AI Insight
EnsPlex is a new computational framework for predicting protein complex structures that combines multiple prediction methods (conformation-expanded docking, AlphaFold-Multimer, AlphaFold3, and Boltz-1) with a machine learning model called FACET to select the best candidates. Testing on 102 antigen-antibody systems showed EnsPlex achieved up to 27.8% better success rates compared to AlphaFold3 alone when selecting the same number of predicted structures. The approach addresses a key challenge in structural biology by both generating diverse candidate structures and accurately identifying which predictions are most likely correct.
Why it matters
Accurate prediction of protein complex structures is critical for drug discovery, vaccine design, and understanding immune responses. By improving prediction accuracy for antigen-antibody interactions specifically, this method could accelerate the development of therapeutic antibodies and help researchers better understand how antibodies recognize disease targets.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Protein complex structure prediction depends on both the breadth of candidate coverage and the ability to select accurate models within a limited output budget. Most existing approaches emphasize only one stage. End-to-end models and molecular docking workflows generate candidate structures, whereas quality-assessment models primarily rerank a predefined candidate pool. A complete strategy must account for complementary sampling across generators, differences among scoring scales and the allocation of final candidate quotas. Here, EnsPlex is presented as a multi-source framework that couples structural sampling with candidate selection for protein-protein interaction complex prediction. EnsPlex combines conformation-expanded docking, AlphaFold-Multimer, AlphaFold3 and Boltz-1 to expand the sampled conformational space. Conformation-expanded docking comprises monomer conformational expansion followed by flexible HADDOCK docking. FACET is trained to predict candidate quality using DockQ and its component metrics as supervision. Across 102 antigen-antibody systems, EnsPlex achieved up to a 27.8% relative improvement in target success rate over AlphaFold3 with its built-in ranking under matched output budgets. FACET also improved within-source ranking in the internal candidate pools and in homology-filtered external data. These findings support the utility of EnsPlex for structure prediction in the evaluated antigen-antibody systems.