# How can we use AI to make drugs?

Page: https://stenobird.com/podcast/oxford-sparks-big-questions-420721/how-can-we-use-ai-to-make-drugs
Text version: https://stenobird.com/podcast/oxford-sparks-big-questions-420721/how-can-we-use-ai-to-make-drugs.md
Podcast: [Oxford Sparks Big Questions](https://stenobird.com/podcast/oxford-sparks-big-questions-420721)
Published: 2026-06-17T11:30:00+00:00
Episode link: https://oxfordsparks.libsyn.com/how-can-we-use-ai-to-make-drugs
Audio file: https://traffic.libsyn.com/secure/oxfordsparks/Ox-AI_drugs-v1.mp3?dest-id=790107
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/oxford-sparks-big-questions-420721/episodes/how-can-we-use-ai-to-make-drugs
Duration seconds: 728

## Resource

Put simply, most drugs work by binding to a protein and altering how they function. But how can we model how well a particular molecule will bind to a particular protein, and use that knowledge to help discover new treatments? In this episode, we talk to Prof Fergus Imrie from Oxford's Department of Statistics, who is one of the lead researchers on the OpenBind consortium. This project aims to create the world's largest open-access dataset of protein-ligand interactions, providing invaluable quantities of data for AI-driven drug discovery

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/oxford-sparks-big-questions-420721/episodes/how-can-we-use-ai-to-make-drugs/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/oxford-sparks-big-questions-420721/how-can-we-use-ai-to-make-drugs.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.