Anthropic reports Claude drug development work with six partners, including 35,000 antibody designs in about a month

Anthropic says its life sciences team has spent the past several months in research partnerships with six organizations developing new medicines: BigHat Biosciences, Bristol Myers Squibb, Divergence Labs, Enveda, Generate Biomedicines and The Column Group. The company has also started drug discovery efforts of its own, including programs for rare childhood forms of muscular dystrophy, where Claude handles much of the scientific and operational work, according to Anthropic.

Anthropic's stated strategy is to involve AI in every stage of drug development, from target identification and molecule design to manufacturing, regulatory filings and clinical trials. It argues that the bottlenecks are distributed across the process rather than concentrated in one problem. The company says it has already prioritized specific model improvements based on what it learned. It plans to scale this work up substantially.

The post links technical reports and preprints from each partner. The figures below are reported by Anthropic and its partners.

Case studies

Generate Biomedicines (modality engineering). Generate is working to extend CAR T-cell therapy, which has historically treated blood cell cancers, to solid tumors. Six Generate scientists used Claude Code to propose new designs for one part of the therapy's genetic instructions. One design was about 70% shorter than the standard version. In lab tests, it allowed immune cells to make roughly 10 times as many receptors, killed tumor cells more efficiently, and kept the immune cells active for longer.

Divergence Labs (hit generation). Divergence is developing a food allergy treatment that detaches IgE from immune cells, rather than only neutralizing circulating IgE. The design needs two "arms": one that binds IgE tightly and one that helps pry it from the cell. Claude turned the goals into a design plan, then, largely autonomously, generated roughly 35,000 antibody designs in about a month. Early tests found three designs that bound IgE and 20 that dislodged it. Three of those 20 appeared to dislodge IgE more than the standard medication. The next step is building a drug that combines both arms.

BigHat Biosciences (lead optimization). BigHat's scientists and an Anthropic researcher worked with Claude to improve binding, stability and clumping in two antibody fragment leads. Claude, connected to BigHat's lab data system Reccy, proposed changes, and the lab made and tested about 1,010 variants in about 10 weeks. Partway through, the team suspected the standard heat-stability and clumping metrics were misleading. Claude and the researcher reanalyzed the raw data and proposed different metrics and a protocol change, and the main predictions held. Compared with the originals, the best versions bound more than 10x more tightly. The cancer-targeting lead stayed in solution 18°C higher, and the lead for longer-lasting drugs clumped more than 100x more slowly.

Enveda (manufacturing and filings). Enveda says its manufacturing chemists spent up to 75% of their time on paperwork. It built a system connecting its manufacturing documents to Claude, which flags possible issues. Across 1,061 pages of documentation, Claude caught all 11 issues human reviewers had spotted and flagged seven they had missed. Human review time fell by 89%, from over 25 hours to less than three. Claude also wrote first drafts of two regulatory documents. One took four hours, compared with about three months by hand. For the other, Enveda's standard human review found one minor error.

The Column Group (company creation). TCG is establishing Pleiades, a new company that will use Claude to run many more, and more complex, drug programs than is usual for a small team. Anthropic describes it as a possible model for reducing the scientific and administrative overhead of running a biotechnology company.

What this means

The results cover distinct tasks: molecule design, candidate screening, assay analysis, document review and regulatory drafting. That matches Anthropic's argument that Claude's role in drug development extends beyond proposing molecules. The BigHat case includes Claude helping question the standard metrics, not only optimizing against them.

The molecular results come from early lab tests. Anthropic frames the outcomes as promising trajectories, and says only that it is optimistic some programs may yield effective medicines. The Enveda figures are the most operational: measured review time and issue detection on a defined document set, with human reviewers as the baseline. Divergence's next step, combining the two arms into one drug, will be the first test of whether its separate hits work together.

Anthropic's own muscular dystrophy programs and the Pleiades company suggest the work is moving toward Claude running larger parts of drug programs, though the details of those efforts are in the linked reports.