seekia/internal/genetics/geneticAnalysis/geneticAnalysis.go

// geneticAnalysis implements the geneticAnalysis objects
// There are 2 geneticAnalysis types: Person and Couple

package geneticAnalysis

import "seekia/internal/genetics/locusValue"


type PersonAnalysis struct{

	AnalysisVersion int

	// This is a list of each raw genome identifier (not including combined genomes)
	AllRawGenomeIdentifiersList [][16]byte

	// This is true if there is more than 1 raw genome
	CombinedGenomesExist bool

	// These are the identifiers for the combined genomes
	// These only exist if CombinedGenomesExist == true
	OnlyIncludeSharedGenomeIdentifier [16]byte
	OnlyExcludeConflictsGenomeIdentifier [16]byte

	// This map stores each genome's locus values
	// Only the loci that belong in the locusMetadata package are inside of this map
	// This is necessary, otherwise genetic analyses would be too large by containing each analyzed raw genome.
	// Map Structure: Genome Identifier -> Genome locus values map (rsID -> Locus Value)
	GenomesMap map[[16]byte]map[int64]locusValue.LocusValue

	// Map Structure: Disease Name -> PersonMonogenicDiseaseInfo
	MonogenicDiseasesMap map[string]PersonMonogenicDiseaseInfo

	// Map Structure: Disease Name -> PersonPolygenicDiseaseInfo
	PolygenicDiseasesMap map[string]PersonPolygenicDiseaseInfo

	// These are traits which have discrete outcomes, rather than numeric outcomes
	// For example: Eye color
	// Map Structure: Trait Name -> Trait Info Object
	DiscreteTraitsMap map[string]PersonDiscreteTraitInfo

	// These are traits which have numeric outcomes, rather than discrete outcomes
	// For example: Height
	// Map Structure: Trait Name -> Trait Info Object
	NumericTraitsMap map[string]PersonNumericTraitInfo
}


type PersonMonogenicDiseaseInfo struct{

	// This map gives information about each genome's monogenic disease risk
	// If no map entries exist, then no disease info is known
	// Map Structure: Genome Identifier -> PersonGenomeMonogenicDiseaseInfo
	MonogenicDiseaseInfoMap map[[16]byte]PersonGenomeMonogenicDiseaseInfo

	// This is true if there are multiple genomes and the results for each genome differ
	ConflictExists bool
}

type PersonGenomeMonogenicDiseaseInfo struct{

	// This describes if the person has the disease
	PersonHasDisease bool

	// This describes the number of variants that were tested for this disease
	QuantityOfVariantsTested int

	// This describes the number of loci that were tested for this disease
	// 1 locus can have multiple potential variants
	QuantityOfLociTested int

	// This describes the number of loci which are phased
	// This number will always be <= QuantityOfLociTested
	QuantityOfPhasedLoci int

	// This describes the probability that the person will pass a disease variant
	// It is a value that represents a percentage between 0-100
	ProbabilityOfPassingADiseaseVariant int

	// This map contains info about all tested monogenic disease variants for the genome
	// If the map does not contain an item for a disease variant, then the genome does not contain information for that variant
	// Map Structure: Variant Identifier -> PersonGenomeMonogenicDiseaseVariantInfo
	VariantsInfoMap map[[3]byte]PersonGenomeMonogenicDiseaseVariantInfo
}

type PersonGenomeMonogenicDiseaseVariantInfo struct{

	// These bools describe if each base has the variant at the variant's locus
	Base1HasVariant bool
	Base2HasVariant bool

	// This bool describes if the bases are phased or not
	// If they are not phased, then Base1/2 are the same, the number carries no meaning
	// If they are phased, then Base1 is inherited from the father? and Base2 was inherited from the mother?
	LocusIsPhased bool
}

type PersonPolygenicDiseaseInfo struct{

	// If no map entries exist, then no disease info is known
	// Map Structure: Genome Identifier -> PersonGenomePolygenicDiseaseInfo
	PolygenicDiseaseInfoMap map[[16]byte]PersonGenomePolygenicDiseaseInfo

	// This is true if there are multiple genomes and the results from each genome differ
	ConflictExists bool
}

type PersonGenomePolygenicDiseaseInfo struct{

	// This is total risk score for this disease for the person's genome
	// This is a number between 1-10
	RiskScore int

