An incredible multidisciplinary team effort with my ex-colleagues at Microsoft Research AI for Science. Proud to be part of it!

With this publication, we hope we further cement the idea that deep generative models can go beyond static structure generation and towards capturing biologically relevant dynamics at scale.

BioEmu is a generative deep learning model for emulating protein equilibrium ensembles. It's already been open-sourced and used across the community to generate high-fidelity protein structural ensembles.

5/ At @mayoclinic.org, clinicians are at the forefront of AI innovation and deployment. Progress depends on a deep, practical understanding of how AI works. I hope this series helps bridge the gap between cutting-edge technology and clinical care. Let me know what you think and feel free to share!

4/ 💬 Lectures 5 & 6: How ChatGPT works, and how to use it.
- How ChatGPT was created
- Prompting strategies
- How to reduce hallucinations with RAG
If you're using LLMs in medicine, start here.

3/ 🖼️ Lectures 3 & 4: How AI sees medical images.
- What AI imaging models actually “look at”
- Convolutional neural networks (CNNs)
For anyone thinking of applying AI to image data.

2/ 🧠 Lectures 1 & 2: Foundational concepts of deep learning from the ground up.
- Gradient descent
- Neural networks
- Generalisation and overfitting
If you’re new to AI and want to grasp the basics, start here.

If this sounds like a fit — or if you're curious to learn more — here's the link: jobs.mayoclinic.org/job/rocheste...

We're looking for curious, technically strong researchers who want to work on problems that matter. Background in ML, stats, or applied data science is ideal. Radiation oncology experience welcome, but not required.

Having worked in both academic and industry labs, I’ve seen what each does best, and what they sometimes can’t.

With AIDA, we’re closing the loop between idea → data → model → clinical feedback → deployment — all under one roof.

Our aim is to bridge the gap between the ambition of leading AI labs, the rigor of academic research, and the grounded reality of patient care.

AIDA is a research group embedded directly within one of the world’s busiest cancer centers.

We work at the intersection of:
– Clinical data at scale
– Cutting-edge ML
– Daily oncology practice