit bestHit = object.getBestHit(type);
if (bestHit == null)
return NULL;
return bestHit.getGene().getGeneName();
}
});
}
// Best family
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Family", "Export best " + l + " hit family name (e.g. TRBV12 for TRBV12-3*00)", "Best " + l + " family", "best" + l + "Family") {
@Override
protected String extract(VDJCObject object) {
VDJCHit bestHit = object.getBestHit(type);
if (bestHit == null)
return NULL;
return bestHit.getGene().getFamilyName();
}
});
}
// Best hit score
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "HitScore", "Export score for best " + l + " hit", "Best " + l + " hit score", "best" + l + "HitScore") {
@Override
protected String extract(VDJCObject object) {
VDJCHit bestHit = object.getBestHit(type);
if (bestHit == null)
return NULL;
return String.valueOf(bestHit.getScore());
}
});
}
// All hits
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "HitsWithScore", "Export all " + l + " hits with score", "All " + l + " hits", "all" + l + "HitsWithScore") {
@Override
protected String extract(VDJCObject object) {
VDJCHit[] hits = object.getHits(type);
if (hits.length == 0)
return "";
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
sb.append(hits[i].getGene().getName()).append("(").append(SCORE_FORMAT.format(hits[i].getScore())).append(")");
if (i == hits.length - 1)
break;
sb.append(",");
}
return sb.toString();
}
});
}
// All hits without score
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Hits", "Export all " + l + " hits", "All " + l + " Hits", "all" + l + "Hits") {
@Override
protected String extract(VDJCObject object) {
VDJCHit[] hits = object.getHits(type);
if (hits.length == 0)
return "";
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
sb.append(hits[i].getGene().getName());
if (i == hits.length - 1)
break;
sb.append(",");
}
return sb.toString();
}
});
}
// All gene names
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new StringExtractor("-" + Character.toLowerCase(l) + "Genes", "Export all " + l + " gene names (e.g. TRBV12-3 for TRBV12-3*00)", "All " + l + " genes", "all" + l + "Genes", type) {
@Override
String extractStringForHit(VDJCHit hit) {
return hit.getGene().getGeneName();
}
});
}
// All families
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new StringExtractor("-" + Character.toLowerCase(l) + "Families", "Export all " + l + " gene family anmes (e.g. TRBV12 for TRBV12-3*00)", "All " + l + " families", "all" + l + "Families", type) {
@Override
String extractStringForHit(VDJCHit hit) {
return hit.getGene().getFamilyName();
}
});
}
// Best alignment
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Alignment", "Export best " + l + " alignment", "Best " + l + " alignment", "best" + l + "Alignment") {
@Override
protected String extract(VDJCObject object) {
VDJCHit bestHit = object.getBestHit(type);
if (bestHit == null)
return NULL;
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
Alignment<NucleotideSequence> alignment = bestHit.getAlignment(i);
if (alignment == null)
sb.append(NULL);
else
sb.append(alignment.toCompactString());
if (i == object.numberOfTargets() - 1)
break;
sb.append(",");
}
return sb.toString();
}
});
}
// All alignments
for (final GeneType type : GeneType.values()) {
char l = type.getLetter();
descriptorsList.add(new PL_O("-" + Character.toLowerCase(l) + "Alignments", "Export all " + l + " alignments", "All " + l + " alignments", "all" + l + "Alignments") {
@Override
protected String extract(VDJCObject object) {
VDJCHit[] hits = object.getHits(type);
if (hits.length == 0)
return "";
StringBuilder sb = new StringBuilder();
for (int j = 0; ; ++j) {
for (int i = 0; ; i++) {
Alignment<NucleotideSequence> alignment = hits[j].getAlignment(i);
if (alignment == null)
sb.append(NULL);
else
sb.append(alignment.toCompactString());
if (i == object.numberOfTargets() - 1)
break;
sb.append(',');
}
if (j == hits.length - 1)
break;
sb.append(';');
}
return sb.toString();
}
});
}
