EnsPlex: Integrative Protein Complex Prediction through Multi-source Complementary Structural Sampling and Topology-Aware Candidate Selection
- 1East China Normal University
Abstract
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.
Related
- Selection-aware metrics provide complementary decision-level information in plant genomic prediction
- Integrative omics reveals candidate drug-repurposing targets in Tritrichomonas foetus
- Integrative GWAS and Transcriptome Analysis Reveal Genetic Architecture and Candidate Genes for Drought Tolerance During Soybean Germination
- Global use of traditional, complementary and integrative medicine among adults with cancer in hospital and clinical settings: A systematic review and meta-analysis
- Integrative transcriptomic analysis and preclinical validation identify lansoprazole as a therapeutic candidate for preeclampsia
BibTeX
@misc{hu2026ensplex,
title = {{EnsPlex: Integrative Protein Complex Prediction through Multi-source Complementary Structural Sampling and Topology-Aware Candidate Selection}},
author = {B. Hu and Z. Lu and K. Zaman and Z. Sun and X. He},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.26.754739},
url = {https://www.biorxiv.org/content/10.64898/2026.09.26.754739v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - EnsPlex: Integrative Protein Complex Prediction through Multi-source Complementary Structural Sampling and Topology-Aware Candidate Selection
AU - B. Hu
AU - Z. Lu
AU - K. Zaman
AU - Z. Sun
AU - X. He
PY - 2026
DA - 2026/09/26
PB - bioRxiv
DO - 10.64898/2026.09.26.754739
UR - https://www.biorxiv.org/content/10.64898/2026.09.26.754739v1
AB - 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.
ER -