- * This tool will generate reduced versions of the BAM files that still follow the BAM specification - * and contain all the information necessary to call variants according to the GATK Best Practices recommendations. - * Some options allow you to tune how much compression you want to achieve. The default values have been - * shown to reduce a typical whole exome BAM file by 100x. The higher the coverage, the bigger the - * savings in file size and performance of the downstream tools. - * - *
- * The BAM file to be compressed - *
- * - *- * The compressed (reduced) BAM file. - * - *
- *- * java -Xmx4g -jar GenomeAnalysisTK.jar \ - * -R ref.fasta \ - * -T ReduceReads \ - * -I myData.bam \ - * -o myData.reduced.bam - *- */ - -@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_DATA, extraDocs = {CommandLineGATK.class} ) -@PartitionBy(PartitionType.CONTIG) -@ReadFilters({UnmappedReadFilter.class, NotPrimaryAlignmentFilter.class, DuplicateReadFilter.class, FailsVendorQualityCheckFilter.class, BadCigarFilter.class}) -@Downsample(by=DownsampleType.BY_SAMPLE, toCoverage=40) -public class ReduceReads extends ReadWalker
- * The original and reduced BAM files. - *
- * - *- * A list of intervals present in one bam but not the other. - *
- * - *- * java -Xmx2g -jar GenomeAnalysisTK.jar \ - * -I:original original.bam \ - * -I:reduced reduced.bam \ - * -R ref.fasta \ - * -T AssessReducedCoverage \ - * -o output.intervals - *- * - * @author ebanks + * @author Valentin Ruano-Rubio <valentin@broadinstitute.org> */ -@DocumentedGATKFeature( groupName = "Quality Control and Simple Analysis Tools", extraDocs = {CommandLineGATK.class} ) -@ReadFilters({UnmappedReadFilter.class, NotPrimaryAlignmentFilter.class, DuplicateReadFilter.class, FailsVendorQualityCheckFilter.class, BadCigarFilter.class}) -@Hidden -public class AssessReducedCoverage extends LocusWalker
As more results are requested the array will grow. All positions and solutions are + * calculated up to {@code i}
. + */ + private ArrayListTo be used at vertices that do not have any valid path to the requested sink vertices
* - * UnvalidatingGenomeLoc is a simple utility to create GenomeLocs without going through the parser. Should - * only be used outside of the engine. - * - * User: carneiro - * Date: 10/16/12 - * Time: 2:07 PM + * @author Valentin Ruano-Rubio <valentin@broadinstitute.org> */ -public class FinishedGenomeLoc extends UnvalidatingGenomeLoc { - private boolean finished; +final class DeadEndKBestSubHaplotypeFinder implements KBestSubHaplotypeFinder { - public FinishedGenomeLoc(final String contigName, final int contigIndex, final int start, final int stop, final boolean finished) { - super(contigName, contigIndex, start, stop); - this.finished = finished; + /** + * Sole instance of this class. + */ + public static DeadEndKBestSubHaplotypeFinder INSTANCE = new DeadEndKBestSubHaplotypeFinder(); + + /** + * Prevents instantiation of more than one instance; please use {@link #INSTANCE}. + */ + protected DeadEndKBestSubHaplotypeFinder() { } - public FinishedGenomeLoc(final GenomeLoc loc, final boolean finished) { - super(loc.getContig(), loc.getContigIndex(), loc.getStart(), loc.getStop()); - this.finished = finished; + @Override + public int getCount() { + return 0; } - public boolean isFinished() { - return finished; + @Override + public KBestHaplotype getKBest(int k) { + if (k < 0) + throw new IllegalArgumentException("k cannot be negative"); + else + throw new IllegalArgumentException("k cannot be equal or greater to the haplotype count"); } } diff --git a/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/BaseIndex.java b/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/EmptyPathHaplotypeFinder.java similarity index 74% rename from protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/BaseIndex.java rename to protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/EmptyPathHaplotypeFinder.java index 665e3e7ce..0e50ec02b 100644 --- a/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/BaseIndex.java +++ b/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/EmptyPathHaplotypeFinder.java @@ -1,136 +1,147 @@ /* * By downloading the PROGRAM you agree to the following terms of use: -* +* * BROAD INSTITUTE - SOFTWARE LICENSE AGREEMENT - FOR ACADEMIC NON-COMMERCIAL RESEARCH PURPOSES ONLY -* +* * This Agreement is made between the Broad Institute, Inc. with a principal address at 7 Cambridge Center, Cambridge, MA 02142 (BROAD) and the LICENSEE and is effective at the date the downloading is completed (EFFECTIVE DATE). -* +* * WHEREAS, LICENSEE desires to license the PROGRAM, as defined hereinafter, and BROAD wishes to have this PROGRAM utilized in the public interest, subject only to the royalty-free, nonexclusive, nontransferable license rights of the United States Government pursuant to 48 CFR 52.227-14; and * WHEREAS, LICENSEE desires to license the PROGRAM and BROAD desires to grant a license on the following terms and conditions. * NOW, THEREFORE, in consideration of the promises and covenants made herein, the parties hereto agree as follows: -* +* * 1. DEFINITIONS * 1.1 PROGRAM shall mean copyright in the object code and source code known as GATK2 and related documentation, if any, as they exist on the EFFECTIVE DATE and can be downloaded from http://www.broadinstitute/GATK on the EFFECTIVE DATE. -* +* * 2. LICENSE -* 2.1 Grant. Subject to the terms of this Agreement, BROAD hereby grants to LICENSEE, solely for academic non-commercial research purposes, a non-exclusive, non-transferable license to: (a) download, execute and display the PROGRAM and (b) create bug fixes and modify the PROGRAM. +* 2.1 Grant. Subject to the terms of this Agreement, BROAD hereby grants to LICENSEE, solely for academic non-commercial research purposes, a non-exclusive, non-transferable license to: (a) download, execute and display the PROGRAM and (b) create bug fixes and modify the PROGRAM. * The LICENSEE may apply the PROGRAM in a pipeline to data owned by users other than the LICENSEE and provide these users the results of the PROGRAM provided LICENSEE does so for academic non-commercial purposes only. For clarification purposes, academic sponsored research is not a commercial use under the terms of this Agreement. * 2.2 No Sublicensing or Additional Rights. LICENSEE shall not sublicense or distribute the PROGRAM, in whole or in part, without prior written permission from BROAD. LICENSEE shall ensure that all of its users agree to the terms of this Agreement. LICENSEE further agrees that it shall not put the PROGRAM on a network, server, or other similar technology that may be accessed by anyone other than the LICENSEE and its employees and users who have agreed to the terms of this agreement. -* 2.3 License Limitations. Nothing in this Agreement shall be construed to confer any rights upon LICENSEE by implication, estoppel, or otherwise to any computer software, trademark, intellectual property, or patent rights of BROAD, or of any other entity, except as expressly granted herein. LICENSEE agrees that the PROGRAM, in whole or part, shall not be used for any commercial purpose, including without limitation, as the basis of a commercial software or hardware product or to provide services. LICENSEE further agrees that the PROGRAM shall not be copied or otherwise adapted in order to circumvent the need for obtaining a license for use of the PROGRAM. -* -* 3. OWNERSHIP OF INTELLECTUAL PROPERTY +* 2.3 License Limitations. Nothing in this Agreement shall be construed to confer any rights upon LICENSEE by implication, estoppel, or otherwise to any computer software, trademark, intellectual property, or patent rights of BROAD, or of any other entity, except as expressly granted herein. LICENSEE agrees that the PROGRAM, in whole or part, shall not be used for any commercial purpose, including without limitation, as the basis of a commercial software or hardware product or to provide services. LICENSEE further agrees that the PROGRAM shall not be copied or otherwise adapted in order to circumvent the need for obtaining a license for use of the PROGRAM. +* +* 3. OWNERSHIP OF INTELLECTUAL PROPERTY * LICENSEE acknowledges that title to the PROGRAM shall remain with BROAD. The PROGRAM is marked with the following BROAD copyright notice and notice of attribution to contributors. LICENSEE shall retain such notice on all copies. LICENSEE agrees to include appropriate attribution if any results obtained from use of the PROGRAM are included in any publication. * Copyright 2012 Broad Institute, Inc. * Notice of attribution: The GATK2 program was made available through