avro.variantMetadata.avdl Maven / Gradle / Ivy
The newest version!
@namespace("org.opencb.biodata.models.variant.metadata")
protocol VariantMetadataProtocol {
// we need import metadata.avdl
import idl "metadata.avdl";
/**
Some studies does not provide real samples information.
Instead, only aggregated data is provided as file attributes.
This field represents the schema of representing aggregated data (if any)
*/
enum Aggregation {
/**
There is none aggregated data
*/
NONE,
/**
Basic aggregated data
Attributes used:
- AC: Allele Count
- AN: Allele Number
- AF: Allele Frequency
- GTC: Genotype Count
- GTS: Genotypes Sort
The attributes may refere to different cohorts with a prefix or sufix
*/
BASIC,
/**
EVS like aggregated data
Adds some attributes to the basic mode:
- GROUPS_ORDER: Used to specify the order of the comma separated values of cohorts in tags such as MAF.
- MAF: Minnor Allele Frequency for all the cohorts, ordered by GROUPS_ORDER
*/
EVS,
/**
EXAC like aggregated data
Adds some attributes to the basic mode:
- HOM: Homozygous Counts
- HET: Heterozygous Counts
*/
EXAC
}
// /**
// Counts the number of variants within a certain frequency range.
// */
// record VariantsByFrequency {
// /** Inclusive frequency range start */
// float startFrequency;
//
// /** Exclusive frequency range end */
// float endFrequency;
//
// /** Number of variants with this frequency */
// int count;
// }
/**
Variant statistics for a set of variants.
The variants set can be contain a whole study, a cohort, a sample, a region, ...
*/
record VariantSetStats {
/** Number of variants in the variant set */
long variantCount;
/** Number of samples in the variant set */
long sampleCount;
/**
* The number of occurrences for each FILTER value in files from this set.
* Each file can contain more than one filter value (usually separated by ';').
**/
map filterCount;
/** Number of genotypes found for all samples in variants set */
map genotypeCount = {};
/** Number of files in the variant set */
long filesCount;
/** TiTvRatio = num. transitions / num. transversions */
float tiTvRatio;
/** Mean Quality for all the variants with quality */
float qualityAvg;
/** Standard Deviation of the quality */
float qualityStdDev;
// /**
// array of elements to classify variants according to their 'rarity'
// Typical frequency ranges:
// - very rare -> from 0 to 0.001
// - rare -> from 0.001 to 0.005
// - low frequency -> from 0.005 to 0.05
// - common -> from 0.05
// */
// array numRareVariants = [];
/** Variants count group by type. e.g. SNP, INDEL, MNP, SNV, ... */
map typeCount = {};
/** Variants count group by biotype. e.g. protein-coding, miRNA, lncRNA, ... */
map biotypeCount = {};
/** Variants count group by consequence type. e.g. synonymous_variant, missense_variant, stop_lost, ... */
map consequenceTypeCount = {};
/** Number of variants per chromosome */
map chromosomeCount = {};
/** Total density of variants within the chromosome. counts / chromosome.length */
map chromosomeDensity = {};
}
record IndelLength {
int lt5;
int lt10;
int lt15;
int lt20;
int gte20;
}
record DepthCount {
int na;
int lt5;
int lt10;
int lt15;
int lt20;
int gte20;
}
record SampleVariantStats {
/** Sample identifier **/
string id;
/** Number of variants where the sample has the main allele (i.e. 0/1, 1/1, ./1, 1/2, ...) */
int variantCount;
/** Number of variants per chromosome **/
// TODO: Should include chromosome density?
map chromosomeCount = {};
/** Variants count group by type. e.g. SNP, INDEL, MNP, SNV, ... */
map typeCount = {};
/** Number of variants per genotype. Only counts genotypes with the main allele. Phase is ignored. **/
map genotypeCount = {};
/** Indel length grouped in ranges **/
IndelLength indelLengthCount;
/**
* The number of occurrences for each FILTER value in files from this set.
* Each file can contain more than one filter value (usually separated by ';').
**/
map filterCount;
/** TiTvRatio = num. transitions / num. transversions */
float tiTvRatio;
/** Mean Quality for all the variants with quality */
float qualityAvg;
/** Standard Deviation of the quality */
float qualityStdDev;
// TODO ?
// /** Number of positions not sequenced **/
// int missingPositions;
//double missingnessScore ??
