Bristol Myers Squibb has partnered with AI startup Chai Discovery to accelerate antibody drug discovery using machine learning.
Rather than conducting 12–24 months of iterative lab screening, Chai's platform aims to compress early-stage discovery into weeks by generating antibody designs from scratch using AI models that predict molecular folding and function.
The partnership signals biopharma's broader shift toward AI-driven discovery platforms and joins Chai's existing collaborations with Eli Lilly, Pfizer, and Novartis.
What happened
Bristol Myers Squibb announced a strategic collaboration with Chai Discovery, a 2024-founded AI company, to integrate Chai's molecular folding and de novo design models into BMS's drug discovery process for therapeutic antibodies.
Why it matters
Instead of relying on traditional lab-based screening that can take 12 to 24 months, Chai's platform uses AI to design antibodies from scratch in weeks, potentially unlocking discovery of difficult-to-target disease mechanisms. This represents a shift in the biopharma industry toward AI-driven discovery; Chai has also partnered with Eli Lilly, Pfizer, and Novartis.
What to watch
The integration will create a continuously learning discovery system within BMS's portfolio. Chai was founded in 2024 by Joshua Meier (CEO), Jack Dent (President), Matthew McPartlon (CTO), and Jacques Boitreaud, drawing talent from OpenAI, Meta FAIR, Stripe, and Absci.
Ask the AI about this article →
Bristol Myers Squibb's partnership with Chai Discovery represents a broader industry pivot toward AI-driven drug discovery. Traditionally, antibody development has been constrained by the wet-lab bottleneck: identifying viable candidates against complex or difficult-to-target antigens required months or years of iterative screening. Targets that are conformationally flexible, embedded in cell membranes multiple times, or historically "undruggable" posed particular challenges for conventional hybridoma and display library approaches.
Chai's platform reframes this challenge as a computational problem. By deploying generative models that predict molecular folding and biochemical function, the system can design antibody sequences and structures from scratch to meet defined biophysical constraints—compressing the early-stage pipeline from months into weeks. For BMS, this integration into a continuously learning discovery system potentially unlocks access to high-value targets that standard methods cannot address. Chai's existing partnerships with Eli Lilly, Pfizer, and Novartis suggest the company's approach has gained credibility across the sector; the BMS deal signals this model is becoming foundational rather than experimental.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Chai, an AI platform for drug discovery, announced a collaboration with Bristol Myers Squibb to use AI for ide…
Hark and AT&T have announced a partnership focused on providing connectivity solutions for future AI devices
John Deere raised its full-year 2026 profit guidance after reporting a quarterly earnings beat driven by stron…
AT&T is deploying open-source AI models to reduce its reliance on Anthropic's commercial services and lower it…
Zayo, a network infrastructure provider, has expanded its partnership with Corning, a materials science compan…
The pharmaceutical industry is increasing investment in artificial intelligence to accelerate drug discovery a…