the generosity of Medical and Population Genetics program at the Broad Institute, Inc. * LICENSEE shall not use any trademark or trade name of BROAD, or any variation, adaptation, or abbreviation, of such marks or trade names, or any names of officers, faculty, students, employees, or agents of BROAD except as states above for attribution purposes. -* +* * 4. INDEMNIFICATION * LICENSEE shall indemnify, defend, and hold harmless BROAD, and their respective officers, faculty, students, employees, associated investigators and agents, and their respective successors, heirs and assigns, (Indemnitees), against any liability, damage, loss, or expense (including reasonable attorneys fees and expenses) incurred by or imposed upon any of the Indemnitees in connection with any claims, suits, actions, demands or judgments arising out of any theory of liability (including, without limitation, actions in the form of tort, warranty, or strict liability and regardless of whether such action has any factual basis) pursuant to any right or license granted under this Agreement. -* +* * 5. NO REPRESENTATIONS OR WARRANTIES * THE PROGRAM IS DELIVERED AS IS. BROAD MAKES NO REPRESENTATIONS OR WARRANTIES OF ANY KIND CONCERNING THE PROGRAM OR THE COPYRIGHT, EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NONINFRINGEMENT, OR THE ABSENCE OF LATENT OR OTHER DEFECTS, WHETHER OR NOT DISCOVERABLE. BROAD EXTENDS NO WARRANTIES OF ANY KIND AS TO PROGRAM CONFORMITY WITH WHATEVER USER MANUALS OR OTHER LITERATURE MAY BE ISSUED FROM TIME TO TIME. * IN NO EVENT SHALL BROAD OR ITS RESPECTIVE DIRECTORS, OFFICERS, EMPLOYEES, AFFILIATED INVESTIGATORS AND AFFILIATES BE LIABLE FOR INCIDENTAL OR CONSEQUENTIAL DAMAGES OF ANY KIND, INCLUDING, WITHOUT LIMITATION, ECONOMIC DAMAGES OR INJURY TO PROPERTY AND LOST PROFITS, REGARDLESS OF WHETHER BROAD SHALL BE ADVISED, SHALL HAVE OTHER REASON TO KNOW, OR IN FACT SHALL KNOW OF THE POSSIBILITY OF THE FOREGOING. -* +* * 6. ASSIGNMENT * This Agreement is personal to LICENSEE and any rights or obligations assigned by LICENSEE without the prior written consent of BROAD shall be null and void. -* +* * 7. MISCELLANEOUS * 7.1 Export Control. LICENSEE gives assurance that it will comply with all United States export control laws and regulations controlling the export of the PROGRAM, including, without limitation, all Export Administration Regulations of the United States Department of Commerce. Among other things, these laws and regulations prohibit, or require a license for, the export of certain types of software to specified countries. * 7.2 Termination. LICENSEE shall have the right to terminate this Agreement for any reason upon prior written notice to BROAD. If LICENSEE breaches any provision hereunder, and fails to cure such breach within thirty (30) days, BROAD may terminate this Agreement immediately. Upon termination, LICENSEE shall provide BROAD with written assurance that the original and all copies of the PROGRAM have been destroyed, except that, upon prior written authorization from BROAD, LICENSEE may retain a copy for archive purposes. * 7.3 Survival. The following provisions shall survive the expiration or termination of this Agreement: Articles 1, 3, 4, 5 and Sections 2.2, 2.3, 7.3, and 7.4. -* 7.4 Notice. Any notices under this Agreement shall be in writing, shall specifically refer to this Agreement, and shall be sent by hand, recognized national overnight courier, confirmed facsimile transmission, confirmed electronic mail, or registered or certified mail, postage prepaid, return receipt requested. All notices under this Agreement shall be deemed effective upon receipt. -* 7.5 Amendment and Waiver; Entire Agreement. This Agreement may be amended, supplemented, or otherwise modified only by means of a written instrument signed by all parties. Any waiver of any rights or failure to act in a specific instance shall relate only to such instance and shall not be construed as an agreement to waive any rights or fail to act in any other instance, whether or not similar. This Agreement constitutes the entire agreement among the parties with respect to its subject matter and supersedes prior agreements or understandings between the parties relating to its subject matter. +* 7.4 Notice. Any notices under this Agreement shall be in writing, shall