de.charite.compbio.jannovar.annotation.VariantEffect Maven / Gradle / Ivy
package de.charite.compbio.jannovar.annotation;
import com.google.common.base.Function;
import com.google.common.base.Predicate;
// TODO(holtgrew): For now, only insert most specific variants by default, add switch that adds transitive changes
// TODO(holtgrew): structural variants need more refinement
/**
* These codes reflect the possible types of variants that we call for an exome.
*
* The values in this enum are given in the putative order of impact (more severe to less severe). The documentation
* gives the sequence ontology (SO) ID and the SO description. Also, the documentation of each value explains whether
* Jannovar generates this annotation or not.
*
* @author Peter Robinson
* @author Marten Jaeger
* @author Manuel Holtgrewe
* @author Max Schubach
*/
public enum VariantEffect {
//
// HIGH Putative Impact
//
// change of feature structure or larger units
/**
* SO:1000182 A kind of chromosome
* variation where the chromosome complement is not an exact multiple of the haploid number (is a
* chromosome_variation).
*
* Not used in Jannovar annotations.
*/
CHROMOSOME_NUMBER_VARIATION,
/**
* SO:0001893 A feature ablation
* whereby the deleted region includes a transcript feature (is a: feature_ablation)
*
* Not used in Jannovar annotations.
*/
TRANSCRIPT_ABLATION,
/**
* SO:0001572 A sequence variant
* whereby an exon is lost from the transcript (is a (is a: {@link #SPLICING_VARIANT}), {@link #TRANSCRIPT_VARIANT}
* ).
*
* Not used in Jannovar annotations.
*/
EXON_LOSS_VARIANT,
// high impact changes in the coding region
/**
* SO:0001909 A frameshift variant
* that causes the translational reading frame to be extended relative to the reference feature (is a
* {@link #FRAMESHIFT_VARIANT}, internal_feature_elongation).
*/
FRAMESHIFT_ELONGATION,
/**
* SO:0001910 A frameshift variant
* that causes the translational reading frame to be shortened relative to the reference feature (is a
* {@link #FRAMESHIFT_VARIANT}, internal_feature_truncation).
*/
FRAMESHIFT_TRUNCATION,
/**
* SO:0001589A sequence variant
* which causes a disruption of the translational reading frame, because the number of nucleotides inserted or
* deleted is not a multiple of threee (is a: protein_altering_variant).
*
* Used for frameshift variant for the case where there is no stop codon any more and the rare case in which the
* transcript length is retained.
*/
FRAMESHIFT_VARIANT,
/**
* SO:0001908 A sequence variant
* that causes the extension of a genomic feature from within the feature rather than from the terminus of the
* feature, with regard to the reference sequence.
*
* In Jannovar, used to annotate a {@link #COMPLEX_SUBSTITUTION} that does not lead to a frameshift and increases
* the transcript length.
*/
INTERNAL_FEATURE_ELONGATION,
/**
* SO:0001906 A sequence variant
* that causes the reduction of a genomic feature, with regard to the reference sequence (is a: feature_variant).
*
* The term
* INTERNAL_FEATURE_TRUNCATION would be more fitting but is not available in SO.
*
* In Jannovar, used to annotate a {@link #COMPLEX_SUBSTITUTION} that does not lead to a frameshift and decreases
* the transcript length.
*/
FEATURE_TRUNCATION,
/**
* SO:0002007 An MNV is a multiple
* nucleotide variant (substitution) in which the inserted sequence is the same length as the replaced sequence (is
* a: substitution).
*/
MNV,
/**
* SO:1000005 When no simple or
* well defined DNA mutation event describes the observed DNA change, the keyword "complex" should be used. Usually
* there are multiple equally plausible explanations for the change (is a: substitution).
*
* Used together with {@link #INTERNAL_FEATURE_ELONGATION} or {@link #FEATURE_TRUNCATION} to describe an variant
* that does not lead to a frameshift but a changed transcript length. Used together with
* {@link #FRAMESHIFT_ELONGATION} or {@link #FRAMESHIFT_TRUNCATION} if the substitution leads to a frameshift
* variant.
*/
COMPLEX_SUBSTITUTION,
/**
* SO:0001587 A sequence variant
* whereby at least one base of a codon is changed, resulting in a premature stop codon, leading to a shortened
* transcript (is a: nonsynonymous_variant, feature_truncation).
