Highly Scalable Tensor Factorization for Prediction of Drug-Protein Interaction Type

TL;DR

This paper introduces Macau, a scalable tensor factorization method that integrates high-dimensional compound features and multiple measurement types to predict drug-protein interaction types, especially inhibitory interactions.

Contribution

The paper presents Macau, a novel tensor factorization approach with a noise injection MCMC sampler that efficiently incorporates high-dimensional side information for large-scale drug-protein interaction prediction.

Findings

Successfully identified latent subspace separating IC50 and Ki measurement types.

Detected competitive inhibitory activity between compounds and proteins.

Scalable to millions of compounds with high-dimensional features.

Abstract

The understanding of the type of inhibitory interaction plays an important role in drug design. Therefore, researchers are interested to know whether a drug has competitive or non-competitive interaction to particular protein targets. Method: to analyze the interaction types we propose factorization method Macau which allows us to combine different measurement types into a single tensor together with proteins and compounds. The compounds are characterized by high dimensional 2D ECFP fingerprints. The novelty of the proposed method is that using a specially designed noise injection MCMC sampler it can incorporate high dimensional side information, i.e., millions of unique 2D ECFP compound features, even for large scale datasets of millions of compounds. Without the side information, in this case, the tensor factorization would be practically futile. Results: using public IC50 and Ki data from ChEMBL we trained a model from where we can identify the latent subspace separating the two measurement types (IC50 and Ki). The results suggest the proposed method can detect the competitive inhibitory activity between compounds and proteins.