FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning
Kalifa, D.; Singer, U.; Radinsky, K.
Show abstract
Accurate protein representations that integrate sequence and three-dimensional (3D) struc-ture are critical to many biological and biomedical tasks. Most existing models either ignore structure or combine it with sequence through a single, static fusion step. Here we present FusionProt, a unified model that learns representations via iterative, bidirectional fusion be-tween a protein language model and a structure encoder. A single learnable token serves as a carrier, alternating between sequence attention and spatial message passing across layers. FusionProt is evaluated on Enzyme Commission (EC), Gene Ontology (GO), and mutation stability prediction tasks. It improves Fmax by a median of +1.3 points (up to +2.0) across EC and GO benchmarks, and boosts AUROC by +3.6 points over the strongest baseline on mutation stability. Inference cost remains practical, with only [~] 2-5% runtime over-head. Beyond state-of-the-art performance, we further demonstrate FusionProts practical relevance through representative biological case studies, suggesting that the model captures biologically relevant features.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ProteinBERT: A universal deep-learning model of protein sequence and function 98%
- Pair-EGRET: enhancing the prediction of protein-proteininteraction sites through graph attention networks and protein language models 98%
- FAPM: Functional Annotation of Proteins using Multi-Modal Models Beyond Structural Modeling 97%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.