*/
STOP_GAINED,
/**
* SO:0001578 A sequence variant
* where at least one base of the terminator codon (stop) is changed, resulting in an elongated transcript (is a:
* nonsynonymous variant, terminator_codon_variant, feature_elongation)
*/
STOP_LOST,
/**
* SO:0002012 A codon variant that
* changes at least one base of the canonical start codon (is a: initiator_codon_variant).
*/
START_LOST,
// splicing changes, might change splicing
/**
* SO:0001574 A splice variant
* that changes the 2 base region at the 3' end of an intron (is a {@link #SPLICE_REGION_VARIANT}).
*/
SPLICE_ACCEPTOR_VARIANT,
/**
* SO:0001575 A splice variant
* that changes the 2 base pair region at the 5' end of an intron (is a {@link #SPLICE_REGION_VARIANT}).
*/
SPLICE_DONOR_VARIANT,
// change in rare amino acids, exotic variant
/**
* SO:0002008 A sequence variant
* whereby at least one base of a codon encoding a rare amino acid is changed, resulting in a different encoded
* amino acid (children: selenocysteine_loss, pyrrolysine_loss).
*
* Not used in Jannovar annotations.
*/
RARE_AMINO_ACID_VARIANT,
/**
* Marker for smallest {@link VariantEffect} with {@link PutativeImpact#HIGH} impact.
*/
_SMALLEST_HIGH_IMPACT,
//
// MODERATE Putative Impact
//
// moderate impact changes in coding region that
/**
* SO:0001583 A sequence variant,
* that changes one or more bases, resulting in a different amino acid sequence but where the length is preserved.
*/
MISSENSE_VARIANT,
/**
* SO:0001821 An inframe non
* synonymous variant that inserts bases into in the coding sequence (is a: inframe_indel,
* internal_feature_elongation).
*/
INFRAME_INSERTION,
/**
* SO:0001824 An inframe increase
* in cds length that inserts one or more codons into the coding sequence within an existing codon (is a:
* {@link #INFRAME_INSERTION}).
*/
DISRUPTIVE_INFRAME_INSERTION,
/**
* SO:0001822 An inframe non
* synonymous variant that deletes bases from the coding sequence (is a: inframe_indel, feature_truncation).
*/
INFRAME_DELETION,
/**
* SO:0001826 An inframe decrease
* in cds length that deletes bases from the coding sequence starting within an existing codon (is a:
* {@link #INFRAME_DELETION}).
*/
DISRUPTIVE_INFRAME_DELETION,
// changes in the UTR
/**
* SO:0002013 A sequence variant
* that causes the reduction of a the 5'UTR with regard to the reference sequence (is a:
* {@link #FIVE_PRIME_UTR_EXON_VARIANT} or {@link #FIVE_PRIME_UTR_INTRON_VARIANT})
*
* Jannovar does not yield use this at the moment.
*/
FIVE_PRIME_UTR_TRUNCATION,
/**
* SO:0002015 A sequence variant
* that causes the reduction of a the 3' UTR with regard to the reference sequence (is a:
* {@link #FIVE_PRIME_UTR_EXON_VARIANT} or {@link #FIVE_PRIME_UTR_INTRON_VARIANT}).
*
* Jannovar does not yield use this at the moment.
*/
THREE_PRIME_UTR_TRUNCATION,
// changes in the splicing region
/**
* SO:0001630 A sequence variant
* in which a change has occurred within the region of the splice site, either within 1-3 bases of the exon or 3-8
* bases of the intron (is a: {@link #SPLICING_VARIANT}).
*/
SPLICE_REGION_VARIANT,
/**
* Marker for smallest {@link VariantEffect} with {@link PutativeImpact#MODERATE} impact.
*/
_SMALLEST_MODERATE_IMPACT,
//
// LOW Putative Impact
//
/**
* SO:0001567 A sequence variant
* where at least one base in the terminator codon is changed, but the terminator remains (is a:
* {@link #SYNONYMOUS_VARIANT}, terminator_codon_variant).
*/
STOP_RETAINED_VARIANT,
/**
* SO:0001582 A codon variant that
* changes at least one base of the first codon of a transcript (is a: {@link #CODING_SEQUENCE_VARIANT}, children:
* start_retained_variant, start_lost).
*/
INITIATOR_CODON_VARIANT,
/**
* SO:0001819 A sequence variant
* where there is no resulting change to the encoded amino acid (is a: {@link #CODING_SEQUENCE_VARIANT}, children:
* start_retained_variant, stop_retained_variant).