specifically refer to this Agreement, and shall be sent by hand, recognized national overnight courier, confirmed facsimile transmission, confirmed electronic mail, or registered or certified mail, postage prepaid, return receipt requested. All notices under this Agreement shall be deemed effective upon receipt. +* 7.5 Amendment and Waiver; Entire Agreement. This Agreement may be amended, supplemented, or otherwise modified only by means of a written instrument signed by all parties. Any waiver of any rights or failure to act in a specific instance shall relate only to such instance and shall not be construed as an agreement to waive any rights or fail to act in any other instance, whether or not similar. This Agreement constitutes the entire agreement among the parties with respect to its subject matter and supersedes prior agreements or understandings between the parties relating to its subject matter. * 7.6 Binding Effect; Headings. This Agreement shall be binding upon and inure to the benefit of the parties and their respective permitted successors and assigns. All headings are for convenience only and shall not affect the meaning of any provision of this Agreement. * 7.7 Governing Law. This Agreement shall be construed, governed, interpreted and applied in accordance with the internal laws of the Commonwealth of Massachusetts, U.S.A., without regard to conflict of laws principles. */ - -package org.broadinstitute.sting.gatk.walkers.compression.reducereads; - -import org.broadinstitute.sting.utils.exceptions.ReviewedStingException; +package org.broadinstitute.sting.gatk.walkers.haplotypecaller.graphs; /** - * Simple byte / base index conversions + * Trivial k-best sub-haplotype finder where the source and sink vertex are the same one. * - * - * @author carneiro - * @since 8/26/11 + * @author Valentin Ruano-Rubio <valentin@broadinstitute.org> */ -public enum BaseIndex { - A ( 'A', 0 ), - C ( 'C', 1 ), - G ( 'G', 2 ), - T ( 'T', 3 ), - D ( 'D', 4 ), - I ( 'I', 5 ), // insertion to the right of the base - N ( 'N', 6 ); - - final byte b; - final int index; - - public byte getByte() { return b; } +class EmptyPathHaplotypeFinderNode implements KBestSubHaplotypeFinder { /** - * Ordinal is stored in SyntheticRead rather than enum to save object reference, and store as byte for compactness. - * It is stored as byte, and this method merely eliminates a cast. + * Caches the only solution returned by this finder. */ - public byte getOrdinalByte() { return (byte)ordinal(); } + private final KBestHaplotype singleHaplotypePath; - private BaseIndex(char base, int index) { - this.b = (byte)base; - this.index = index; + /** + * Constructs a new empty k-best haplotype finder. + * + * @param graph the search graph. + * @param vertex the source and sink vertex of the only solution returned by this finder. + */ + public EmptyPathHaplotypeFinderNode(final SeqGraph graph, final SeqVertex vertex) { + singleHaplotypePath = new MyBestHaplotypePath(graph,vertex); + } + + @Override + public int getCount() { + return 1; + } + + @Override + public KBestHaplotype getKBest(int k) { + if (k < 0) + throw new IllegalArgumentException("k cannot be negative"); + if (k > 0) + throw new IllegalArgumentException("k cannot greater than the possible haplotype count"); + return singleHaplotypePath; } /** - * Converts a byte representation of a base to BaseIndex - * - * @param base the byte representation of the base - * @return the BaseIndex representation of the base; + * Custom extension of {@link KBestHaplotype} that implements the single solution behaviour. */ - public static BaseIndex byteToBase(final byte base) { - switch (base) { - case 'A': - case 'a': - return A; - case 'C': - case 'c': - return C; - case 'G': - case 'g': - return G; - case 'T': - case 't': - return T; - case 'D': - case 'd': - case '-': - return D; - case 'I': - case 'i': - return I; - case 'N': - case 'n': - return N; - default: throw new ReviewedStingException("Tried to create a byte index for an impossible base " + base); + private class MyBestHaplotypePath extends KBestHaplotype { + + /** + * The solution's only vertex. + */ + private final SeqVertex vertex; + + /** + * The search graph. + */ + private final SeqGraph graph; + + /** + * Whether the vertex is a reference vertex. + * + *Initialize lazily.
