Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9,844 changes: 9,402 additions & 442 deletions docs/schema/valuesets.yaml

Large diffs are not rendered by default.

1,375 changes: 1,374 additions & 1 deletion project/jsonschema/valuesets.schema.json

Large diffs are not rendered by default.

2,325 changes: 2,325 additions & 0 deletions src/valuesets/datamodel/valuesets.py

Large diffs are not rendered by default.

2,325 changes: 2,325 additions & 0 deletions src/valuesets/datamodel/valuesets_pydantic.py

Large diffs are not rendered by default.

83 changes: 82 additions & 1 deletion src/valuesets/enums/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@
from .bioprocessing.scale_up import ProcessScaleEnum, BioreactorTypeEnum, FermentationModeEnum, OxygenationStrategyEnum, AgitationTypeEnum, DownstreamProcessEnum, FeedstockTypeEnum, ProductTypeEnum, SterilizationMethodEnum

# Business domain
from .business.currencies import CurrencyCode
from .business.human_resources import EmploymentTypeEnum, JobLevelEnum, HRFunctionEnum, CompensationTypeEnum, PerformanceRatingEnum, RecruitmentSourceEnum, TrainingTypeEnum, EmployeeStatusEnum, WorkArrangementEnum, BenefitsCategoryEnum
from .business.industry_classifications import NAICSSectorEnum, EconomicSectorEnum, BusinessActivityTypeEnum, IndustryMaturityEnum, MarketStructureEnum, IndustryRegulationLevelEnum
from .business.management_operations import ManagementMethodologyEnum, StrategicFrameworkEnum, OperationalModelEnum, PerformanceMeasurementEnum, DecisionMakingStyleEnum, LeadershipStyleEnum, BusinessProcessTypeEnum
Expand All @@ -79,10 +80,12 @@

# Chemistry domain
from .chemistry.chemical_entities import SubatomicParticleEnum, BondTypeEnum, PeriodicTableBlockEnum, ElementFamilyEnum, ElementMetallicClassificationEnum, HardOrSoftEnum, BronstedAcidBaseRoleEnum, LewisAcidBaseRoleEnum, OxidationStateEnum, ChiralityEnum, NanostructureMorphologyEnum
from .chemistry.identifiers import ChemicalIdentifierScheme
from .chemistry.reaction_directionality import RelativeTimeEnum, PresenceEnum, ReactionDirectionality
from .chemistry.reactions import ReactionTypeEnum, ReactionMechanismEnum, CatalystTypeEnum, ReactionConditionEnum, ReactionRateOrderEnum, EnzymeClassEnum, SolventClassEnum, ThermodynamicParameterEnum

# Clinical domain
from .clinical.gene2phenotype import G2PConfidenceCategory, G2PAllelicRequirement, G2PCrossCuttingModifier, G2PMolecularMechanism, G2PMolecularMechanismSynopsis, G2PMolecularMechanismSupport, G2PMechanismEvidenceCategory, G2PFunctionEvidence, G2PFunctionalAlterationEvidence, G2PModelsEvidence, G2PRescueEvidence, G2PVariantConsequence, G2PVariantTypeGroup, G2PVariantType, G2PPanel
from .clinical.genetics import ModeOfInheritance
from .clinical.nih_demographics import RaceOMB1997Enum, EthnicityOMB1997Enum, BiologicalSexEnum, AgeGroupEnum, ParticipantVitalStatusEnum, RecruitmentStatusEnum, StudyPhaseEnum
from .clinical.phenopackets import KaryotypicSexEnum, PhenotypicSexEnum, AllelicStateEnum, LateralityEnum, OnsetTimingEnum, ACMGPathogenicityEnum, TherapeuticActionabilityEnum, InterpretationProgressEnum, RegimenStatusEnum, DrugResponseEnum
Expand All @@ -99,6 +102,8 @@
from .computing.mime_types import MimeType, MimeTypeCategory, TextCharset, CompressionType
from .computing.ontologies import OWLProfileEnum
from .computing.quantum import QubitType, QuantumAlgorithmCategoryType
from .computing.systems_engineering import SystemLifeCycleProcess15288
from .computing.verification_validation_ieee_1012 import VerificationValidationProcessIEEE1012

