Agents can design therapeutic antibodies with mixed success

Can agents reliably design therapeutic antibodies?

Machine Learning

Summary

Designing better antibodies for therapies is hard and sometimes done by computer programs called agents. This paper studied how well these agents follow instructions when designing antibodies and what helps them do better. The authors tested agents working with clear instructions and agents working by improving existing designs without instructions. They found that tools help agents follow instructions but hurt how well they optimize, while learning from design history has the opposite effect. Combining these methods, agents worked about as well as a standard optimization technique.

What this means in practice

  • For biotechnology engineers: Use agents that incorporate tools and design history to improve antibody optimization within protein design pipelines.
  • For drug development teams: Incorporate agent-based design techniques to explore new antibody sequences and enhance therapeutic candidates.
  • For computational chemistry software developers: Integrate task-guided and black-box agent design approaches into software to automate antibody molecule optimization.$Commercial implications: Enables automated antibody design tools that pharmaceutical companies can license for faster drug candidate generation.

Authors

Asli Alpman, Nick Bhattacharya, Aaron Solomon, Hunter Elliott

Abstract

Recent work has demonstrated agents driving protein design workflows, either through orchestration of specialized tools or direct manipulation of sequences. Yet the fidelity with which agents follow protein design instructions and the factors contributing to their effectiveness remain understudied. We examine agentic antibody design under two settings: when explicit molecular-editing instructions are provided and when agents receive only previously-scored sequences and are prompted to propose improvements. We call the first task-guided and the second black-box design. For the task-guided setting, we curate ten expert-validated affinity-improvement tasks and show that LLM judges closely reproduce programmatic evaluations of instruction following. We then study two augmentations: access to antibody-relevant tools and to previously scored design history. Tools improve instruction following (IF) and sequence space exploration while reducing optimization performance, whereas design history reduces IF but improves optimization performance at the expense of exploration. Finally, we combine taskguided and black-box design within an in silico optimization loop and show that our agentic optimizer performs comparably to an established Bayesian optimization baseline.