+ */ + private Boolean isReference; + + /** + * Constructs a new empty k-best haplotype solution. + * + * @param graph the search graph. + * @param vertex the source and sink vertex of the only solution returned by the outer finder. + */ + public MyBestHaplotypePath(final SeqGraph graph, final SeqVertex vertex) { + this.vertex = vertex; + this.graph = graph; + } + + @Override + public SeqGraph graph() { + return graph; + } + + @Override + public int score() { + return 0; + } + + @Override + public int rank() { + return 0; + } + + @Override + protected SeqVertex head() { + return vertex; + } + + @Override + protected KBestHaplotype tail() { + return null; + } + + @Override + public boolean isReference() { + return (isReference != null) ? isReference: (isReference = graph.isReferenceNode(vertex)); } } - - /** - * Definition of a nucleotide for the BaseIndex is anything that has been read as a base - * by the machine (A,C,G,T), even if it couldn't tell which base it was, but it knows - * there is a base there (N). - * - * @return whether or not it is a nucleotide, given the definition above - */ - public final boolean isNucleotide() { - return !isIndel(); - } - - /** - * Whether or not this base is an insertion or a deletion - * - * @return true for I or D, false otherwise - */ - public final boolean isIndel() { - return this == D || this == I; - } -} +} \ No newline at end of file diff --git a/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/CompressionStash.java b/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/KBestHaplotype.java similarity index 67% rename from protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/CompressionStash.java rename to protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/KBestHaplotype.java index 22ea78521..ca22f17ec 100644 --- a/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/compression/reducereads/CompressionStash.java +++ b/protected/gatk-protected/src/main/java/org/broadinstitute/sting/gatk/walkers/haplotypecaller/graphs/KBestHaplotype.java @@ -1,107 +1,171 @@ /* * By downloading the PROGRAM you agree to the following terms of use: -* +* * BROAD INSTITUTE - SOFTWARE LICENSE AGREEMENT - FOR ACADEMIC NON-COMMERCIAL RESEARCH PURPOSES ONLY -* +* * This Agreement is made between the Broad Institute, Inc. with a principal address at 7 Cambridge Center, Cambridge, MA 02142 (BROAD) and the LICENSEE and is effective at the date the downloading is completed (EFFECTIVE DATE). -* +* * WHEREAS, LICENSEE desires to license the PROGRAM, as defined hereinafter, and BROAD wishes to have this PROGRAM utilized in the public interest, subject only to the royalty-free, nonexclusive, nontransferable license rights of the United States Government pursuant to 48 CFR 52.227-14; and * WHEREAS, LICENSEE desires to license the PROGRAM and BROAD desires to grant a license on the following terms and conditions. * NOW, THEREFORE, in consideration of the promises and covenants made herein, the parties hereto agree as follows: -* +* * 1. DEFINITIONS * 1.1 PROGRAM shall mean copyright in the object code and source code known as GATK2 and related documentation, if any, as they exist on the EFFECTIVE DATE and can be downloaded from http://www.broadinstitute/GATK on the EFFECTIVE DATE. -* +* * 2. LICENSE -* 2.1 Grant. Subject to the terms of this Agreement, BROAD hereby grants to LICENSEE, solely for academic non-commercial research purposes, a non-exclusive, non-transferable license to: (a) download, execute and display the PROGRAM and (b) create bug fixes and modify the PROGRAM. +* 2.1 Grant. Subject to the terms of this Agreement, BROAD hereby grants to LICENSEE, solely for academic non-commercial research purposes, a non-exclusive, non-transferable license to: (a) download, execute and display the PROGRAM and (b) create bug fixes and modify the PROGRAM. * The LICENSEE may apply the PROGRAM in a pipeline to data owned by users other than the LICENSEE and provide these users the results of the PROGRAM provided LICENSEE does so for academic non-commercial purposes only. For clarification purposes, academic sponsored research is not a commercial use under the terms of this Agreement. * 2.2 No Sublicensing or Additional Rights. LICENSEE shall not sublicense or distribute the PROGRAM, in whole or in part, without prior written permission from BROAD. LICENSEE shall ensure that all of its users agree to the terms of this Agreement. LICENSEE further agrees that it shall not put the PROGRAM on a network, server, or other similar technology that may be accessed by anyone other than the LICENSEE and its employees and users who have agreed to the terms of this agreement. -* 2.3 License Limitations. Nothing