*/
SYNONYMOUS_VARIANT,
// changes in coding transcripts, exons/introns
/**
* SO:0001969 A sequence variant
* that changes non-coding intro sequence in a non-coding transcript (is a: {@link #CODING_TRANSCRIPT_VARIANT},
* {@link #INTRON_VARIANT}).
*/
CODING_TRANSCRIPT_INTRON_VARIANT,
// changes in non-coding transcripts, exons/introns
/**
* SO:0001792 A sequence variant
* that changes non-coding exon sequence in a non-coding transcript (is a: {@link #NON_CODING_TRANSCRIPT_VARIANT},
* {@link #EXON_VARIANT}).
*/
NON_CODING_TRANSCRIPT_EXON_VARIANT,
/**
* SO:0001970 A sequence variant
* that changes non-coding intro sequence in a non-coding transcript (is a: {@link #NON_CODING_TRANSCRIPT_VARIANT},
* {@link #INTRON_VARIANT}).
*/
NON_CODING_TRANSCRIPT_INTRON_VARIANT,
/**
* SO:0001983 A 5' UTR variant
* where a premature start codon is introduced, moved or lost (is a: {@link #FIVE_PRIME_UTR_EXON_VARIANT} or
* {@link #FIVE_PRIME_UTR_INTRON_VARIANT}).
*
* Not used in Jannovar annotations.
*/
// TODO(holtgrem): use
FIVE_PRIME_UTR_PREMATURE_START_CODON_GAIN_VARIANT,
/**
* SO:0002092 A UTR variant of the
* 5' UTR (is a: 5_prime_UTR_variant; is a: UTR_variant).
*/
FIVE_PRIME_UTR_EXON_VARIANT,
/**
* SO:0002089 A UTR variant of the
* 3' UTR (is a: 3_prime_UTR_variant; is a: UTR_variant).
*/
THREE_PRIME_UTR_EXON_VARIANT,
/**
* SO:0002091 A UTR variant
* between 5' UTRs (is a: 5_prime_UTR_variant; is a: UTR_variant).
*/
FIVE_PRIME_UTR_INTRON_VARIANT,
/**
* SO:0002090 A UTR variant
* between 3' UTRs (is a: 3_prime_UTR_variant; is a: UTR_variant).
*/
THREE_PRIME_UTR_INTRON_VARIANT,
/**
* Marker for smallest {@link VariantEffect} with {@link PutativeImpact#LOW} impact.
*/
_SMALLEST_LOW_IMPACT,
//
// MODIFIER Putative Impact
//
// duplication marker
/**
* SO:1000039 A tandem duplication
* where the individual regions are in the same orientation (is a: tandem_duplication).
*
* In Jannovar used, as an additional marker to describe that an insertion is a duplication.
*/
DIRECT_TANDEM_DUPLICATION,
// variant in custom region
/**
* Variant in a user-specified custom region.
*
* Not used in Jannovar annotations.
*/
// TODO(holtgrem): use?
CUSTOM,
// variants with distances to genes/transcripts
/**
* SO:0001631 A sequence variant
* located 5' of a gene (is a: {@link #INTERGENIC_VARIANT}).
*/
UPSTREAM_GENE_VARIANT,
/**
* SO:0001632 A sequence variant
* located 3' of a gene (is a: {@link #INTERGENIC_VARIANT}).
*/
DOWNSTREAM_GENE_VARIANT,
/**
* SO:0001628 A sequence variant
* located in the intergenic region, between genes (is a: feature_variant).
*/
INTERGENIC_VARIANT,
// regulatory / TFBS variants
/**
* SO:0001782 A sequence variant
* located within a transcription factor binding site (is a: {@link #REGULATORY_REGION_VARIANT}).
*
* Not used in Jannovar annotations.
*/
TF_BINDING_SITE_VARIANT,
/**
* SO:0001566 A sequence variant
* located within a regulatory region (is a: feature_variant).
*
* Not used in Jannovar annotations.
*/
REGULATORY_REGION_VARIANT,
// variant in intronic regions
/**
* SO:0002018 A transcript variant
* occurring within a conserved region of an intron (is a: {@link #INTRON_VARIANT}).
*
* Not used in Jannovar annotations.
*/
CONSERVED_INTRON_VARIANT,
/**
* SO:0002011 A variant that
* occurs within a gene but falls outside of all transcript features. This occurs when alternate transcripts of a
* gene do not share overlapping sequence (is a: {@link #TRANSCRIPT_VARIANT} ).