# Core domain
from .confidence_levels import RelativeTimeEnum, PresenceEnum, ConfidenceLevel, CIOConfidenceLevel, OBCSCertaintyLevel, IPCCLikelihoodScale, IPCCConfidenceLevel, NCITFivePointConfidenceScale
Expand Down Expand Up @@ -203,7 +208,10 @@

# Medical domain
from .medical.clinical import BloodTypeEnum, AnatomicalSystemEnum, MedicalSpecialtyEnum, DrugRouteEnum, VitalSignEnum, DiagnosticTestTypeEnum, SymptomSeverityEnum, AllergyTypeEnum, VaccineTypeEnum, BMIClassificationEnum
from .medical.dicom import DICOMModalityEnum, DICOMValueRepresentationEnum, DICOMAttributeTypeEnum, DICOMTransferSyntaxEnum, DICOMNetworkServiceEnum, DICOMSoftwareToolEnum
from .medical.family_history import FamilyRelationship, FamilyHistoryStatus, GeneticRelationship
from .medical.imaging_data_management import ImagingDataLifecycleStageEnum, ImagingDataSourceTypeEnum, DICOMValidationIssueTypeEnum, ImageQualityMetricEnum, ImagingInteroperabilityStandardEnum, Bridge2AIDataGenerationProjectEnum
from .medical.imaging_deidentification import DICOMDeidentificationMethodEnum, DICOMDeidentificationActionEnum, ImageDeidentificationTargetEnum, DeidentificationRegulatoryFrameworkEnum, DefacingMethodEnum, DefacingToolEnum
from .medical.imaging_platforms import MRIPlatformEnum, MicroscopyPlatformEnum, ImagingSystemPlatformEnum
from .medical.neuroimaging import MRIModalityEnum, MRISequenceTypeEnum, MRIContrastTypeEnum, FMRIParadigmTypeEnum
from .medical.oncology.icdo import TumorTopography, TumorMorphology, TumorBehavior, TumorGrade
Expand All @@ -221,6 +229,13 @@
from .preservation.events import PreservationEventType, PreservationEventOutcome
from .preservation.fixity import CryptographicHashFunction

# Process_Engineering domain
from .process_engineering.process_industries import ProcessIndustryCategory, ProcessOperationMode
from .process_engineering.process_modeling import DesignSimulationMethod, FlowsheetSolutionApproach, ProcessSimulator
from .process_engineering.process_streams import ProcessStreamRole, ProcessStreamPhase, UtilityType
from .process_engineering.thermodynamics import EquationOfStateModel, ActivityCoefficientModel, ThermodynamicPropertyPackage, MixingRuleModel, PoyntingCorrectionMethod
from .process_engineering.unit_operations import UnitOperationType, ProcessEquipmentType

# Publishing domain
from .publishing.arxiv_categories import ArxivCategory
from .publishing.osti_record import OstiWorkflowStatus, OstiAccessLimitation, OstiCollectionType, OstiSensitivityFlag, OstiOrganizationIdentifierType, OstiProductType, OstiOrganizationType, OstiPersonType, OstiContributorType, OstiRelatedIdentifierType, OstiRelationType, OstiIdentifierType, OstiGeolocationType, OstiMediaLocationType
Expand All @@ -234,12 +249,13 @@

# Statistics domain
from .statistics.prediction_outcomes import OutcomeTypeEnum
from .statistics.statistical_tests import StatisticalTestEnum, TTestTypeEnum, NormalityTestEnum, HomoscedasticityTestEnum, PostHocTestEnum, MultipleTestingCorrectionEnum, CorrelationCoefficientEnum, TestTailednessEnum, DistributionalAssumptionEnum, ComparisonObjectiveEnum

# Time domain
from .time.temporal import DayOfWeek, Month, Quarter, Season, TimePeriod, TimeOfDay, BusinessTimeFrame, GeologicalEra, HistoricalPeriod