/**
* Heterozygosity rate as defined by PLINK: (N–O)/N
*
* N is the number of non-missing genotypes
* O is the observed number of homozygous genotypes for a given individual
**/
float heterozygosityRate;
/** Number of mendelian errors grouped by PLINK error codes grouped by Chromosome. **/
map> mendelianErrorCount = {};
DepthCount depthCount;
/**
* Variants count group by consequence type. e.g. missense_variant, synonymous_variant, stop_lost, ...
* Each counter is increased at most one per variant. If multiple overlapping transcripts have the same consequence type, it will count as one.
*/
map consequenceTypeCount = {};
/**
* Variants count group by biotype. e.g. protein-coding, miRNA, lncRNA, ...
* Each counter is increased at most one per variant. If multiple overlapping genes have the same biotypes, it will count as one.
*/
map biotypeCount = {};
/**
* Variants count group by clinical significance. e.g. benign, likely_benign, likely_pathogenic, pathogenic, uncertain_significance ...
* Each counter is increased at most one per variant. If multiple variant traits have the same clinical significance, it will count as one.
*/
map clinicalSignificanceCount = {};
}
record VariantFileHeaderComplexLine {
/** Key of group of the Complex Header Line, e.g. INFO, FORMAT, FILTER, ALT, ... */
string key;
/** ID or Name of the line */
string id;
/** The description */
union {null, string} description = null;
/**
Arity of the values associated with this metadata line.
Only present if the metadata line describes data fields, i.e. key == INFO or FORMAT
Accepted values:
- : The field has always this number of values.
- A: The field has one value per alternate allele.
- R: The field has one value for each possible allele, including the reference.
- G: The field has one value for each possible genotype
- .: The number of possible values varies, is unknown or unbounded.
*/
union {null, string} number = null;
/**
Type of the values associated with this metadata line.
Only present if the metadata line describes data fields, i.e. key == INFO or FORMAT
Accepted values:
- Integer
- Float
- String
- Character
- Flag
*/
union {null, string} type = null;
/** Other optional fields */
map genericFields = {};
}
record VariantFileHeaderSimpleLine {
/** Key of group of the Simple Header Line, e.g. source, assembly, pedigreeDB, ... */
string key;
/** Value */
string value;
}
/**
Variant File Header. Contains simple and complex metadata lines describing the content of the file.
This header matches with the VCF header.
A header may have multiple Simple or Complex lines with the same key
*/
record VariantFileHeader {
string version;
/** complex lines, e.g. INFO= */
array complexLines = [];
/** simple lines, e.g. fileDate=20090805 */
array simpleLines = [];
}
record VariantFileMetadata {
/** File id. Will match with the {@link org.opencb.biodata.models.variant.avro.FileEntry#getFileId} */
string id;
/** Path to the original file */
union { null, string } path = null;
/** Ordered list of sample ids contained in the file */
array sampleIds = [];
/** Global statistics calculated for this file */
union { null, VariantSetStats } stats = null;
/** The Variant File Header */
union { null, VariantFileHeader } header = null;
/** Other user defined attributes related with the file */
map attributes = {};
}
record VariantStudyStats {
map sampleStats = {};
map cohortStats = {};
}
record VariantStudyMetadata {
/** Study id. Will match with the {@link org.opencb.biodata.models.variant.StudyEntry#getStudyId} */
string id;
/** Optional description */
union { null, string } description = null;
/**
Some studies does not provide real samples information.
Instead, only aggregated data is provided as file attributes.
This field represents the schema of representing aggregated data (if any)
*/
Aggregation aggregation = "NONE";
/** Aggregation of all the file headers from this study */
union {null, VariantFileHeader} aggregatedHeader = null;
/** Metadata from all the files contained in this study */
array files = [];
/** Metadata from all the individuals and samples in this study */
array individuals = [];
/** Metadata from with all the cohorts defined in this study */
array cohorts = [];
/** Type of sample set. Defines the type of the study. */
org.opencb.biodata.models.metadata.SampleSetType sampleSetType;
/** Samples and Cohort global statistics */
union { null, VariantStudyStats } stats = null;
/** Other user defined attributes related with the study */
map attributes = {};
}
record VariantMetadata {
/** Data model version */
string version = "v1.0.0";
/** Species information. Same species and assembly for all the studies */
union { null, org.opencb.biodata.models.metadata.Species } species = null;
/** Creation date */
union { null, string } creationDate = null;
/** Optional description */
union { null, string } description = null;
/** List of studies within this set of data */
array studies = [];
}
}