*/
// TODO(holtgrem): use?
INTRAGENIC_VARIANT,
/**
* SO:0002017 A sequence variant
* located in a conserved intergenic region, between genes (is a: {@link #INTERGENIC_VARIANT}).
*/
CONSERVED_INTERGENIC_VARIANT,
// general variant types
/**
* SO:0001537 A sequence variant
* that changes one or more sequence features (is a: sequence variant).
*/
STRUCTURAL_VARIANT,
/**
* SO:0001580 A sequence variant
* that changes the coding sequence (is a: {@link #CODING_TRANSCRIPT_VARIANT}, {@link #EXON_VARIANT}).
*
* Sequence Ontology does not have a term
*
* CODING_TRANSCRIPT_EXON_VARIANT, so we use this.
*
* Not used in Jannovar annotations.
*/
CODING_SEQUENCE_VARIANT,
/**
* SO:0001627 A transcript variant
* occurring within an intron (is a: {@link #TRANSCRIPT_VARIANT}).
*
* Jannovar uses {@link #CODING_TRANSCRIPT_INTRON_VARIANT} and {@link #NON_CODING_TRANSCRIPT_INTRON_VARIANT}
* instead.
*/
INTRON_VARIANT,
/**
* SO:0001791 A sequence variant
* that changes exon sequence (is a: {@link #TRANSCRIPT_VARIANT}).
*/
EXON_VARIANT,
/**
* SO:0001568 A sequence variant
* that changes the process of splicing (is a: {@link #GENE_VARIANT}).
*
* Not used in Jannovar annotations.
*/
SPLICING_VARIANT,
/**
* SO:0000276 Variant affects a
* miRNA (is a: miRNA_primary_transcript, small_regulatory_ncRNA).
*
* Not used in Jannovar annotations.
*/
// TODO(holtgrem): use?
MIRNA,
/**
* SO:0001564 A sequence variant
* where the structure of the gene is changed (is a: feature_variant).
*
* Not used in Jannovar annotations.
*/
GENE_VARIANT,
/**
* SO:0001968 A transcript variant
* of a protein coding gene (is a: {@link #TRANSCRIPT_VARIANT}).
*
* Not used in Jannovar annotations.
*/
CODING_TRANSCRIPT_VARIANT,
/**
* SO:0001619 (is a:
* {@link #TRANSCRIPT_VARIANT}).
*
* Used for marking splicing variants as non-coding.
*/
NON_CODING_TRANSCRIPT_VARIANT,
/**
* SO:0001576 A sequence variant
* that changes the structure of the transcript (is a: {@link #GENE_VARIANT}). TRANSCRIPT_VARIANT, /**
* SO: (is a: {@link #GENE_VARIANT})).
*
* Not used in Jannovar annotations.
*/
TRANSCRIPT_VARIANT,
/**
* SO:0000605 A region containing
* or overlapping no genes that is bounded on either side by a gene, or bounded by a gene and the end of the
* chromosome (is a: biological_region).
*
* Not used in Jannovar annotations.
*/
INTERGENIC_REGION,
/**
* SO:0000340 Structural unit
* composed of a nucleic acid molecule which controls its own replication through the interaction of specific
* proteins at one or more origins of replication (is a: replicon).
*
* Not used in Jannovar annotations.
*/
CHROMOSOME,
/**
* SO:0001060 Top level term for
* variants, can be used for marking "uknown effect".
*
* Not used in Jannovar annotations.
*/
SEQUENCE_VARIANT;
/**
* {@link Predicate} for testing whether a {@link VariantEffect} is related to splicing.
*/
public static final Predicate IS_SPLICING = new Predicate() {
@Override
public boolean apply(VariantEffect arg) {
return arg.isSplicing();
}
};
/**
* {@link Predicate} for testing whether a {@link VariantEffect} is intronic.
*/
public static final Predicate IS_INTRONIC = new Predicate() {
@Override
public boolean apply(VariantEffect arg) {
return arg.isIntronic();
}
};
/**
* {@link Function} for converting from {@link VariantEffect} to SO term String.
*/
public static final Function TO_SO_TERM = new Function() {
@Override
public String apply(VariantEffect arg) {
return arg.getSequenceOntologyTerm();
}
};
/**
* {@link Function} for converting from {@link VariantEffect} to legacy term.