# Units domain
from .units.measurements import LengthUnitEnum, MassUnitEnum, VolumeUnitEnum, TemperatureUnitEnum, TimeUnitEnum, PressureUnitEnum, ConcentrationUnitEnum, FrequencyUnitEnum, AngleUnitEnum, DataSizeUnitEnum
from .units.measurements import LengthUnitEnum, MassUnitEnum, VolumeUnitEnum, TemperatureUnitEnum, TimeUnitEnum, PressureUnitEnum, ConcentrationUnitEnum, FrequencyUnitEnum, AngleUnitEnum, DataSizeUnitEnum, MassFlowRateUnitEnum, MolarFlowRateUnitEnum, VolumetricFlowRateUnitEnum
from .units.quantity_kinds import QuantityKindEnum

# Visual domain
Expand All @@ -250,6 +266,7 @@
"AcademicDegree",
"AccessRights",
"AcousticRadiationTypeEnum",
"ActivityCoefficientModel",
"AdditiveManufacturingEnum",
"AgeGroupEnum",
"AgitationTypeEnum",
Expand Down Expand Up @@ -305,6 +322,7 @@
"BloodTypeEnum",
"BondTypeEnum",
"BravaisLatticeEnum",
"Bridge2AIDataGenerationProjectEnum",
"BronstedAcidBaseRoleEnum",
"BuildingEnergyPerformanceLevel",
"BuildingEnergyStandard",
Expand Down Expand Up @@ -334,6 +352,7 @@
"CellPolarity",
"CellProliferationState",
"CellularityEnum",
"ChemicalIdentifierScheme",
"ChipFabricationNodeType",
"ChiralityEnum",
"ChromatographyType",
Expand All @@ -347,6 +366,7 @@
"CommonMineral",
"CommonOrganismTaxaEnum",
"CommunicationProtocolEnum",
"ComparisonObjectiveEnum",
"CompassDirection",
"CompensationTypeEnum",
"ComplianceStandardEnum",
Expand All @@ -365,6 +385,7 @@
"CoordinationGeometry",
"CopyrightStatus",
"CorporateGovernanceRoleEnum",
"CorrelationCoefficientEnum",
"CountryCodeISO2Enum",
"CountryCodeISO3Enum",
"CriticalMineral",
Expand All @@ -375,7 +396,17 @@
"CrystalSystemEnum",
"CrystallizationMethod",
"CurrencyChemical",
"CurrencyCode",
"CurrencyCodeISO4217Enum",
"DICOMAttributeTypeEnum",
"DICOMDeidentificationActionEnum",
"DICOMDeidentificationMethodEnum",
"DICOMModalityEnum",
"DICOMNetworkServiceEnum",
"DICOMSoftwareToolEnum",
"DICOMTransferSyntaxEnum",
"DICOMValidationIssueTypeEnum",
"DICOMValueRepresentationEnum",
"DNABaseEnum",
"DNABaseExtendedEnum",
"DNADamageResponse",
Expand All @@ -399,14 +430,19 @@
"DayOfWeek",
"DecisionMakingStyleEnum",
"DecommissioningPhaseType",
"DefacingMethodEnum",
"DefacingToolEnum",
"DefectClassificationEnum",
"DefenseInDepthLevelEnum",
"DeidentificationRegulatoryFrameworkEnum",
"DerivatizationMethod",
"DesignSimulationMethod",
"DetectionModeEnum",
"Detector",
"DetectorType",
"DiagnosticTestTypeEnum",
"DigitalObjectCategory",
"DistributionalAssumptionEnum",
"DocumentFormatEnum",
"DownstreamProcessEnum",
"DrugExposureProvenanceEnum",
Expand Down Expand Up @@ -438,6 +474,7 @@
"EnvironmentalImpact",
"EnzymeClassEnum",
"EnzymologyAssayEnum",
"EquationOfStateModel",
"EthnicityOMB1997Enum",
"ExecutionModeEnum",
"ExperimentalDesignMethodType",
Expand Down Expand Up @@ -469,6 +506,7 @@
"FireSafetyColorEnum",
"FissileIsotopeEnum",
"FlowerColorEnum",
"FlowsheetSolutionApproach",
"FoodColoringEnum",
"FossilFuelTypeEnum",
"FraudDetectionEnum",
Expand All @@ -484,6 +522,21 @@
"FusionConfinementType",
"FusionFuelType",
"FusionPlasmaParameterType",
"G2PAllelicRequirement",
"G2PConfidenceCategory",
"G2PCrossCuttingModifier",
"G2PFunctionEvidence",
"G2PFunctionalAlterationEvidence",
"G2PMechanismEvidenceCategory",
"G2PModelsEvidence",
"G2PMolecularMechanism",
"G2PMolecularMechanismSupport",
"G2PMolecularMechanismSynopsis",
"G2PPanel",
"G2PRescueEvidence",
"G2PVariantConsequence",
