Overview of available features

Data Sources

DataSource: Base class for data sources.

Data sources are used to load data from a source programmatically.

Core

• Papyrus: Papyrus (See data collection with Papyrus tutorial.)

Data Filters

DataFilter: Base class for data filters.

Data filters are used to filter data based on some criteria. Examples can be found in the data preparation tutorial.

Core

• CategoryFilter: CategoryFilter

• RepeatsFilter: RepeatsFilter

Descriptor Sets

DescriptorSet: Base class for descriptor sets.

Descriptor sets are used to calculate molecular descriptors for a set of molecules. Examples can be found in the descriptor calculation tutorial.

Core

• DrugExPhyschem: DrugExPhyschem

• PredictorDesc:PredictorDesc

• RDKitDescs: RDKitDescs

• SmilesDescs: SmilesDescs

• TanimotoDistances: TanimotoDistances

• DataFrameDescriptorSet: DataFrameDescriptorSet

• Fingerprint: Fingerprint

  • AtomPairFP: AtomPairFP

  • AvalonFP: AvalonFP

  • LayeredFP: LayeredFP

  • MaccsFP: MaccsFP

  • MorganFP: MorganFP

  • PatternFP: PatternFP

  • RDKitFP: RDKitFP

  • RDKitMACCSFP: RDKitMACCSFP

  • TopologicalFP: TopologicalFP

Extra

• ExtendedValenceSignature: ExtendedValenceSignature

• Mold2: Mold2

• Mordred: Mordred

• PaDEL: PaDEL

• ProteinDescriptorSet: ProteinDescriptorSet

  • ProDec: ProDec

• Fingerprint: Fingerprint

  • CDKAtomPairs2DFP: CDKAtomPairs2DFP

  • CDKEStateFP: CDKEStateFP

  • CDKExtendedFP: CDKExtendedFP

  • CDKFP: CDKFP

  • CDKGraphOnlyFP: CDKGraphOnlyFP

  • CDKKlekotaRothFP: CDKKlekotaRothFP

  • CDKMACCSFP: CDKMACCSFP

  • CDKPubchemFP: CDKPubchemFP

  • CDKSubstructureFP: CDKSubstructureFP

Data Splitters

DataSplit: Base class for data splitters.

Data splitters are used to split data into training and test sets. Examples can be found in the data splitting tutorial.

Core

• RandomSplit: RandomSplit

• ScaffoldSplit: ScaffoldSplitter

• TemporalSplit: StratifiedSplitter

• ManualSplit: ManualSplit

• BootstrapSplit: BootstrapSplit

• GBMTDataSplit: GBMTDataSplit

  • GBMTRandomSplit: GBMTRandomSplit

  • ClusterSplit: ClusterSplit

Extra

• LeaveTargetsOut: LeaveTargetsOut

• PCMSplit: PCMSplit

  • TemporalPerTarget: TemporalPerTarget

Feature Filters

FeatureFilter: Base class for feature filters.

Feature filters are used to filter features based on some criteria. Examples can be found in the data preparation tutorial.

Core

• HighCorrelationFilter: HighCorrelationFilter

• LowVarianceFilter: LowVarianceFilter

• BorutaFilter: BorutaFilter (numpy version restricted to numpy<1.24.0)

Models

QSPRModel: Base class for models.

Models are used to predict properties of molecules. A general example can be found in the quick start tutorial. More detailed information can be found throughout the basic and advanced modelling tutorials.

Core

• SklearnModel: SklearnModel

Extra

• PCMModel: PCMModel (See PCM tutorial.)

GPU

More information can be found in the deep learning tutorial.

• DNNModel: DNNModel

• ChempropModel: ChempropModel (See Chemprop tutorial.)

• PyBoostModel: PyBoostModel

Metrics

Metric: Base class for metrics

Metrics are used to evaluate the performance of models. More information can be found in the model assessment tutorial.

Core

• SklearnMetrics: SklearnMetrics

• MaskedMetric: MaskedMetric

• CalibrationError: CalibrationError

• BEDROC: BEDROC

• EnrichmentFactor: EnrichmentFactor

• RobustInitialEnhancement: RobustInitialEnhancement

• Prevalence: Prevalence

• Sensitivity: Sensitivity

• Specificity: Specificity

• PositivePredictivity: PositivePredictivity

• NegativePredictivity: NegativePredictivity

• CohenKappa: CohenKappa

• BalancedPositivePredictivity: BalancedPositivePredictivity

• BalancedNegativePredictivity: BalancedNegativePredictivity

• BalancedMatthewsCorrcoeff: BalancedMatthewsCorrcoeff

• BalancedCohenKappa: BalancedCohenKappa

• KSlope: KSlope

• R20: R20

• KPrimeSlope: KPrimeSlope

• RPrime20: RPrime20

• Pearson: Pearson

• Spearman: Spearman

• Kendall: Kendall

• AverageFoldError: AverageFoldError

• AbsoluteAverageFoldError: AbsoluteAverageFoldError

• PercentageWithinFoldError: PercentageWithinFoldError

Model Assessors

ModelAssessor: Base class for model assessors.

Model assessors are used to assess the performance of models. More information be found in the model assessment tutorial.

Core

• CrossValAssessor: CrossValAssessor

• TestSetAssessor: TestSetAssessor

Hyperparameter Optimizers

HyperparameterOptimization: Base class for hyperparameter optimizers.

Hyperparameter optimizers are used to optimize the hyperparameters of models. More information can be found in the hyperparameter optimization tutorial.

Core

• GridSearchOptimization: GridSearchOptimization

• OptunaOptimization: OptunaOptimization

Model Plots

ModelPlot: Base class for model plots.

Model plots are used to visualize the performance of models. Examples can be found throughout the basic and advanced modelling tutorials.

Core

• RegressionPlot: RegressionPlot

  • CorrelationPlot: CorrelationPlot

  • WilliamsPlot: WilliamsPlot

• ClassifierPlot: ClassifierPlot

  • ROCPlot: ROCPlot

  • PRCPlot: PRCPlot

  • CalibrationPlot: CalibrationPlot

  • MetricsPlot: MetricsPlot

  • ConfusionMatrixPlot: ConfusionMatrixPlot

Monitors

• FitMonitor: Base class for monitoring model fitting

• AssessorMonitor: Base class for monitoring model assessment (subclass of FitMonitor)

• HyperparameterOptimizationMonitor: Base class for monitoring hyperparameter optimization (subclass of AssessorMonitor)

Monitors are used to monitor the training of models. More information can be found in the model monitoring tutorial.

Core

• NullMonitor: NullMonitor

• ListMonitor: ListMonitor

• BaseMonitor: BaseMonitor

  • FileMonitor: FileMonitor

  • WandBMonitor: WandBMonitor

Scaffolds

Scaffold: Base class for scaffolds.

Class for calculating molecular scaffolds of different kinds

Core

• Murcko: Murcko

• BemisMurcko: BemisMurcko

Clustering

MoleculeClusters: Base class for clustering molecules.

Classes for clustering molecules

Core

• RandomClusters: RandomClusters

• ScaffoldClusters: ScaffoldClusters

• FPSimilarityClusters: FPSimilarityClusters

  • FPSimilarityMaxMinClusters: FPSimilarityMaxMinClusters

  • FPSimilarityLeaderPickerClusters: FPSimilarityLeaderPickerClusters