*/
public static final Function TO_LEGACY_NAME = new Function() {
@Override
public String apply(VariantEffect arg) {
return arg.getLegacyTerm();
}
};
/**
* @return true if the effect type denotes a frameshift variant (can only return true only
* small variants, spanning at most one exon, are considered).
*/
boolean isFrameshiftVariant() {
switch (this) {
case FRAMESHIFT_ELONGATION:
case FRAMESHIFT_TRUNCATION:
return true;
default:
return false;
}
}
/**
* @return Legacy (old Jannovar) id.
*/
public String getLegacyTerm() {
switch (this) {
case DIRECT_TANDEM_DUPLICATION:
case DISRUPTIVE_INFRAME_DELETION:
case FEATURE_TRUNCATION:
case INFRAME_DELETION:
return "NON_FS_DELETION";
case DOWNSTREAM_GENE_VARIANT:
return "DOWNSTREAM";
case FIVE_PRIME_UTR_PREMATURE_START_CODON_GAIN_VARIANT:
case FIVE_PRIME_UTR_TRUNCATION:
case FIVE_PRIME_UTR_EXON_VARIANT:
return "UTR5";
case FRAMESHIFT_ELONGATION:
return "FS_INSERTION";
case FRAMESHIFT_TRUNCATION:
return "FS_DELETION";
case FRAMESHIFT_VARIANT:
return "FS_SUBSTITUTION";
case INITIATOR_CODON_VARIANT:
return "STARTLOSS";
case CONSERVED_INTERGENIC_VARIANT:
case INTERGENIC_VARIANT:
return "INTERGENIC";
case INFRAME_INSERTION:
case DISRUPTIVE_INFRAME_INSERTION:
case INTERNAL_FEATURE_ELONGATION:
return "NON_FS_INSERTION";
case INTRAGENIC_VARIANT:
return "INTRAGENIC";
case CONSERVED_INTRON_VARIANT:
case CODING_TRANSCRIPT_INTRON_VARIANT:
case INTRON_VARIANT:
case FIVE_PRIME_UTR_INTRON_VARIANT:
case THREE_PRIME_UTR_INTRON_VARIANT:
return "INTRONIC";
case MNV:
return "NON_FS_SUBSTITUTION";
case NON_CODING_TRANSCRIPT_EXON_VARIANT:
return "ncRNA_EXONIC";
case NON_CODING_TRANSCRIPT_INTRON_VARIANT:
return "ncRNA_INTRONIC";
case MISSENSE_VARIANT:
case RARE_AMINO_ACID_VARIANT:
return "MISSENSE";
case SPLICE_ACCEPTOR_VARIANT:
case SPLICE_DONOR_VARIANT:
case SPLICE_REGION_VARIANT:
case SPLICING_VARIANT:
return "SPLICING";
case START_LOST:
return "STARTLOSS";
case STOP_GAINED:
return "STOPGAIN";
case STOP_LOST:
return "STOPLOSS";
case STOP_RETAINED_VARIANT:
case SYNONYMOUS_VARIANT:
return "SYNONYMOUS";
case THREE_PRIME_UTR_TRUNCATION:
case THREE_PRIME_UTR_EXON_VARIANT:
return "UTR3";
case TRANSCRIPT_ABLATION:
return "TRANSCRIPT_ABLATION";
case UPSTREAM_GENE_VARIANT:
return "UPSTREAM";
case SEQUENCE_VARIANT:
return "UNKNOWN";
case GENE_VARIANT:
case CHROMOSOME:
case CHROMOSOME_NUMBER_VARIATION:
case CODING_SEQUENCE_VARIANT:
case CODING_TRANSCRIPT_VARIANT:
case COMPLEX_SUBSTITUTION:
case CUSTOM:
case EXON_LOSS_VARIANT:
case EXON_VARIANT:
case MIRNA:
case INTERGENIC_REGION:
case NON_CODING_TRANSCRIPT_VARIANT:
case REGULATORY_REGION_VARIANT:
case STRUCTURAL_VARIANT:
case TF_BINDING_SITE_VARIANT:
case TRANSCRIPT_VARIANT:
case _SMALLEST_HIGH_IMPACT:
case _SMALLEST_LOW_IMPACT:
case _SMALLEST_MODERATE_IMPACT:
default:
return null;
}
}
/**
* @return {@link PutativeImpact} of this effect annotation.
