How a researcher uses Codex and ChatGPT to search for new antimicrobial molecules
What happened
Researchers at MIT used OpenAI’s Codex and ChatGPT to automatically generate and evaluate thousands of candidate antimicrobial molecules, turning natural‑language prompts into SMILES strings and then filtering them with computational models before testing the most promising compounds in the lab. The approach identified several novel molecules that showed activity against drug‑resistant bacteria, demonstrating that large language models can accelerate early‑stage drug discovery by handling the chemistry‑design loop that traditionally requires expert chemists.
Why it matters
This success shows that AI language models can become practical tools for pharmaceutical research, potentially shortening development timelines and lowering costs for new antibiotics. It also signals a broader shift in the AI industry toward domain‑specific applications that combine generative models with scientific validation pipelines.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from openai.com and summarised automatically by AIPulsee's pipeline. See how it runs.