MF-ProtDisMap: protein real-valued distance prediction with fusion of sequence and coevolutionary features

Abstract

The precise estimation of protein inter-residue distances is essential for high-accuracy protein structure modeling. Currently, the prediction methods are predominantly based on MSA-derived coevolutionary features or language model-based sequence features. To effectively leverage the strengths of both methods, this study developed MF-ProtDisMap (Multi-Feature Protein Distance Map), an integrative framework that effectively combines both feature types to achieve superior real-valued distance prediction. Briefly, MSA Transformer is employed to extract the coevolutionary features from protein multiple sequence alignments, whereas ESM2 is used to capture long-range interactions and sequence-level features. To reduce the computational cost while maximizing the representation of fused feature information, we adopt group pooling for feature dimensionality reduction and introduce Diff-former-a novel module combining a diffusion model with a triangular attention mechanism to enhance representation learning. MF-ProtDisMap achieved a MAE of 2.20 Å and an RMSE of 3.40 Å in the protein real-valued distance prediction task. The predicted distances can be converted into contact results, achieving ROC and PR values of 84.56 % and 81.01 %, respectively. These results demonstrate that MF-ProtDisMap outperforms state-of-the-art real-valued protein distance methods.