in this Agreement shall be construed to confer any rights upon LICENSEE by implication, estoppel, or otherwise to any computer software, trademark, intellectual property, or patent rights of BROAD, or of any other entity, except as expressly granted herein. LICENSEE agrees that the PROGRAM, in whole or part, shall not be used for any commercial purpose, including without limitation, as the basis of a commercial software or hardware product or to provide services. LICENSEE further agrees that the PROGRAM shall not be copied or otherwise adapted in order to circumvent the need for obtaining a license for use of the PROGRAM. -* -* 3. OWNERSHIP OF INTELLECTUAL PROPERTY +* 2.3 License Limitations. Nothing in this Agreement shall be construed to confer any rights upon LICENSEE by implication, estoppel, or otherwise to any computer software, trademark, intellectual property, or patent rights of BROAD, or of any other entity, except as expressly granted herein. LICENSEE agrees that the PROGRAM, in whole or part, shall not be used for any commercial purpose, including without limitation, as the basis of a commercial software or hardware product or to provide services. LICENSEE further agrees that the PROGRAM shall not be copied or otherwise adapted in order to circumvent the need for obtaining a license for use of the PROGRAM. +* +* 3. OWNERSHIP OF INTELLECTUAL PROPERTY * LICENSEE acknowledges that title to the PROGRAM shall remain with BROAD. The PROGRAM is marked with the following BROAD copyright notice and notice of attribution to contributors. LICENSEE shall retain such notice on all copies. LICENSEE agrees to include appropriate attribution if any results obtained from use of the PROGRAM are included in any publication. * Copyright 2012 Broad Institute, Inc. * Notice of attribution: The GATK2 program was made available through the generosity of Medical and Population Genetics program at the Broad Institute, Inc. * LICENSEE shall not use any trademark or trade name of BROAD, or any variation, adaptation, or abbreviation, of such marks or trade names, or any names of officers, faculty, students, employees, or agents of BROAD except as states above for attribution purposes. -* +* * 4. INDEMNIFICATION * LICENSEE shall indemnify, defend, and hold harmless BROAD, and their respective officers, faculty, students, employees, associated investigators and agents, and their respective successors, heirs and assigns, (Indemnitees), against any liability, damage, loss, or expense (including reasonable attorneys fees and expenses) incurred by or imposed upon any of the Indemnitees in connection with any claims, suits, actions, demands or judgments arising out of any theory of liability (including, without limitation, actions in the form of tort, warranty, or strict liability and regardless of whether such action has any factual basis) pursuant to any right or license granted under this Agreement. -* +* * 5. NO REPRESENTATIONS OR WARRANTIES * THE PROGRAM IS DELIVERED AS IS. BROAD MAKES NO REPRESENTATIONS OR WARRANTIES OF ANY KIND CONCERNING THE PROGRAM OR THE COPYRIGHT, EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NONINFRINGEMENT, OR THE ABSENCE OF LATENT OR OTHER DEFECTS, WHETHER OR NOT DISCOVERABLE. BROAD EXTENDS NO WARRANTIES OF ANY KIND AS TO PROGRAM CONFORMITY WITH WHATEVER USER MANUALS OR OTHER LITERATURE MAY BE ISSUED FROM TIME TO TIME. * IN NO EVENT SHALL BROAD OR ITS RESPECTIVE DIRECTORS, OFFICERS, EMPLOYEES, AFFILIATED INVESTIGATORS AND AFFILIATES BE LIABLE FOR INCIDENTAL OR CONSEQUENTIAL DAMAGES OF ANY KIND, INCLUDING, WITHOUT LIMITATION, ECONOMIC DAMAGES OR INJURY TO PROPERTY AND LOST PROFITS, REGARDLESS OF WHETHER BROAD SHALL BE ADVISED, SHALL HAVE OTHER REASON TO KNOW, OR IN FACT SHALL KNOW OF THE POSSIBILITY OF THE FOREGOING. -* +* * 6. ASSIGNMENT * This Agreement is personal to LICENSEE and any rights or obligations assigned by LICENSEE without the prior written consent of BROAD shall be null and void. -* +* * 7. MISCELLANEOUS * 7.1 Export Control. LICENSEE gives assurance that it will comply with all United States export control laws and regulations controlling the export of the PROGRAM, including, without limitation, all Export Administration Regulations of the United States Department of Commerce. Among other things, these laws and regulations prohibit, or require a license for, the export of certain types of software to specified countries. * 7.2 Termination. LICENSEE shall have the right to terminate this Agreement for any reason upon prior written notice to BROAD. If LICENSEE breaches any provision hereunder, and fails to cure such breach within thirty (30) days, BROAD may terminate this Agreement