CrossPredGO: A Novel Light-weight Cross-modal Multi-attention Framework for Protein Function Prediction

Proteins are represented in various ways, each contributing differently to protein-related tasks. Here, information from each representation (protein sequence, 3D structure, and interaction data) is combined for an efficient protein function prediction task. Recently, uni-modal has produced promising results with state-of-the-art attention mechanisms that learn the relative importance of features, whereas multi-modal approaches have produced promising results by simply concatenating obtained features using a computational approach from different representations which leads to an increase in the overall trainable parameters. In this paper, we propose a novel, light-weight <italic>cross-modal multi-attention</italic> (CrMoMulAtt) mechanism that captures the relative contribution of each modality with a lower number of trainable parameters. The proposed mechanism shows a higher contribution from PPI and a lower contribution from structure data. The results obtained from the proposed CrossPredGO mechanism demonstrate an increment in <inline-formula><tex-math notation="LaTeX">$F_{max}$</tex-math></inline-formula> in the range of +(3.29 to 7.20)&#x0025; with at most 31&#x0025; lower trainable parameters compared with <italic>DeepGO</italic> and <italic>MultiPredGO</italic>.