*/
public PutativeImpact getImpact() {
if (this.ordinal() <= _SMALLEST_HIGH_IMPACT.ordinal())
return PutativeImpact.HIGH;
else if (this.ordinal() <= _SMALLEST_MODERATE_IMPACT.ordinal())
return PutativeImpact.MODERATE;
else if (this.ordinal() <= _SMALLEST_LOW_IMPACT.ordinal())
return PutativeImpact.LOW;
else
return PutativeImpact.MODIFIER;
}
/**
* @return String with the Sequence
* Ontology term.
*/
public String getSequenceOntologyTerm() {
switch (this) {
case CHROMOSOME:
return "chromosome";
case CHROMOSOME_NUMBER_VARIATION:
return "chromosome_number_variation";
case CODING_SEQUENCE_VARIANT:
return "coding_sequence_variant";
case CODING_TRANSCRIPT_INTRON_VARIANT:
return "coding_transcript_intron_variant";
case CODING_TRANSCRIPT_VARIANT:
return "coding_transcript_variant";
case COMPLEX_SUBSTITUTION:
return "complex_substitution";
case CONSERVED_INTERGENIC_VARIANT:
return "conserved_intergenic_variant";
case CONSERVED_INTRON_VARIANT:
return "conserved_intron_variant";
case CUSTOM:
return "";
case DIRECT_TANDEM_DUPLICATION:
return "direct_tandem_duplication";
case DISRUPTIVE_INFRAME_DELETION:
return "disruptive_inframe_deletion";
case DISRUPTIVE_INFRAME_INSERTION:
return "disruptive_inframe_insertion";
case DOWNSTREAM_GENE_VARIANT:
return "downstream_gene_variant";
case EXON_LOSS_VARIANT:
return "exon_loss_variant";
case EXON_VARIANT:
return "exon_variant";
case FEATURE_TRUNCATION:
return "feature_truncation";
case FIVE_PRIME_UTR_PREMATURE_START_CODON_GAIN_VARIANT:
return "5_prime_UTR_premature_start_codon_gain_variant";
case FIVE_PRIME_UTR_TRUNCATION:
return "5_prime_UTR_truncation";
case FIVE_PRIME_UTR_EXON_VARIANT:
return "5_prime_UTR_exon_variant";
case FIVE_PRIME_UTR_INTRON_VARIANT:
return "5_prime_UTR_intron_variant";
case FRAMESHIFT_ELONGATION:
return "frameshift_elongation";
case FRAMESHIFT_TRUNCATION:
return "frameshift_truncation";
case GENE_VARIANT:
return "gene_variant";
case INFRAME_DELETION:
return "inframe_deletion";
case INFRAME_INSERTION:
return "inframe_insertion";
case INITIATOR_CODON_VARIANT:
return "initiator_codon_variant";
case INTERGENIC_REGION:
return "intergenic_region";
case INTERGENIC_VARIANT:
return "intergenic_variant";
case INTERNAL_FEATURE_ELONGATION:
return "internal_feature_elongation";
case INTRAGENIC_VARIANT:
return "intragenic_variant";
case INTRON_VARIANT:
return "intron_variant";
case MIRNA:
return "miRNA";
case MISSENSE_VARIANT:
return "missense_variant";
case MNV:
return "mnv";
case NON_CODING_TRANSCRIPT_EXON_VARIANT:
return "non_coding_transcript_exon_variant";
case NON_CODING_TRANSCRIPT_INTRON_VARIANT:
return "non_coding_transcript_intron_variant";
case NON_CODING_TRANSCRIPT_VARIANT:
return "non_coding_transcript_variant";
case RARE_AMINO_ACID_VARIANT:
return "rare_amino_acid_variant";
case REGULATORY_REGION_VARIANT:
return "regulatory_region_variant";
case SEQUENCE_VARIANT:
return "sequence_variant";
case SPLICE_ACCEPTOR_VARIANT:
return "splice_acceptor_variant";
case SPLICE_DONOR_VARIANT:
return "splice_donor_variant";
case SPLICE_REGION_VARIANT:
return "splice_region_variant";
case SPLICING_VARIANT:
return "splicing_variant";
case START_LOST:
return "start_lost";
case STOP_GAINED:
return "stop_gained";
case STOP_LOST:
return "stop_lost";
case STOP_RETAINED_VARIANT:
return "stop_retained_variant";
case STRUCTURAL_VARIANT:
return "structural_variant";
case SYNONYMOUS_VARIANT:
return "synonymous_variant";
case TF_BINDING_SITE_VARIANT:
return "tf_binding_site_variant";
case THREE_PRIME_UTR_TRUNCATION:
return "3_prime_UTR_truncation";
case THREE_PRIME_UTR_EXON_VARIANT:
return "3_prime_UTR_exon_variant";
case THREE_PRIME_UTR_INTRON_VARIANT:
return "3_prime_UTR_intron_variant";
case TRANSCRIPT_ABLATION:
return "transcript_ablation";
case TRANSCRIPT_VARIANT:
return "transcript_variant";
case UPSTREAM_GENE_VARIANT:
return "upstream_gene_variant";
case FRAMESHIFT_VARIANT:
return "frameshift_variant";
case _SMALLEST_HIGH_IMPACT:
case _SMALLEST_LOW_IMPACT:
case _SMALLEST_MODERATE_IMPACT:
default:
return null;
}
}
/**
* @return String with the Sequence
* Ontology ID.
