Benchmarking antibody development
TxBench-Antibody-Development tests whether AI agents can make the evidence-based decisions that take a therapeutic antibody from a chosen candidate to its first dose in people, such as whether it can be made and stored reliably, whether a manufacturing change altered the drug, or what starting dose is safe. It is the fourth domain in TxBench, which assesses agentic ability to make therapeutics.
In this repo, there are 3 public tasks that DO NOT APPEAR in the benchmark, but mimic benchmark like questions.
Apache 2.0 - see LICENSE.