{"type":"ScholarlyArticle","title":"MultiGeo: Predicting Drug-Target Affinity via Adaptive Multi-Conformation Ensemble Learning","authors":[{"name":"Ruida Zeng","slug":"ruida-zeng","given":"Ruida","family":"Zeng","affiliation":""},{"name":"Cheng Guo","slug":"cheng-guo","given":"Cheng","family":"Guo","affiliation":""},{"name":"Yajie Meng","slug":"yajie-meng","given":"Yajie","family":"Meng","affiliation":""},{"name":"Xunkun Cheng","slug":"xunkun-cheng","given":"Xunkun","family":"Cheng","affiliation":""},{"name":"Zhiwei Xu","slug":"zhiwei-xu","given":"Zhiwei","family":"Xu","affiliation":""},{"name":"Xiangzheng Fu","slug":"xiangzheng-fu","given":"Xiangzheng","family":"Fu","affiliation":""},{"name":"Pan Zeng","slug":"pan-zeng","given":"Pan","family":"Zeng","affiliation":""},{"name":"Shuting Jin","slug":"shuting-jin","given":"Shuting","family":"Jin","affiliation":""},{"name":"Junlin Xu","slug":"junlin-xu","given":"Junlin","family":"Xu","affiliation":""}],"abstract":"Predicting drug–target affinity (DTA) is central to drug discovery, yet most deep learning models rely on a single static protein structure, neglecting the conformational heterogeneity that underlies many binding mechanisms. We propose MultiGeo, a DTA prediction framework that explicitly leverages multiple protein conformations rather than a single snapshot. For each target, MultiGeo starts from an ensemble of structure predictions and uses confidence scores to adaptively select a small set of high-quality, diverse conformers. A hierarchical structural encoder then extracts multi-scale geometric features from these conformers, which are aggregated by a GRU to obtain an ensemble-level representation. To avoid indiscriminately mixing noisy or redundant views, we introduce a disagreement-aware gating mechanism that adaptively fuses this ensemble representation with the dominant structure only when the additional conformers provide complementary information. Finally, ligand–target interactions are modeled via a block-wise cross-attention module that captures multi-perspective dependencies between ligand and protein features. Extensive experiments on multiple DTA benchmarks demonstrate that MultiGeo consistently outperforms state-of-the-art baselines, showing that explicitly encoding conformational diversity yields more accurate and robust affinity prediction.","doi":"10.24963/ijcai.2026/628","url":"https://ijcai.org/proceedings/2026/628","pdf":"https://ijcai.org/proceedings/2026/0628.pdf","markdown":"https://ijcai.org/proceedings/2026/628.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/628","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":628,"pages":{"first":5639,"last":5646},"keywords":["Multidisciplinary Topics and Applications: Bioinformatics"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}