descriptorsList.add(new FeatureExtractors.NSeqExtractor("-nFeature", "Export nucleotide sequence of specified gene feature", "N. Seq. ", "nSeq") {
@Override
public String convert(NSequenceWithQuality seq) {
return seq.getSequence().toString();
}
});
descriptorsList.add(new FeatureExtractors.NSeqExtractor("-qFeature", "Export quality string of specified gene feature", "Qual. ", "qual") {
@Override
public String convert(NSequenceWithQuality seq) {
return seq.getQuality().toString();
}
});
descriptorsList.add(new FeatureExtractors.WithHeader("-aaFeature", "Export amino acid sequence of specified gene feature", 1, new String[] { "AA. Seq. " }, new String[] { "aaSeq" }) {
@Override
protected String extractValue(VDJCObject object, GeneFeature[] parameters) {
GeneFeature geneFeature = parameters[parameters.length - 1];
NSequenceWithQuality feature = object.getFeature(geneFeature);
if (feature == null)
return NULL;
int targetId = object.getTargetContainingFeature(geneFeature);
TranslationParameters tr = targetId == -1 ? TranslationParameters.FromLeftWithIncompleteCodon : object.getPartitionedTarget(targetId).getPartitioning().getTranslationParameters(geneFeature);
if (tr == null)
return NULL;
return AminoAcidSequence.translate(feature.getSequence(), tr).toString();
}
});
// descriptorsList.add(new FeatureExtractorDescriptor("-aaFeatureFromLeft", "Export amino acid sequence of " +
// "specified gene feature starting from the leftmost nucleotide (differs from -aaFeature only for " +
// "sequences which length are not multiple of 3)", "AA. Seq.", "aaSeq") {
// @Override
// public String convert(NSequenceWithQuality seq) {
// return AminoAcidSequence.translate(seq.getSequence(), FromLeftWithoutIncompleteCodon).toString();
// }
// });
//
// descriptorsList.add(new FeatureExtractorDescriptor("-aaFeatureFromRight", "Export amino acid sequence of " +
// "specified gene feature starting from the rightmost nucleotide (differs from -aaFeature only for " +
// "sequences which length are not multiple of 3)", "AA. Seq.", "aaSeq") {
// @Override
// public String convert(NSequenceWithQuality seq) {
// return AminoAcidSequence.translate(seq.getSequence(), FromRightWithoutIncompleteCodon).toString();
// }
// });
descriptorsList.add(new FeatureExtractors.NSeqExtractor("-minFeatureQuality", "Export minimal quality of specified gene feature", "Min. qual. ", "minQual") {
@Override
public String convert(NSequenceWithQuality seq) {
return "" + seq.getQuality().minValue();
}
});
descriptorsList.add(new FeatureExtractors.NSeqExtractor("-avrgFeatureQuality", "Export average quality of specified gene feature", "Mean. qual. ", "meanQual") {
@Override
public String convert(NSequenceWithQuality seq) {
return "" + seq.getQuality().meanValue();
}
});
descriptorsList.add(new FeatureExtractors.NSeqExtractor("-lengthOf", "Exports length of specified gene feature.", "Length of ", "lengthOf") {
@Override
public String convert(NSequenceWithQuality seq) {
return "" + seq.size();
}
});
descriptorsList.add(new FeatureExtractors.MutationsExtractor("-nMutations", "Extract nucleotide mutations for specific gene feature; relative to germline sequence.", 1, new String[] { "N. Mutations in " }, new String[] { "nMutations" }) {
@Override
String convert(Mutations<NucleotideSequence> mutations, NucleotideSequence seq1, NucleotideSequence seq2, TranslationParameters tr) {
return mutations.encode(",");
}
});
descriptorsList.add(new FeatureExtractors.MutationsExtractor("-nMutationsRelative", "Extract nucleotide mutations for specific gene feature relative to another feature.", 2, new String[] { "N. Mutations in ", " relative to " }, new String[] { "nMutationsIn", "Relative" }) {
@Override
String convert(Mutations<NucleotideSequence> mutations, NucleotideSequence seq1, NucleotideSequence seq2, TranslationParameters tr) {
return mutations.encode(",");
}
});
final class AAMutations extends FeatureExtractors.MutationsExtractor {
AAMutations(String command, String description, int nArgs, String[] hPrefix, String[] sPrefix) {
super(command, description, nArgs, hPrefix, sPrefix);
}
@Override