immediately. Upon termination, LICENSEE shall provide BROAD with written assurance that the original and all copies of the PROGRAM have been destroyed, except that, upon prior written authorization from BROAD, LICENSEE may retain a copy for archive purposes. * 7.3 Survival. The following provisions shall survive the expiration or termination of this Agreement: Articles 1, 3, 4, 5 and Sections 2.2, 2.3, 7.3, and 7.4. -* 7.4 Notice. Any notices under this Agreement shall be in writing, shall specifically refer to this Agreement, and shall be sent by hand, recognized national overnight courier, confirmed facsimile transmission, confirmed electronic mail, or registered or certified mail, postage prepaid, return receipt requested. All notices under this Agreement shall be deemed effective upon receipt. -* 7.5 Amendment and Waiver; Entire Agreement. This Agreement may be amended, supplemented, or otherwise modified only by means of a written instrument signed by all parties. Any waiver of any rights or failure to act in a specific instance shall relate only to such instance and shall not be construed as an agreement to waive any rights or fail to act in any other instance, whether or not similar. This Agreement constitutes the entire agreement among the parties with respect to its subject matter and supersedes prior agreements or understandings between the parties relating to its subject matter. +* 7.4 Notice. Any notices under this Agreement shall be in writing, shall specifically refer to this Agreement, and shall be sent by hand, recognized national overnight courier, confirmed facsimile transmission, confirmed electronic mail, or registered or certified mail, postage prepaid, return receipt requested. All notices under this Agreement shall be deemed effective upon receipt. +* 7.5 Amendment and Waiver; Entire Agreement. This Agreement may be amended, supplemented, or otherwise modified only by means of a written instrument signed by all parties. Any waiver of any rights or failure to act in a specific instance shall relate only to such instance and shall not be construed as an agreement to waive any rights or fail to act in any other instance, whether or not similar. This Agreement constitutes the entire agreement among the parties with respect to its subject matter and supersedes prior agreements or understandings between the parties relating to its subject matter. * 7.6 Binding Effect; Headings. This Agreement shall be binding upon and inure to the benefit of the parties and their respective permitted successors and assigns. All headings are for convenience only and shall not affect the meaning of any provision of this Agreement. * 7.7 Governing Law. This Agreement shall be construed, governed, interpreted and applied in accordance with the internal laws of the Commonwealth of Massachusetts, U.S.A., without regard to conflict of laws principles. */ +package org.broadinstitute.sting.gatk.walkers.haplotypecaller.graphs; -package org.broadinstitute.sting.gatk.walkers.compression.reducereads; - -import it.unimi.dsi.fastutil.objects.ObjectAVLTreeSet; -import it.unimi.dsi.fastutil.objects.ObjectSortedSet; -import org.broadinstitute.sting.utils.*; - -import java.util.Collection; - +import org.broadinstitute.sting.utils.haplotype.Haplotype; /** - * A stash of regions that must be kept uncompressed in all samples + * Represents a result from a K-best haplotype search. * - * In general, these are regions that were kept uncompressed by a tumor sample and we want to force - * all other samples (normals and/or tumors) to also keep these regions uncompressed - * - * User: carneiro - * Date: 10/15/12 - * Time: 4:08 PM + * @author Valentin Ruano-Rubio <valentin@broadinstitute.org> */ -public class CompressionStash extends ObjectAVLTreeSetCurrently, the score is the multiplicity total sum of edges along the haplotype path
+ * + * @return 0 or greater. + */ + public abstract int score(); + + /** + * Indicates whether this result is the reference haplotype. + * + * @return {@code true} if it is the reference haplotype, {@code false} otherwise. + */ + public abstract boolean isReference(); + + /** + * The rank of this solution within the list of solutions that resulted from the same search. + * + *0 would correspond to the best solution, 1 with the second best and so on
+ * + * @return 0 or greater. + */ + public abstract int rank(); + + private byte[] bases; + + private Haplotype haplotype; + + private PathIf there is only a single source vertex, its finder is the top finder. However whent there + * is more than one possible source, we create a composite finder that alternates between individual source vertices + * for their best haplotypes.