	// This map stores the confidence ranges for the predicted risk score
	// If we want to know how accurate the prediction is with a X% accuracy, how far would we have to expand the
	//		risk score's range to be accurate, X% of the time?
	// For example: 50% accuracy requires a +/-2 point range, 80% accuracy requires a +-5 point range
	// Map Structure: Accuracy probability (0-100) -> Amount to add to value in both +/- directions so prediction is that accurate
	ConfidenceRangesMap map[int]float64

	// This describes the quantity of loci tested for this disease
	QuantityOfLociKnown int

	QuantityOfPhasedLoci int
}


type PersonDiscreteTraitInfo struct{

	// This map contains the person's trait info for each genome
	// If no map entries exist, then no trait info is known
	// Map Structure: Genome Identifier -> PersonGenomeDiscreteTraitInfo
	TraitInfoMap map[[16]byte]PersonGenomeDiscreteTraitInfo

	// This is true if there are multiple genomes and the results from each genome differ
	ConflictExists bool
}

// For a trait analysis, both analysis methods may exist in the results
// However, the GUI will only display the results from one of the methods.
// The neural network prediction is always prioritized over the rule-based prediction
type PersonGenomeDiscreteTraitInfo struct{

	// This is true if it is possible to analyze this trait using a neural network
	NeuralNetworkExists bool

	// This is true if a neural network analysis was performed for this genome
	// This means that at least 1 locus for this trait was contained in the genome
	NeuralNetworkAnalysisExists bool

	NeuralNetworkAnalysis PersonGenomeDiscreteTraitInfo_NeuralNetwork

	// This is true if it is possible to analyze this trait using rules
	AnyRulesExist bool

	// This is true if a rules-based analysis was performed for this genome
	// This means that all of the loci for at least 1 rule for this trait was contained in the genome
	RulesAnalysisExists bool

	RulesAnalysis PersonGenomeDiscreteTraitInfo_Rules
}

type PersonGenomeDiscreteTraitInfo_NeuralNetwork struct{

	// The predicted outcome (Example: "Blue")
	PredictedOutcome string

	// Probability (0-100) that the outcome from the neural network is true
	PredictionConfidence int

	QuantityOfLociKnown int

	QuantityOfPhasedLoci int
}

type PersonGenomeDiscreteTraitInfo_Rules struct{

	// Map Structure: Rule Identifier -> Genome Passes rule (true if the genome passes the rule)
	GenomePassesRulesMap map[[3]byte]bool

	// This is true if there was not a tie between summed rule outcome scores
	// It is possible to have some tested rules without a known outcome
	PredictedOutcomeExists bool

	// This is the outcome that was predicted
	// Example: "Intolerant"
	PredictedOutcome string

	// This should be len(GenomePassesRulesMap)
	QuantityOfRulesTested int

	// This only counts the loci which are used for rules
	// For example, loci that are only used in neural-network-based prediction are not counted
	QuantityOfLociKnown int
}


type PersonNumericTraitInfo struct{

	// This map contains the person's trait info for each genome
	// If no map entries exist, then no trait info is known
	// Map Structure: Genome Identifier -> PersonGenomeNumericTraitInfo
	TraitInfoMap map[[16]byte]PersonGenomeNumericTraitInfo

	// This is true if there are multiple genomes and the results from each genome differ
	ConflictExists bool
}

type PersonGenomeNumericTraitInfo struct{

	// The predicted outcome (Example: The predicted height for this person, in centimeters)
	PredictedOutcome float64

	// This map stores the confidence ranges for the predicted value
	// If we want to know how accurate the prediction is with a X% accuracy, how far would we have to expand the
	//		predicted value's range to be accurate, X% of the time?
	// For example: 50% accuracy requires a +/-5 point range, 80% accuracy requires a +-15 point range
	// Map Structure: Accuracy probability (0-100) -> Amount to add to value in both +/- directions so prediction is that accurate
	ConfidenceRangesMap map[int]float64

	QuantityOfLociKnown int

	QuantityOfPhasedLoci int
}


type CoupleAnalysis struct{

	AnalysisVersion int

	Pair1Person1GenomeIdentifier [16]byte
	Pair1Person2GenomeIdentifier [16]byte

	// This is only true if at least 1 person has more than 1 genome
	SecondPairExists bool

	// These are empty unless SecondPairExists == true
	Pair2Person1GenomeIdentifier [16]byte
	Pair2Person2GenomeIdentifier [16]byte