String convert(Mutations<NucleotideSequence> mutations, NucleotideSequence seq1, NucleotideSequence seq2, TranslationParameters tr) {
if (tr == null)
return "-";
Mutations<AminoAcidSequence> aaMuts = MutationsUtil.nt2aa(seq1, mutations, tr);
if (aaMuts == null)
return "-";
return aaMuts.encode(",");
}
}
descriptorsList.add(new AAMutations("-aaMutations", "Extract amino acid mutations for specific gene feature", 1, new String[] { "AA. Mutations in " }, new String[] { "aaMutations" }));
descriptorsList.add(new AAMutations("-aaMutationsRelative", "Extract amino acid mutations for specific gene feature relative to another feature.", 2, new String[] { "AA. Mutations in ", " relative to " }, new String[] { "aaMutationsIn", "Relative" }));
final class MutationsDetailed extends FeatureExtractors.MutationsExtractor {
MutationsDetailed(String command, String description, int nArgs, String[] hPrefix, String[] sPrefix) {
super(command, description, nArgs, hPrefix, sPrefix);
}
@Override
String convert(Mutations<NucleotideSequence> mutations, NucleotideSequence seq1, NucleotideSequence seq2, TranslationParameters tr) {
if (tr == null)
return "-";
MutationsUtil.MutationNt2AADescriptor[] descriptors = MutationsUtil.nt2aaDetailed(seq1, mutations, tr, 10);
if (descriptors == null)
return "-";
StringBuilder sb = new StringBuilder();
for (int i = 0; i < descriptors.length; i++) {
sb.append(descriptors[i]);
if (i == descriptors.length - 1)
break;
sb.append(",");
}
return sb.toString();
}
}
String detailedMutationsFormat = "Format <nt_mutation>:<aa_mutation_individual>:<aa_mutation_cumulative>, where <aa_mutation_individual> is an expected amino acid " + "mutation given no other mutations have occurred, and <aa_mutation_cumulative> amino acid mutation is the observed amino acid " + "mutation combining effect from all other. WARNING: format may change in following versions.";
descriptorsList.add(new MutationsDetailed("-mutationsDetailed", "Detailed list of nucleotide and corresponding amino acid mutations. " + detailedMutationsFormat, 1, new String[] { "Detailed mutations in " }, new String[] { "mutationsDetailedIn" }));
descriptorsList.add(new MutationsDetailed("-mutationsDetailedRelative", "Detailed list of nucleotide and corresponding amino acid mutations written, positions relative to specified gene feature. " + detailedMutationsFormat, 2, new String[] { "Detailed mutations in ", " relative to " }, new String[] { "mutationsDetailedIn", "Relative" }));
descriptorsList.add(new ExtractReferencePointPosition());
descriptorsList.add(new ExtractDefaultReferencePointsPositions());
descriptorsList.add(new PL_A("-readId", "Export id of read corresponding to alignment", "Read id", "readId") {
@Override
protected String extract(VDJCAlignments object) {
return "" + object.getMinReadId();
}
@Override
public FieldExtractor<VDJCAlignments> create(OutputMode outputMode, String[] args) {
System.out.println("WARNING: -readId is deprecated. Use -readIds");
return super.create(outputMode, args);
}
});
descriptorsList.add(new PL_A("-readIds", "Export id of read corresponding to alignment", "Read id", "readId") {
@Override
protected String extract(VDJCAlignments object) {
long[] readIds = object.getReadIds();
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
sb.append(readIds[i]);
if (i == readIds.length - 1)
return sb.toString();
sb.append(",");
}
}
});
descriptorsList.add(new ExtractSequence(VDJCAlignments.class, "-sequence", "Export aligned sequence (initial read), or 2 sequences in case of paired-end reads", "Read(s) sequence", "readSequence"));
descriptorsList.add(new ExtractSequenceQuality(VDJCAlignments.class, "-quality", "Export initial read quality, or 2 qualities in case of paired-end reads", "Read(s) sequence qualities", "readQuality"));
descriptorsList.add(new PL_C("-cloneId", "Unique clone identifier", "Clone ID", "cloneId") {
@Override
protected String extract(Clone object) {
return "" + object.getId();
}
});
descriptorsList.add(new PL_C("-count", "Export clone count", "Clone count", "cloneCount") {
