Skip to content
Learn Motion
ExploreHow it worksMembership
Log in
Learn Motion

AI Antibody Design vs Human Design: A Conceptual Overview

1Why Antibody Design Matters2How Humans Design Antibodies3How AI Learns to Design Antibodies4Comparing AI and Human Design5Evidence, Limits, and Open Questions
How AI Learns to Design Antibodies

From Thousands of Candidates to a Shortlist

4 / 4
Follow the funnel from top to bottom. At the top, the generative model has produced thousands of candidates, far more than any lab could make. The first narrowing is scoring and filtering: each candidate gets predicted numbers, and anything that fails a hard requirement is dropped. The next narrowing is ranking, which orders what is left so the best-looking candidates are tested first. By the bottom you have a shortlist small enough to actually produce and measure. Notice that most candidates are discarded, and that is intended. The funnel is how cheap computation is converted into a small number of experiments worth running. But keep one thing in mind: every score along the way is a prediction. The shortlist is a prioritized set of hypotheses, and the experiment at the bottom is still what settles the question.
0:00 / 0:00

Generation is cheap, so a model can propose far more candidates than anyone could ever make and test. The pipeline therefore ends with a narrowing step: candidates are scored, filtered, and ranked until a small shortlist remains for real experiments.

Scoring assigns each candidate one or more numbers — a predicted binding strength, a predicted structural quality, a plausibility score from the generative model. Filtering removes candidates that fail hard constraints: sequences that look non-antibody-like, that carry obvious liabilities, or that are too similar to something already on the list. Ranking then orders what survives, so the most promising candidates are tested first.

The funnel shape is the point. Thousands of generated sequences become hundreds after filtering, then tens after ranking, and finally a handful that a lab can actually produce and measure. Each stage discards most of its input, and that is not a failure of the pipeline; it is how the pipeline converts cheap computation into an expensive experiment that is worth running. The scores are predictions, so the shortlist is a prioritized set of hypotheses, not a set of answers. The experiment at the end of the funnel is still what decides.

Previous4 / 4Next

Learn Motion

Generate a course. Learn it properly.

Operated by Wuhan Daoyin Technology Co., Ltd.

Contact: [email protected]
Privacy PolicyTerms of Service

© 2026 Learn Motion