Predictions of protein–protein interactions: Learning sequences and structures

Abstract

In view of understanding protein–protein interactions, we present a proof-of-principles workflow able to learn and make predictions. To this end, a neural network-based pipeline that integrates amino acid sequences with structural features is developed. At a first step, an undercomplete autoencoder compresses the high-dimensional protein sequence and structural into embeddings. These, and thereby the learned encoder together with protein–protein interaction scores from known databases, are passed to a supervised interaction-prediction network, which is constructed as a fully connected architecture. The latter can process embeddings of protein pairs and perform two tasks: (a) classify whether an interaction occurs (binary classification) or (b) predict this interaction through a score metric (regression). The use of structural data in addition to sequence data is assessed in view of an enhancement in the prediction. By this, a proof-of-principles investigation of protein interactions is demonstrated based on different embedding information. Our learning results underline the importance of sequence data rather than raw protein residue coordinates in the predictive workflow. The latter provides a modular prototype for follow-up, more extensive protein modeling, including larger proteins and sequence of variable sizes. This prototype workflow should be combined with physics-based modeling for enhanced information gain and a detailed insight into interaction and conformational aspects of protein complexes.