*/
public String getSequenceOID() {
switch (this) {
case CHROMOSOME:
return "SO:0000340";
case CHROMOSOME_NUMBER_VARIATION:
return "SO:1000182";
case CODING_SEQUENCE_VARIANT:
return "SO:0001580";
case CODING_TRANSCRIPT_INTRON_VARIANT:
return "SO:0001969";
case CODING_TRANSCRIPT_VARIANT:
return "SO:0001968";
case COMPLEX_SUBSTITUTION:
return "SO:1000005";
case CONSERVED_INTERGENIC_VARIANT:
return "SO:0002017";
case CONSERVED_INTRON_VARIANT:
return "SO:0002018";
case CUSTOM:
return "";
case DIRECT_TANDEM_DUPLICATION:
return "SO:1000039";
case DISRUPTIVE_INFRAME_DELETION:
return "SO:0001826";
case DISRUPTIVE_INFRAME_INSERTION:
return "SO:0001824";
case DOWNSTREAM_GENE_VARIANT:
return "SO:0001632";
case EXON_LOSS_VARIANT:
return "SO:0001572";
case EXON_VARIANT:
return "SO:0001791";
case FEATURE_TRUNCATION:
return "SO:0001906";
case FIVE_PRIME_UTR_PREMATURE_START_CODON_GAIN_VARIANT:
return "SO:0001983";
case FIVE_PRIME_UTR_TRUNCATION:
return "SO:0002013";
case FIVE_PRIME_UTR_EXON_VARIANT:
return "SO:0002092";
case FIVE_PRIME_UTR_INTRON_VARIANT:
return "SO:0002091";
case FRAMESHIFT_ELONGATION:
return "SO:0001909";
case FRAMESHIFT_TRUNCATION:
return "SO:0001910";
case GENE_VARIANT:
return "SO:0001564";
case INFRAME_DELETION:
return "SO:0001822";
case INFRAME_INSERTION:
return "SO:0001821";
case INITIATOR_CODON_VARIANT:
return "SO:0001582";
case INTERGENIC_REGION:
return "SO:0000605";
case INTERGENIC_VARIANT:
return "SO:0001628";
case INTERNAL_FEATURE_ELONGATION:
return "SO:0001908";
case INTRAGENIC_VARIANT:
return "SO:0002011";
case INTRON_VARIANT:
return "SO:0001627";
case MIRNA:
return "SO:0000276";
case MISSENSE_VARIANT:
return "SO:0001583";
case MNV:
return "SO:0002007";
case NON_CODING_TRANSCRIPT_EXON_VARIANT:
return "SO:0001792";
case NON_CODING_TRANSCRIPT_INTRON_VARIANT:
return "SO:0001970";
case NON_CODING_TRANSCRIPT_VARIANT:
return "SO:0001619";
case RARE_AMINO_ACID_VARIANT:
return "SO:0002008";
case REGULATORY_REGION_VARIANT:
return "SO:0001566";
case SEQUENCE_VARIANT:
return "SO:0001060";
case SPLICE_ACCEPTOR_VARIANT:
return "SO:0001574";
case SPLICE_DONOR_VARIANT:
return "SO:0001575";
case SPLICE_REGION_VARIANT:
return "SO:0001630";
case SPLICING_VARIANT:
return "SO:0001568";
case START_LOST:
return "SO:0002012";
case STOP_GAINED:
return "SO:0001587";
case STOP_LOST:
return "SO:0001578";
case STOP_RETAINED_VARIANT:
return "SO:0001567";
case STRUCTURAL_VARIANT:
return "SO:0001537";
case SYNONYMOUS_VARIANT:
return "SO:0001819";
case TF_BINDING_SITE_VARIANT:
return "SO:0001782";
case THREE_PRIME_UTR_TRUNCATION:
return "SO:0002015";
case THREE_PRIME_UTR_EXON_VARIANT:
return "SO:0002089";
case THREE_PRIME_UTR_INTRON_VARIANT:
return "SO:0002090";
case TRANSCRIPT_ABLATION:
return "SO:0001893";
case TRANSCRIPT_VARIANT:
return "SO:0001576";
case UPSTREAM_GENE_VARIANT:
return "SO:0001631";
case FRAMESHIFT_VARIANT:
return "SO:0001589";
case _SMALLEST_HIGH_IMPACT:
case _SMALLEST_LOW_IMPACT:
case _SMALLEST_MODERATE_IMPACT:
default:
return null;
}
}
/**
* Forward to ordinal() member function.
