wavFeatExt

wavFeatExt provides tools for simulating copy-number alteration (CNA) profiles, applying a non-decimated Haar wavelet transform to genomic signals, and extracting wavelet-derived features for use in supervised learning.

Key Features:

• CNA Profile Simulation: Simulates copy-number alteration profiles for generating genomic data.
• Wavelet Transform: Applies a non-decimated Haar wavelet transform to genomic signals.
• Feature Extraction: Extracts wavelet-derived features from transformed genomic signals.
• Machine Learning Methods: Implements lasso and elastic-net regularisation, random forest, partial least squares, neural networks, and k-nearest neighbours for training predictive models from genomic feature vectors.

Scientific Applications:

• Copy-number Alteration Analysis: Enables end-to-end analysis from CNA simulation to feature extraction and classification for genomic studies.

Methodology:

The workflow applies a non-decimated Haar wavelet transform to genomic signals, extracts wavelet-derived features, and trains predictive models using multiple machine learning methods including lasso and elastic-net regularisation, random forest, partial least squares, neural networks, and k-nearest neighbours.