ProteinDataLoader<T>

Models & Types · AiDotNet.Data.Graph

Loads protein structure datasets as flattened feature/label tensors for graph-level classification.

Inheritance: DataLoaderBase<T> → InputOutputDataLoaderBase<T, Tensor<T>, Tensor<T>> → ProteinDataLoader<T>

How It Works

Expects a directory structure with protein files in CSV or TSV format:

Features are flattened residue features Tensor[N, MaxResidues * FeatureDimension]. Labels are functional class index Tensor[N, 1].

Constructors

Constructor Summary
ProteinDataLoader(ProteinDataLoaderOptions options)

Properties

Property Summary
int FeatureCount { get; }
int OutputDimension { get; }
int TotalCount { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
ValueTuple<IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>, IInputOutputDataLoader<T, Tensor<T>, Tensor<T>>> Split(double trainRatio, double validationRatio, int? seed)