*
* @return int with the number used for sorting values of type {@link VariantEffect}.
*/
public int getNumber() {
return ordinal();
}
/**
* @return true if this {@link VariantEffect} annotates structural variants.
*/
public boolean isStructural() {
return (this == STRUCTURAL_VARIANT);
}
/**
* @return true if this {@link VariantEffect} could affect splicing.
*/
public boolean isSplicing() {
switch (this) {
case SPLICING_VARIANT:
case SPLICE_ACCEPTOR_VARIANT:
case SPLICE_DONOR_VARIANT:
case SPLICE_REGION_VARIANT:
return true;
default:
return false;
}
}
/**
* @return true if equal to {@link #CODING_TRANSCRIPT_INTRON_VARIANT} or
* {@link #NON_CODING_TRANSCRIPT_INTRON_VARIANT}.
*/
public boolean isIntronic() {
return (this == CODING_TRANSCRIPT_INTRON_VARIANT || this == NON_CODING_TRANSCRIPT_INTRON_VARIANT);
}
/**
* @return true if the variant effect does not indicate a change affecting the exome, {@link #CUSTOM}
* is considered on-exome
* @see #isOffTranscript
*/
public boolean isOffExome() {
// Note that this function is called by isOffTranscript() which allows intronic and UTR changes.
switch (this) {
case CUSTOM:
case DISRUPTIVE_INFRAME_DELETION:
case DISRUPTIVE_INFRAME_INSERTION:
case EXON_LOSS_VARIANT:
case EXON_VARIANT:
case FEATURE_TRUNCATION:
case FIVE_PRIME_UTR_PREMATURE_START_CODON_GAIN_VARIANT:
case FRAMESHIFT_ELONGATION:
case FRAMESHIFT_TRUNCATION:
case INFRAME_DELETION:
case INFRAME_INSERTION:
case INITIATOR_CODON_VARIANT:
case INTERNAL_FEATURE_ELONGATION:
case INTRON_VARIANT:
case MISSENSE_VARIANT:
case MNV:
case NON_CODING_TRANSCRIPT_EXON_VARIANT:
case RARE_AMINO_ACID_VARIANT:
case SPLICE_ACCEPTOR_VARIANT:
case SPLICE_DONOR_VARIANT:
case SPLICE_REGION_VARIANT:
case SPLICING_VARIANT:
case START_LOST:
case STOP_GAINED:
case STOP_LOST:
case STOP_RETAINED_VARIANT:
case SYNONYMOUS_VARIANT:
case TRANSCRIPT_ABLATION:
return false;
default:
return true;
}
}
/**
* @return true if the variant effect does not indicate a change affecting a transcript,
* {@link #CUSTOM} is considered on-transcript
* @see #isOffExome
*/
public boolean isOffTranscript() {
// This function first calls isOffExome() to check whether the variant effect is off-exome. Then, this function
// also allows intronic and 5'/3' variants.
if (!isOffExome())
return false;
switch (this) {
case CODING_TRANSCRIPT_INTRON_VARIANT:
case FIVE_PRIME_UTR_TRUNCATION:
case FIVE_PRIME_UTR_INTRON_VARIANT:
case FIVE_PRIME_UTR_EXON_VARIANT:
case THREE_PRIME_UTR_TRUNCATION:
case THREE_PRIME_UTR_EXON_VARIANT:
case THREE_PRIME_UTR_INTRON_VARIANT:
case NON_CODING_TRANSCRIPT_INTRON_VARIANT:
case NON_CODING_TRANSCRIPT_VARIANT:
return false;
default:
return true;
}
}
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy