REFINED (REpresentation of Features as Images with NEighborhood Dependencies): A novel feature representation for Convolutional Neural Networks

TL;DR

The paper introduces REFINED, a novel image-based feature representation for non-image data that enhances convolutional neural network performance by capturing feature correlations, leading to more accurate predictions in biological datasets.

Contribution

REFINED is a new method that transforms high-dimensional features into images based on feature correlations, enabling CNNs to better utilize non-spatial data for improved predictive accuracy.

Findings

REFINED outperforms traditional models like Random Forests and SVMs in prediction accuracy.

The approach effectively captures feature correlations, aiding in embedded feature selection.

Demonstrated superior performance on synthetic and biological datasets.

Abstract

Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features or features without spatial correlations. We present a novel approach for representation of high dimensional feature vector in a compact image form, termed REFINED (REpresentation of Features as Images with NEighborhood Dependencies), that is conducible for convolutional neural network based deep learning. We consider the correlations between features to generate a compact representation of the features in the form of a two-dimensional image using minimization of pairwise distances similar to multi-dimensional scaling. We hypothesize that this approach enables embedded feature selection and integrated with Convolutional Neural Network based Deep Learning can produce more accurate predictions as compared to Artificial Neural Networks, Random Forests and Support Vector Regression. We illustrate the superior predictive performance of the proposed representation, as compared to existing approaches, using synthetic datasets, cell line efficacy prediction based on drug chemical descriptors for NCI60 dataset and drug sensitivity prediction based on transcriptomic data and chemical descriptors using GDSC dataset. Results illustrated on both synthetic and biological datasets shows the higher prediction accuracy of the proposed framework as compared to existing methodologies while maintaining desirable properties in terms of bias and feature extraction.