GenomicFeatureSelector<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.DomainSpecific
Feature selection for genomic/bioinformatics data.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → GenomicFeatureSelector<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
Genomic data often has millions of features (genes) but only a few hundred samples (patients). This selector uses techniques specifically designed for this challenging scenario, finding the few genes that truly matter for distinguishing between conditions.
How It Works
GenomicFeatureSelector is designed for high-dimensional genomic data such as gene expression profiles, SNPs, or methylation data. It addresses the “large p, small n” problem common in genomics and can incorporate gene grouping.
Constructors
| Constructor | Summary |
|---|---|
GenomicFeatureSelector(int nFeaturesToSelect, double variancePercentile, bool useFoldChangeFilter, double foldChangeThreshold, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> FeatureScores { get; } |
|
Vector<T> FoldChanges { get; } |
|
Vector<T> Variances { get; } |
|
bool SupportsInverseTransform { get; } |
|
bool UseFoldChangeFilter { get; } |
|
double FoldChangeThreshold { get; } |
|
double VariancePercentile { get; } |
|
int NFeaturesToSelect { get; } |
|
int[] SelectedIndices { get; } |
Methods
| Method | Summary |
|---|---|
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target) |
|
bool[] GetSupportMask() |
|
string[] GetFeatureNamesOut(string[] inputFeatureNames) |
|
void Fit(Matrix<T> data, Vector<T> target) |