REFINED (REpresentation of Features as Images with NEighborhood Dependencies): A novel feature representation for Convolutional Neural Networks
This addresses the limitation of CNNs for non-image data in predictive modeling, particularly in drug sensitivity prediction, but is incremental as it adapts existing techniques for feature representation.
The authors tackled the problem of applying convolutional neural networks to non-image data by proposing REFINED, a method to convert high-dimensional feature vectors into images based on feature correlations, which achieved higher prediction accuracy on synthetic and biological datasets compared to existing methods like ANNs, Random Forests, and SVR.
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.