Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
Keyue Qiu, Xintong Wang, Zhilong Zhang, Hao Zhou, Wei-Ying Ma
ICML 2026 regular
Tóm tắt (nguồn: OpenReview · © tác giả)
Biomolecules such as proteins and small-molecule ligands play a central role in biological systems, arising from the tight interplay between sequence and three-dimensional structure. Recent generative models for biomolecular co-design aim to capture this interplay by jointly modeling coupled modalities. However, existing approaches largely adopt a parallel execution of marginal generative processes, implicitly enforcing fixed synchronous coupling. We argue that a critical but overlooked degree of freedom lies in how these marginal processes are \emph{temporally coupled} during training and generation, where inappropriate coupling can introduce high-variance supervision and inconsistent intermediate states, affecting modality consistency. To address this, we introduce GeoCoupling, a systematic framework that optimizes for temporal couplings between heterogeneous modalities. Empirical results across structure-based drug design and unconditional protein design demonstrate the learned couplings consistently outperform synchronous and randomly coupled baselines, yielding biomolecules with improved physical validity and diversity.
Từ khoá
Metadata từ BioTender-max/icml2026-ai-bio (CC0-1.0). Phở không lưu trữ bản PDF; link trỏ về nguồn gốc.
Cùng chủ đề
Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
Hengyuan Cao, Shizhuo Cheng, Mingxuan Liu, Weicheng Huang +4
The rapid evolution of generative models has unlocked new potentials in protein binder design, a pivotal task in structural biology, by facilitating end-to-end generation via…
FIDIA: Function-Informed Sequence Design via Inference-Aligned Policy Optimization
Minghan Li, Fengji Li, Yilin Tao, Yue Deng
Computational protein design typically employs a sequential workflow of structure generation followed by sequence (re)design. While structure generators can be explicitly…
FLIP2: Expanding Protein Fitness Landscape Benchmarks for Real-World Machine Learning Applications
Kieran Didi, Sarah Alamdari, Alex Xijie Lu, Bruce James Wittmann +4
Machine learning methods that predict protein fitness from sequence remain sensitive to changes in data distributions, limiting generalization across common conditions encountered…