"G2PVariantType",
"G2PVariantTypeGroup",
"GOAspect",
"GOElectronicMethods",
"GOEvidenceCode",
Expand Down Expand Up @@ -518,6 +571,7 @@
"HeavyMetalEnum",
"HistoricalPeriod",
"HistoricalStatusEnum",
"HomoscedasticityTestEnum",
"HousingStatus",
"HumanAgeGroupEnum",
"HumanDevelopmentalStage",
Expand All @@ -538,8 +592,13 @@
"IUPACAminoAcidCode",
"IUPACNucleotideCode",
"ImageDefinedRiskFactor",
"ImageDeidentificationTargetEnum",
"ImageFileFormatEnum",
"ImageQualityMetricEnum",
"ImagingAssayEnum",
"ImagingDataLifecycleStageEnum",
"ImagingDataSourceTypeEnum",
"ImagingInteroperabilityStandardEnum",
"ImagingSystemPlatformEnum",
"ImmunologyAssayEnum",
"InSituChemistryRegime",
Expand Down Expand Up @@ -597,6 +656,7 @@
"MaritimeSignalColorEnum",
"MarketStructureEnum",
"MassErrorUnit",
"MassFlowRateUnitEnum",
"MassSpectrometerFileFormat",
"MassSpectrometerVendor",
"MassSpectrometryAssayEnum",
Expand Down Expand Up @@ -625,11 +685,14 @@
"MiningPhase",
"MiningType",
"MitoticPhase",
"MixingRuleModel",
"ModeOfInheritance",
"ModelSystemTypeEnum",
"MolarFlowRateUnitEnum",
"Month",
"MouseDevelopmentalStage",
"MousePostnatalAgeGroupEnum",
"MultipleTestingCorrectionEnum",
"NAICSSectorEnum",
"NCITFivePointConfidenceScale",
"NIHInstituteCenterEnum",
Expand All @@ -640,6 +703,7 @@
"NetworkProtocolEnum",
"NeuroblastomaRiskGroup",
"NewsTopicCategoryEnum",
"NormalityTestEnum",
"NuclearFacilityTypeEnum",
"NuclearForensicsMethodType",
"NuclearFuelCycleStageEnum",
Expand Down Expand Up @@ -708,8 +772,10 @@
"PlateCoatingEnum",
"PlateMaterialEnum",
"PolymerTypeEnum",
"PostHocTestEnum",
"PowerPlantStatusEnum",
"PowerUnit",
"PoyntingCorrectionMethod",
"PredictionOutcomeType",
"PresenceEnum",
"PreservationEventOutcome",
Expand All @@ -718,9 +784,15 @@
"PreservationLevelValue",
"PressureUnitEnum",
"PriorityLevelEnum",
"ProcessEquipmentType",
"ProcessImprovementApproachEnum",
"ProcessIndustryCategory",
"ProcessOperationMode",
"ProcessPerformanceMetric",
"ProcessScaleEnum",
"ProcessSimulator",
"ProcessStreamPhase",
"ProcessStreamRole",
"ProcessingStatus",
"ProcurementTypeEnum",
"ProductTypeEnum",
Expand Down Expand Up @@ -836,6 +908,7 @@
"StandardsMaturityLevel",
"StandardsOrganizationEnum",
"StateOfMatterEnum",
"StatisticalTestEnum",
"StatusEnum",
"SterilizationMethodEnum",
"StrandType",
Expand All @@ -852,11 +925,14 @@
"SupplyChainStrategyEnum",
"SymptomSeverityEnum",
"SynthesisMethodEnum",
"SystemLifeCycleProcess15288",
"TTestTypeEnum",
"TailingCharacterizationType",
"TaxonomicRank",
"TechnologyReadinessLevel",
"TemperatureUnitEnum",
"TemporalAggregationEnum",
"TestTailednessEnum",
"TextCharset",
"TextureEnum",
"TherapeuticActionabilityEnum",
Expand All @@ -865,6 +941,7 @@
"ThermalCyclerTypeEnum",
"ThermalCyclingStepEnum",
"ThermodynamicParameterEnum",
"ThermodynamicPropertyPackage",
"TimeOfDay",
"TimePeriod",
"TimeUnitEnum",
Expand All @@ -889,15 +966,18 @@
"USStateCodeEnum",
"UnconventionalMineralResourceType",
"UniProtSpeciesCode",
"UnitOperationType",
"UpdateFrequency",
"UraniumEnrichmentLevelEnum",
"UtilityType",
"VaccinationPeriodicityEnum",
"VaccinationStatusEnum",
"VaccineCategoryEnum",
"VaccineTypeEnum",
"ValueSetStewardEnum",
"VectorTypeEnum",
"VendorCategoryEnum",
"VerificationValidationProcessIEEE1012",
"ViabilityEnum",
"VideoFormatEnum",
"ViralGenomeTypeEnum",
Expand All @@ -906,6 +986,7 @@
"VitalStatusEnum",
"VitrificationMethod",
"VolumeUnitEnum",
