cs.LGNov 10, 2026

Emergent Biological Capabilities in a Foundation Model for Molecular Interactions

Authors: Adi Mashiach

Organizations: Output Labs

Abstract

Foundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-ligand sequences. From a single representation space, Bonbon exhibits three zero-shot emergent capabilities at hierarchical levels of resolution: functional (mechanism of action), residue (binding site localization, including orthosteric/allosteric discrimination), and bond (covalent versus non-covalent engagement). All three capabilities generalize to out-of-distribution complexes. Bonbon was trained on protein-ligand sequences alone, without any task-specific supervision and without structural coordinates. We conducted controlled scaling experiments across six model scales from 42M to 1.6B parameters; every capability evaluated shows a sharp jump at the largest scale on continuous metrics, even as pretraining loss decreases smoothly. This demonstrates that loss-based scaling laws alone are insufficient to predict when zero-shot emergent capabilities become available. The capabilities reported here emerge after training at a 1:2,000 parameter-to-token ratio to accommodate the sparsity of paired biological interaction data. The same frozen representations achieve state-of-the-art binding and affinity prediction at five orders of magnitude greater speed than co-folding methods. In prospective wet-lab validation across nine disease targets spanning seven protein families, Bonbon achieves a 61.5% dose-response hit rate on de novo compounds, yielding structurally novel molecules not previously reported to inhibit these proteins, including for out-of-distribution targets.

Figures & tables

Appendix figures & tables29 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery

    Mar 3, 2026Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov +17Molecular OptimizationMolecular Property Prediction

  2. BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language

    Jun 20, 2026Qizhi Pei, Zhimeng Zhou, Yi Duan +9Multimodal UnderstandingMultimodal Pretraining

  3. AMix-2: Establishing Protein as a Native Modality in Large Language Models

    May 29, 2026Keyue Qiu, Yixin Wu, Lihao Wang +19Diffusion Language ModelsProtein Language Models