@Override
protected String extract(Clone object) {
return "" + object.getCount();
}
});
descriptorsList.add(new PL_C("-fraction", "Export clone fraction", "Clone fraction", "cloneFraction") {
@Override
protected String extract(Clone object) {
return "" + object.getFraction();
}
});
descriptorsList.add(new ExtractSequence(Clone.class, "-sequence", "Export aligned sequence (initial read), or 2 sequences in case of paired-end reads", "Clonal sequence(s)", "clonalSequence"));
descriptorsList.add(new ExtractSequenceQuality(Clone.class, "-quality", "Export initial read quality, or 2 qualities in case of paired-end reads", "Clonal sequence quality(s)", "clonalSequenceQuality"));
descriptorsList.add(new PL_A("-descrR1", "Export description line from initial .fasta or .fastq file " + "of the first read (only available if --save-description was used in align command)", "Description R1", "descrR1") {
@Override
protected String extract(VDJCAlignments object) {
List<SequenceRead> reads = object.getOriginalReads();
if (reads == null)
throw new IllegalArgumentException("Error for option \'-descrR1\':\n" + "No description available for read: either re-run align action with -OsaveOriginalReads=true option " + "or don't use \'-descrR1\' in exportAlignments");
return reads.get(0).getRead(0).getDescription();
}
@Override
public FieldExtractor<VDJCAlignments> create(OutputMode outputMode, String[] args) {
System.out.println("WARNING: -descrR1 is deprecated. Use -descrsR1");
return super.create(outputMode, args);
}
});
descriptorsList.add(new PL_A("-descrR2", "Export description line from initial .fasta or .fastq file " + "of the second read (only available if --save-description was used in align command)", "Description R2", "descrR2") {
@Override
protected String extract(VDJCAlignments object) {
List<SequenceRead> reads = object.getOriginalReads();
if (reads == null)
throw new IllegalArgumentException("Error for option \'-descrR1\':\n" + "No description available for read: either re-run align action with -OsaveOriginalReads=true option " + "or don't use \'-descrR1\' in exportAlignments");
SequenceRead read = reads.get(0);
if (read.numberOfReads() < 2)
throw new IllegalArgumentException("Error for option \'-descrR2\':\n" + "No description available for second read: your input data was single-end");
return read.getRead(1).getDescription();
}
@Override
public FieldExtractor<VDJCAlignments> create(OutputMode outputMode, String[] args) {
System.out.println("WARNING: -descrR2 is deprecated. Use -descrsR2");
return super.create(outputMode, args);
}
});
descriptorsList.add(new PL_A("-descrsR1", "Export description lines from initial .fasta or .fastq file " + "of the first reads (only available if -OsaveOriginalReads=true was used in align command)", "Descriptions R1", "descrsR1") {
@Override
protected String extract(VDJCAlignments object) {
List<SequenceRead> reads = object.getOriginalReads();
if (reads == null)
throw new IllegalArgumentException("Error for option \'-descrR1\':\n" + "No description available for read: either re-run align action with -OsaveOriginalReads option " + "or don't use \'-descrR1\' in exportAlignments");
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
sb.append(reads.get(i).getRead(0).getDescription());
if (i == reads.size() - 1)
return sb.toString();
sb.append(",");
}
}
});
descriptorsList.add(new PL_A("-descrsR2", "Export description lines from initial .fasta or .fastq file " + "of the second reads (only available if -OsaveOriginalReads=true was used in align command)", "Descriptions R2", "descrsR2") {
@Override
protected String extract(VDJCAlignments object) {
List<SequenceRead> reads = object.getOriginalReads();
if (reads == null)
throw new IllegalArgumentException("Error for option \'-descrR1\':\n" + "No description available for read: either re-run align action with -OsaveOriginalReads option " + "or don't use \'-descrR1\' in exportAlignments");
StringBuilder sb = new StringBuilder();
for (int i = 0; ; i++) {
SequenceRead read = reads.get(i);