"VolumetricFlowRateUnitEnum",
"WasteDisposalMethodEnum",
"WasteFacilityTypeEnum",
"WasteHalfLifeCategoryEnum",
Expand Down
4 changes: 2 additions & 2 deletions src/valuesets/enums/bio/expression_units.py
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,8 @@ class ExpressionUnitEnum(RichEnum):
"NORMALIZED_COUNTS": {'description': 'Counts normalized by a method such as DESeq2 or edgeR', 'annotations': {'normalization': 'library size', 'use': 'differential expression'}, 'aliases': ['Normalized Counts']},
"COUNTS": {'description': 'General read counts category', 'aliases': ['Counts']},
"TPM": {'description': 'Transcripts per million - normalized for gene length and sequencing depth', 'meaning': 'NCIT:C181327', 'annotations': {'normalization': 'length and depth', 'use': 'within and between sample comparisons', 'formula': '(reads/gene_length_kb) / sum(reads/gene_length_kb) * 1e6'}, 'aliases': ['Transcript per million']},
"FPKM": {'description': 'Fragments per kilobase of transcript per million reads mapped', 'meaning': 'STATO:0000172', 'annotations': {'normalization': 'length and depth', 'use': 'within-sample comparisons', 'library_type': 'paired-end'}, 'aliases': ['Fragments per kilobase of transcript per million reads mapped']},
"RPKM": {'description': 'Reads per kilobase of transcript per million reads mapped', 'meaning': 'STATO:0000206', 'annotations': {'normalization': 'length and depth', 'use': 'within-sample comparisons', 'library_type': 'single-end'}, 'aliases': ['Reads per kilobase of transcript per million reads mapped']},
"FPKM": {'description': 'Fragments per kilobase of transcript per million reads mapped', 'meaning': 'STATO:0000172', 'annotations': {'normalization': 'length and depth', 'use': 'within-sample comparisons', 'library_type': 'paired-end'}, 'aliases': ['Fragments per kilobase of transcript per million reads mapped', 'FPKM-fragments per kilobase of transcript per million fragments mapped']},
"RPKM": {'description': 'Reads per kilobase of transcript per million reads mapped', 'meaning': 'STATO:0000206', 'annotations': {'normalization': 'length and depth', 'use': 'within-sample comparisons', 'library_type': 'single-end'}, 'aliases': ['Reads per kilobase of transcript per million reads mapped', 'RPKM-reads per kilobase of transcript per million fragments mapped']},
"CPM": {'description': 'Counts per million reads', 'annotations': {'normalization': 'depth only'}, 'aliases': ['Counts per million']},
"RPKM_UQ": {'description': 'RPKM with upper quartile normalization', 'annotations': {'normalization': 'length, depth, and upper quartile'}},
"VST": {'description': 'Variance stabilizing transformation values', 'annotations': {'method': 'DESeq2', 'use': 'visualization, clustering'}},
Expand Down
20 changes: 20 additions & 0 deletions src/valuesets/enums/bioprocessing/scale_up.py
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,16 @@ class DownstreamProcessEnum(RichEnum):
DISTILLATION = "DISTILLATION"
DRYING = "DRYING"
HOMOGENIZATION = "HOMOGENIZATION"
CLARIFICATION = "CLARIFICATION"
FLOCCULATION = "FLOCCULATION"
ULTRAFILTRATION = "ULTRAFILTRATION"
DIAFILTRATION = "DIAFILTRATION"
TANGENTIAL_FLOW_FILTRATION = "TANGENTIAL_FLOW_FILTRATION"
BUFFER_EXCHANGE = "BUFFER_EXCHANGE"
ADSORPTION = "ADSORPTION"
VIRAL_INACTIVATION = "VIRAL_INACTIVATION"
POLISHING = "POLISHING"
LYOPHILIZATION = "LYOPHILIZATION"