+ */ + private final KBestSubHaplotypeFinder topFinder; + + /** + * Constructs a new best haplotypes finder. + * + * @param graph the seq-graph to search. + * @param source the source vertex for all haplotypes. + * @param sink sink vertices for all haplotypes. + * + * @throws IllegalArgumentException if+ * It will consider all source and sink vertex when looking for haplotypes. + *
+ * + * @param graph the seq-graph to search for the best haplotypes. + */ + public KBestHaplotypeFinder(SeqGraph graph) { + this(graph,graph.getSources(),graph.getSinks()); + } + + /** + * Creates an aggregated recursive finder to try all possible source vertices. + * + * @return never {@code null}. + */ + private KBestSubHaplotypeFinder createAggregatedFinder() { + final List+ * It might return less than k haplotypes if the total number of possible haplotypes is smaller. + *
+ * + * @param k the maximum number of haplotypes to return. + * @return never {@code null}, but perhaps a iterator that return no haplotype. + */ + public Iterator+ * This peculiar signature is convenient for when we want to create finders for the children of a vertex. + *
+ * + * @param baseEdges target collection of edges. + * + * @return never {@code null}, perhaps an empty map if there is no children with valid paths to any sink for this + * finder. + */ + private Map+* Provides the k-best sub-haplotypes from a vertex provided map between outgoing edges and its target finders +*
+*+* This is done efficiently by keeping an priority-queue on best sub-haplotype solutions and pulling them on demand +* as needed. +*
+*+* Solutions are cached for repeated retrieval so that we save compute at vertices that share sub-haplotypes +* (share descendant vertices). This aspect is controlled by {@link KBestSubHaplotypeFinder} that instantiate +* a unique {@link KBestSubHaplotypeFinder} for each vertex in the graph that belongs to a valid path +* between the source and sink node. +*
+* +* @author Valentin Ruano-Rubio <valentin@broadinstitute.org> +*/ +class RecursiveSubHaplotypeFinder extends AggregatedSubHaplotypeFinder { /** - * Creates a stash with the default sorting order (read alignment) - * @param compressor the MultiSampleCompressor object to be used with this stash (for stash.close()) + * Creates a recursive sub-haplotype finder give the target graph, first vertex and all possible outgoing edges + * with the corresponding sub-sub-haplotype finders. + * + *For efficiency shake, it will not verify the content of {@code children} map; i.e. that indeed all keys + * are outgoing edges from {@code vertex} on {@code graph} and that the value sub-haplotype resolver have as + * the first vertex the adjacent vertex through that key edge.
+ * + * @param vertex first vertex for all sub-haplotype solutions provided by this finder + * @param children map from outgoing edge to the corresponding sub-sub-haplotype finder. */ - public ReduceReadsStash(MultiSampleCompressor compressor) { - this.compressor = compressor; - this.outOfOrderReads = new TreeSet+ * These by delegating on the encapsulated solution from outgoing edge's finder by adding + * the edge score and prefixing this outer finder + * source vertex. + *
*/ - public Iterable