Funcotator - removing the required transcript file #8863
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,89 @@ | ||
| package org.broadinstitute.hellbender.utils; | ||
|
|
||
| import htsjdk.samtools.util.Locatable; | ||
| import javassist.Loader; | ||
| import org.broadinstitute.hellbender.engine.ReferenceContext; | ||
| import org.broadinstitute.hellbender.tools.funcotator.FuncotatorUtils; | ||
|
|
||
| import java.util.Arrays; | ||
| import java.util.Comparator; | ||
| import java.util.List; | ||
| import java.util.stream.Collectors; | ||
|
|
||
| /** | ||
| * Class with utility methods for working with transcripts. | ||
| */ | ||
| public class TranscriptUtils { | ||
|
|
||
| //================================================================================================================== | ||
| // Public Static Members: | ||
|
|
||
| /** | ||
| * Extracts the transcript sequence from the reference context given the exons. | ||
| * The given exons are assumed to be all on the same contig. | ||
| * The exons will be sorted in the order they appear in the genome before extracting the sequences. | ||
| * @param refContext the reference context. Must not be {@code null}. | ||
| * @param exons the exons of the transcript. Must not be {@code null}. | ||
| * @return the transcript sequence as coded in the given reference context. | ||
| */ | ||
| public static final String extractTrascriptFromReference(final ReferenceContext refContext, | ||
jonn-smith marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| final List<Locatable> exons) { | ||
| return extractTrascriptFromReference(refContext, exons, false); | ||
| } | ||
|
|
||
| /** | ||
| * Extracts the transcript sequence from the reference context given the exons. | ||
| * The given exons are assumed to be all on the same contig. | ||
| * The exons will be sorted in the order they appear in the genome before extracting the sequences. | ||
| * @param refContext the reference context. Must not be {@code null}. | ||
| * @param exons the exons of the transcript. Must not be {@code null}. | ||
| * @param convertHg19ContigToB37Contig whether to convert the contig names from hg19 to b37. | ||
| * @return the transcript sequence as coded in the given reference context. | ||
| */ | ||
| public static final String extractTrascriptFromReference(final ReferenceContext refContext, | ||
| final List<Locatable> exons, | ||
| final boolean convertHg19ContigToB37Contig ) { | ||
|
|
||
| // TODO: THIS CONVERSION IS BAD. WE MUST REFACTOR THIS EVENTUALLY TO REMOVE THIS AND MAKE SOME B37 DATA SOURCES. | ||
| Utils.nonNull(refContext); | ||
| Utils.nonNull(exons); | ||
|
|
||
| final StringBuilder transcript = new StringBuilder(); | ||
|
|
||
| // We should iterate through the list of exons in sorted order so we can simply append them together. | ||
| for (final Locatable exon : exons.stream().sorted(Comparator.comparingInt(Locatable::getStart).thenComparing(Locatable::getEnd)).toList() ) { | ||
|
There was a problem hiding this comment. again this ordering/overlapping assumption |
||
| final SimpleInterval exonInterval; | ||
|
|
||
| if ( convertHg19ContigToB37Contig ) { | ||
| exonInterval = new SimpleInterval(FuncotatorUtils.convertHG19ContigToB37Contig(exon.getContig()), exon.getStart(), exon.getEnd()); | ||
|
There was a problem hiding this comment. this might be a little cleaner to read with a ternary (alternatively make some helper method somewhere called "getConvertedContigName()" (that goes for GencodeFuncotationFactory as well which also threads this a bunch) |
||
| } | ||
| else { | ||
| exonInterval = new SimpleInterval(exon.getContig(), exon.getStart(), exon.getEnd()); | ||
| } | ||
| transcript.append(new String(refContext.getBases(exonInterval))); | ||
| } | ||
| return transcript.toString(); | ||
| } | ||
|
|
||
| //================================================================================================================== | ||
jonn-smith marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| // Private Static Members: | ||
|
|
||
| //================================================================================================================== | ||
| // Private Members: | ||
|
|
||
| //================================================================================================================== | ||
| // Constructors: | ||
|
|
||
| //================================================================================================================== | ||
| // Override Methods: | ||
|
|
||
| //================================================================================================================== | ||
| // Static Methods: | ||
|
|
||
| //================================================================================================================== | ||
| // Instance Methods: | ||
|
|
||
| //================================================================================================================== | ||
| // Helper Data Types: | ||
|
|
||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.