	Person1HasMultipleGenomes bool
	Person2HasMultipleGenomes bool

	// These are empty unless Person1HasMultipleGenomes == true
	Person1OnlyExcludeConflictsGenomeIdentifier [16]byte
	Person1OnlyIncludeSharedGenomeIdentifier [16]byte

	// These are empty unless Person2HasMultipleGenomes == true
	Person2OnlyExcludeConflictsGenomeIdentifier [16]byte
	Person2OnlyIncludeSharedGenomeIdentifier [16]byte

	// Map Structure: Disease Name -> OffspringMonogenicDiseaseInfo
	MonogenicDiseasesMap map[string]OffspringMonogenicDiseaseInfo

	// Map Structure: Disease Name -> OffspringPolygenicDiseaseInfo
	PolygenicDiseasesMap map[string]OffspringPolygenicDiseaseInfo

	// Discrete traits are traits with discrete outcomes, such as Eye Color
	// Map Structure: Trait Name -> Trait Info Object
	DiscreteTraitsMap map[string]OffspringDiscreteTraitInfo

	// Numeric traits are traits with numeric outcomes, such as Height
	// Map Structure: Trait Name -> Trait Info Object
	NumericTraitsMap map[string]OffspringNumericTraitInfo
}


type OffspringMonogenicDiseaseInfo struct{

	// This map stores the quantity of variants tested in each person's genome
	// Map Structure: Genome Identifier -> Number of variants tested
	QuantityOfVariantsTestedMap map[[16]byte]int

	// This map stores the offspring disease probabilities for each genome pair.
	// A genome pair is a concatenation of two genome identifiers
	// If a map entry doesn't exist, the probabilities are unknown for that genome pair
	// Map Structure: Genome Pair Identifier -> OffspringGenomePairMonogenicDiseaseInfo
	MonogenicDiseaseInfoMap map[[32]byte]OffspringGenomePairMonogenicDiseaseInfo

	// This is true if there is more than 1 genome pair and the results from each genome pair differ
	ConflictExists bool
}


type OffspringGenomePairMonogenicDiseaseInfo struct{

	// At least 1 variant's information is needed from either person to include the diseaseInfo object in the MonogenicDiseaseInfoMap
	ProbabilityOffspringHasDiseaseIsKnown bool

	// This is the probability that the offspring will have the disease
	// Is a number between 0-100%
	ProbabilityOffspringHasDisease int

	ProbabilityOffspringHasVariantIsKnown bool

	// This is the probability that the offspring will have a variant
	// Is a number between 0-100%
	ProbabilityOffspringHasVariant int

	// Map Structure: Variant Identifier -> OffspringMonogenicDiseaseVariantInfo
	VariantsInfoMap map[[3]byte]OffspringMonogenicDiseaseVariantInfo
}

type OffspringMonogenicDiseaseVariantInfo struct{

	// These are all numbers between 0-100%
	ProbabilityOf0MutationsLowerBound int
	ProbabilityOf0MutationsUpperBound int

	ProbabilityOf1MutationLowerBound int
	ProbabilityOf1MutationUpperBound int

	ProbabilityOf2MutationsLowerBound int
	ProbabilityOf2MutationsUpperBound int
}

type OffspringPolygenicDiseaseInfo struct{

	// This map stores the polygenic disease info for each genome pair
	// Map Structure: Genome Pair Identifier -> OffspringGenomePairPolygenicDiseaseInfo
	PolygenicDiseaseInfoMap map[[32]byte]OffspringGenomePairPolygenicDiseaseInfo

	// This is true if there is more than 1 genome pair and the results from each genome pair differ
	ConflictExists bool
}


type OffspringGenomePairPolygenicDiseaseInfo struct{

	// A number between 1-10 representing the offspring's average risk score
	// 1 == lowest risk, 10 == highest risk
	OffspringAverageRiskScore int

	// This map stores the confidence ranges for the predicted risk score
	// If we want to know how accurate the prediction is with a X% accuracy, how far would we have to expand the
	//		risk score's range to be accurate, X% of the time?
	// For example: 50% accuracy requires a +/-2 point range, 80% accuracy requires a +-3 point range
	// Map Structure: Accuracy probability (0-100) -> Amount to add to value in both +/- directions so prediction is that accurate
	PredictionConfidenceRangesMap map[int]float64

	QuantityOfLociKnown int

	// This describes the quantity of loci from both parents that are phased
	// For example, if there are 10 loci for this trait, and one parent has 10 phased loci and the other has 5,
	//		this variable will have a value of 15
	QuantityOfParentalPhasedLoci int

