AI 从分子序列里自己学会了预测药物,没人事先教它
一个只被喂了蛋白质和药物分子配对序列的 AI,没学过任何生物知识,却在训练到某个规模后突然自己会了三件事:判断药物怎么起作用、定位药物结合在蛋白的哪个位置、分辨结合是牢固的共价键还是可逆的。这三样本事在它没见过的分子上也成立。更关键的是,这些能力不是慢慢长出来的——模型从小到大,训练损失一直平滑下降,但能力在最大规模那档突然跳变。也就是说,光看训练误差你根本预测不到它什么时候会开窍。这个模型叫 Bonbon,训练数据是 3.2 万亿个配对序列,没有结构坐标,没有人工标注。它不是你明天能用上的工具,但它指向一个让人不安又兴奋的事实:只要数据够多,AI 会自己长出没人教过的生物直觉。
📄 原文摘要(英文)
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.