# Set metadata after class creation
DownstreamProcessEnum._metadata = {
Expand All @@ -151,6 +161,16 @@ class DownstreamProcessEnum(RichEnum):
"DISTILLATION": {'description': 'Distillation', 'meaning': 'CHMO:0001534', 'annotations': {'principle': 'Boiling point difference'}},
"DRYING": {'description': 'Drying operations', 'meaning': 'CHMO:0001551', 'annotations': {'types': 'Spray, freeze, vacuum'}},
"HOMOGENIZATION": {'description': 'Cell disruption/homogenization', 'annotations': {'methods': 'High pressure, bead mill'}},
"CLARIFICATION": {'description': 'Removal of cells and debris to produce a clarified harvest', 'annotations': {'methods': 'Centrifugation, depth filtration'}},
"FLOCCULATION": {'description': 'Aggregation of cells and debris into flocs to aid clarification'},
"ULTRAFILTRATION": {'description': 'Membrane concentration retaining macromolecules such as proteins', 'meaning': 'CHMO:0001645', 'annotations': {'mwco': 'Typically 1-1000 kDa'}},
"DIAFILTRATION": {'description': 'Buffer exchange and desalting by ultrafiltration with continuous makeup'},
"TANGENTIAL_FLOW_FILTRATION": {'description': 'Crossflow membrane filtration used for concentration and diafiltration', 'annotations': {'aliases': 'TFF, crossflow filtration'}},
"BUFFER_EXCHANGE": {'description': 'Replacement of the buffer matrix of a product stream'},
"ADSORPTION": {'description': 'Capture of product or impurities onto a solid sorbent'},
"VIRAL_INACTIVATION": {'description': 'Treatment step that inactivates potential viral contaminants', 'annotations': {'methods': 'Low pH, solvent/detergent, heat'}},
"POLISHING": {'description': 'Final chromatographic or filtration steps to remove trace impurities'},
"LYOPHILIZATION": {'description': 'Freeze-drying to produce a stable solid product', 'meaning': 'CHMO:0001553', 'annotations': {'aliases': 'freeze drying'}},
}

class FeedstockTypeEnum(RichEnum):
Expand Down
Loading