	// This is a list of prospective offspring risk scores
	// This is useful for plotting on a graph to understand the standard deviation of risk
	SampleOffspringRiskScoresList []int
}


type OffspringDiscreteTraitInfo struct{

	// This map stores the trait info for each genome pair
	// Map Structure: Genome Pair Identifier -> OffspringGenomePairTraitInfo
	TraitInfoMap map[[32]byte]OffspringGenomePairDiscreteTraitInfo

	ConflictExists bool
}

// For a trait analysis, both analysis methods may exist in the results
// However, the GUI will only display the results from one of the methods.
// The neural network prediction is always prioritized over the rule-based prediction
type OffspringGenomePairDiscreteTraitInfo struct{

	// This is true if it is possible to analyze this trait using a neural network
	NeuralNetworkExists bool

	// This is true if a neural network analysis was performed for this genome
	// This means that at least 1 locus for this trait was contained in both of the genomes in the pair
	NeuralNetworkAnalysisExists bool

	NeuralNetworkAnalysis OffspringGenomePairDiscreteTraitInfo_NeuralNetwork

	// This is true if it is possible to analyze this trait using rules
	RulesExist bool

	// This is true if a rules-based analysis was performed for this genome
	// This means that all of the loci for at least 1 rule for this trait was contained in both of the genomes in the pair
	// Also, none of the offspring have an unknown outcome caused by an outcome score tie
	RulesAnalysisExists bool

	RulesAnalysis OffspringGenomePairDiscreteTraitInfo_Rules
}


type OffspringGenomePairDiscreteTraitInfo_NeuralNetwork struct{

	// Map Structure: Outcome Name -> Outcome Probability (0-100)
	// Example: "Intolerant" -> 5
	OffspringOutcomeProbabilitiesMap map[string]int

	// Probability (0-100) that each outcome from the neural network is true
	// This is an average of the confidence for each of the calculated 100 outcome probabilities
	AverageConfidence int

	QuantityOfLociKnown int

	// This describes the quantity of loci from both parents that are phased
	// For example, if there are 10 loci for this trait, and one parent has 10 phased loci and the other has 5,
	//		this variable will have a value of 15
	QuantityOfParentalPhasedLoci int
}

type OffspringGenomePairDiscreteTraitInfo_Rules struct{

	// Map Structure: Outcome Name -> Outcome Probability (0-100)
	// Example: "Intolerant" -> 5
	OffspringOutcomeProbabilitiesMap map[string]int

	// Map Structure: Rule Identifier -> Offspring Probability Of Passing Rule
	// The value stores the probability that the offspring will pass the rule
	// This is a number between 0-100%
	ProbabilityOfPassingRulesMap map[[3]byte]int

	// This should be len(ProbabilityOfPassingRulesMap)
	QuantityOfRulesTested int

	// This only counts the loci which are used for rules
	// For example, loci that are only used in neural-network-based prediction are not counted
	QuantityOfLociKnown int
}

type OffspringNumericTraitInfo struct{

	// This map stores the trait info for each genome pair
	// Map Structure: Genome Pair Identifier -> OffspringGenomePairNumericTraitInfo
	TraitInfoMap map[[32]byte]OffspringGenomePairNumericTraitInfo

	ConflictExists bool
}

type OffspringGenomePairNumericTraitInfo struct{

	// The average outcome for the offspring
	// For example, the average height for an offspring between these 2 people
	OffspringAverageOutcome float64

	// This map stores the confidence ranges for the predicted value
	// If we want to know how accurate the prediction is with a X% accuracy, how far would we have to expand the
	//		predicted value's range to be accurate, X% of the time?
	// For example: 50% accuracy requires a +/-5 point range, 80% accuracy requires a +-15 point range
	// Map Structure: Accuracy probability (0-100) -> Amount to add to value in both +/- directions so prediction is that accurate
	PredictionConfidenceRangesMap map[int]float64

	QuantityOfLociKnown int

	// This describes the quantity of loci from both parents that are phased
	// For example, if there are 10 loci for this trait, and one parent has 10 phased loci and the other has 5,
	//		this variable will have a value of 15
	QuantityOfParentalPhasedLoci int

	// A list of 100 offspring outcomes for 100 prospective offspring from the genome pair
	// Example: A list of heights for 100 prospective offspring
	SampleOffspringOutcomesList []float64
}