---
title: "Advancing AI for biology: Teaching models to design and characterize antibodies"
description: "Monoclonal antibodies are a mainstay of biopharmaceutical development, with over 100 FDA-approved drugs and established manufacturing and regulatory pathways, yet conventional discovery is costly and slow, typically taking six to twelve months from target to lead candidate. AI promises to make antibody development cheaper, faster, and more flexible by designing and characterizing therapeutic antibodies computationally, but scientific questions remain. Development hinges on three factors: the best binding site on the target, which candidates bind most tightly, and whether candidates can survive manufacturing and the clinic. Predictive models for each factor do well on familiar targets and assays but considerably worse on unfamiliar ones, a gap that in-distribution benchmarks have made difficult to measure. Three papers from Amazon Bio Discovery’s science team address research questions about each factor, with methods integrated into the AI-powered application that connects biological AI models with lab services."
---

# Advancing AI for biology: Teaching models to design and characterize antibodies

[AWS](https://yomu.fyi/company/aws) · Melih Yilmaz, Luca Giancardo, Yue Zhao, Edward Lee, Chuanyui Teh, Fangda Xu, Gordon Trang · Sep 21, 2026

**Type:** Announcement

## Summary

Monoclonal antibodies are a mainstay of biopharmaceutical development, with over 100 FDA-approved drugs and established manufacturing and regulatory pathways, yet conventional discovery is costly and slow, typically taking six to twelve months from target to lead candidate. AI promises to make antibody development cheaper, faster, and more flexible by designing and characterizing therapeutic antibodies computationally, but scientific questions remain. Development hinges on three factors: the best binding site on the target, which candidates bind most tightly, and whether candidates can survive manufacturing and the clinic. Predictive models for each factor do well on familiar targets and assays but considerably worse on unfamiliar ones, a gap that in-distribution benchmarks have made difficult to measure. Three papers from Amazon Bio Discovery’s science team address research questions about each factor, with methods integrated into the AI-powered application that connects biological AI models with lab services.

## Context

Monoclonal antibodies are a key class of biopharmaceuticals with over 100 FDA-approved drugs, but conventional discovery is costly and slow, taking six to twelve months from target to lead candidate. AI-based computational design and characterization promise to make development cheaper and faster, yet predictive models perform well on familiar targets but poorly on unfamiliar ones. In-distribution benchmarks have hidden this gap, making it hard to measure and close. The papers aim to address this by tackling the three core factors: binding site, binding affinity, and manufacturability.

## Approach / What changed

The approach involves three research papers from Amazon Bio Discovery’s science team. Each paper addresses one of the three factors in antibody drug development: identifying the best binding site on the target, predicting which candidates bind most tightly, and assessing manufacturability and clinical viability. The models are designed to improve predictive accuracy on unfamiliar targets and assays, moving beyond in-distribution benchmarks. These methods are integrated into Amazon Bio Discovery, an AI-powered application that connects biological AI models with lab services for testing.

## Takeaways

- Conventional antibody discovery typically takes six to twelve months from target to lead candidate, with mounting costs and long timelines.
- Predictive models for antibody development perform well on familiar targets and assays but considerably worse on unfamiliar ones, a gap hidden by in-distribution benchmarks.
- Amazon Bio Discovery integrates biological AI models with lab services, allowing scientists to design and test novel drug candidates computationally.

## FAQ

### What three factors does the post say antibody development hinges on?

The three factors are: the best binding site on the target, which candidates bind most tightly, and whether candidates can survive manufacturing and the clinic. Each is addressed by a separate paper from the science team.

### Why do predictive models underperform on unfamiliar targets?

The models perform well on familiar targets and assays but considerably worse on unfamiliar ones. This gap is difficult to measure because benchmarks are built around in-distribution accuracy, which doesn't reflect real-world generalization.

**Tags:** [AI](https://yomu.fyi/topic/ai), [Antibodies](https://yomu.fyi/topic/antibodies), [Biology](https://yomu.fyi/topic/biology)

- Source: [AWS](https://www.amazon.science/blog/advancing-ai-for-biology-teaching-models-to-design-and-characterize-antibodies)
- Source URL: https://www.amazon.science/blog/advancing-ai-for-biology-teaching-models-to-design-and-characterize-antibodies
- Ingested by Yomu: 2026-09-21T21:00:06.421Z

[Read original post](https://www.amazon.science/blog/advancing-ai-for-biology-teaching-models-to-design-and-characterize-antibodies)