跳到主要内容
Learn Motion
探索课程产品能力价格

下载 Learn Motion

用手机扫描二维码,下载 App。

App Store

扫码从 App Store 下载 Learn Motion打开商店页面

Google Play

扫码从 Google Play 下载 Learn Motion打开商店页面
登录
Learn Motion

How AI Designs a Drug Molecule from Scratch

1Why Designing a Drug Molecule Is Hard2Turning Molecules into Something a Machine Can Read3How Generative Models Propose New Molecules4Scoring and Filtering the Candidates5Testing, Learning, and Improving the Design
How Generative Models Propose New Molecules

Where a new structure comes from

2 / 3
Watch the fragments on the left. Each one is a piece of a real molecule — a ring, a group, a linker — and each appeared many times in the data the model trained on. The animation moves them into the centre and joins them. Now look at the structure that results: every piece is familiar, but this particular assembly is not something the model was ever shown. That is where novelty comes from — not from inventing new chemistry, but from combining known pieces in an order that was never in the training set. And notice the risk sitting right next to it. The model judged each piece plausible as it placed it, but nothing checked whether the finished assembly holds together. Familiar parts can still make an awkward whole.
0:00 / 0:00

A generative model learns by being shown a large collection of real molecules and adjusting itself until those molecules look likely under its distribution. What it absorbs is not a memory of individual compounds but the local patterns that recur across the collection: which rings appear, which functional groups attach to which scaffolds, which linkers connect which fragments, how often a particular arrangement shows up. Those recurring pieces are the model's vocabulary.

Generation then works by composition. The model assembles a structure piece by piece, choosing each next fragment according to the probabilities it learned. Because the choices are made locally and independently, the model can place fragments together in a combination that no training molecule contained. This is the origin of novelty: a molecule is new when the combination is new, even though every individual piece of it was seen during training. Nothing in the model requires the whole assembly to have been observed before.

The same mechanism explains the failure mode. Local plausibility does not add up to global plausibility. A model can join fragments that are each perfectly ordinary into an arrangement that is strained, unstable, or simply not useful — the pieces are familiar, the whole is not. Novelty and quality are therefore separate properties, and a generated structure has to be checked rather than trusted.

上一页2 / 3下一页

Learn Motion

生成课程,认真学会。

运营方:Wuhan Daoyin Technology Co., Ltd.

联系我们: [email protected]
隐私政策用户服务协议

© 2026 Learn Motion