if (read.numberOfReads() < 2)
throw new IllegalArgumentException("Error for option \'-descrsR2\':\n" + "No description available for second read: your input data was single-end");
sb.append(read.getRead(1).getDescription());
if (i == reads.size() - 1)
return sb.toString();
sb.append(",");
}
}
});
descriptorsList.add(new PL_A("-readHistory", "Export read history", "Read history", "readHistory") {
@Override
protected String extract(VDJCAlignments object) {
try {
return GlobalObjectMappers.toOneLine(object.getHistory());
} catch (JsonProcessingException ex) {
throw new RuntimeException(ex);
}
}
});
for (final GeneType type : GeneType.values()) {
String c = Character.toLowerCase(type.getLetter()) + "IdentityPercents";
descriptorsList.add(new PL_O("-" + c, type.getLetter() + " alignment identity percents", type.getLetter() + " alignment identity percents", c) {
@Override
protected String extract(VDJCObject object) {
VDJCHit[] hits = object.getHits(type);
if (hits == null)
return NULL;
StringBuilder sb = new StringBuilder();
sb.append("");
for (int i = 0; ; i++) {
sb.append(hits[i].getIdentity());
if (i == hits.length - 1)
return sb.toString();
sb.append(",");
}
}
});
}
for (final GeneType type : GeneType.values()) {
String c = Character.toLowerCase(type.getLetter()) + "BestIdentityPercent";
descriptorsList.add(new PL_O("-" + c, type.getLetter() + "best alignment identity percent", type.getLetter() + "best alignment identity percent", c) {
@Override
protected String extract(VDJCObject object) {
VDJCHit hit = object.getBestHit(type);
if (hit == null)
return NULL;
return Float.toString(hit.getIdentity());
}
});
}
descriptorsList.add(new PL_O("-chains", "Chains", "Chains", "Chains") {
@Override
protected String extract(VDJCObject object) {
return object.commonChains().toString();
}
});
descriptorsList.add(new PL_O("-topChains", "Top chains", "Top chains", "topChains") {
@Override
protected String extract(VDJCObject object) {
return object.commonTopChains().toString();
}
});
descriptors = descriptorsList.toArray(new Field[descriptorsList.size()]);
}
return descriptors;
}
Also used :
GeneFeature(io.repseq.core.GeneFeature)
ArrayList(java.util.ArrayList)
VDJCObject(com.milaboratory.mixcr.basictypes.VDJCObject)
Alignment(com.milaboratory.core.alignment.Alignment)
AminoAcidSequence(com.milaboratory.core.sequence.AminoAcidSequence)
NSequenceWithQuality(com.milaboratory.core.sequence.NSequenceWithQuality)
ArrayList(java.util.ArrayList)
List(java.util.List)
VDJCAlignments(com.milaboratory.mixcr.basictypes.VDJCAlignments)
JsonProcessingException(com.fasterxml.jackson.core.JsonProcessingException)
Clone(com.milaboratory.mixcr.basictypes.Clone)
Mutations(com.milaboratory.core.mutations.Mutations)
ReferencePoint(io.repseq.core.ReferencePoint)
TranslationParameters(com.milaboratory.core.sequence.TranslationParameters)
NucleotideSequence(com.milaboratory.core.sequence.NucleotideSequence)
SequenceRead(com.milaboratory.core.io.sequence.SequenceRead)
GeneType(io.repseq.core.GeneType)
VDJCHit(com.milaboratory.mixcr.basictypes.VDJCHit)
Aggregations
JsonProcessingException (com.fasterxml.jackson.core.JsonProcessingException)1
Alignment (com.milaboratory.core.alignment.Alignment)1
SequenceRead (com.milaboratory.core.io.sequence.SequenceRead)1
Mutations (com.milaboratory.core.mutations.Mutations)1
AminoAcidSequence (com.milaboratory.core.sequence.AminoAcidSequence)1
NSequenceWithQuality (com.milaboratory.core.sequence.NSequenceWithQuality)1
NucleotideSequence (com.milaboratory.core.sequence.NucleotideSequence)1
TranslationParameters (com.milaboratory.core.sequence.TranslationParameters)1
Clone (com.milaboratory.mixcr.basictypes.Clone)1
VDJCAlignments (com.milaboratory.mixcr.basictypes.VDJCAlignments)1
VDJCHit (com.milaboratory.mixcr.basictypes.VDJCHit)1
VDJCObject (com.milaboratory.mixcr.basictypes.VDJCObject)1
GeneFeature (io.repseq.core.GeneFeature)1
GeneType (io.repseq.core.GeneType)1
ReferencePoint (io.repseq.core.ReferencePoint)1
ArrayList (java.util.ArrayList)1
List (java.util.List)1
