
Fergus Imrie
@fergus_imrie
Florence Nightingale Bicentenary Fellow @OxfordStats | Former Postdoc @UCLA DPhil (PhD) @UniofOxford @OPIGlets
ID: 1307055979062849542
https://fimrie.github.io/ 18-09-2020 20:37:00
107 Tweet
311 Followers
101 Following


I had an amazing time working with Dennis Frauen @ICLR 2025 on sensitivity analysis while he was visiting Cambridge this summer! Preprint here: arxiv.org/abs/2311.16026

Love getting to collaborate and do innovative research like this! UCLA Anesthesiology Congrats Pascal Laferriere-Langlois Fergus Imrie ! Novel Preoperative Risk Stratification Using Digital Phenotyping Applying a Scalable Machine-Learning Approach: Anesthesia & Analgesia journals.lww.com/anesthesia-ana…

How do we stress-test ML models for settings for which we have no or little real data? #SyntheticData generated by #GenerativeModels may be the answer. Join us at #NeurIPS2023, 5pm (#907) to hear more. w/ Nabeel Seedat*,Fergus Imrie,Mihaela van der Schaar Link: neurips.cc/virtual/2023/p…

Label quality is crucial for pseudo-labeling! Check out our latest work demonstrating the impact of label noise on pseudo-labeling and proposing a general strategy for such scenarios Fantastic work Nabeel Seedat and Nicolas!

I’m delighted to announce that I’ve joined Oxford Statistics University of Oxford as a Florence Nightingale Bicentenary Fellow. I’ll be continuing my research in machine learning for medicine and drug discovery. If you’d like to collaborate, please reach out!


OPIGlets are out in force at #AIChem24, organised by our very own Garrett M. Morris DPhil students Lucy Vost, Arun Raja and Ísak Valsson are presenting posters, and Yael is giving a talk about her recent work MolSnapper on Wednesday! Please come and chat to them!


🚨 PhD openings Fantastic opportunity to join University of Oxford for a PhD as part of the new ILESLA programme Research is possible across 5 broad themes including machine learning and drug discovery Deadline: January 31st, 12pm (midday) UK time


Amazing program. I'm very excited to be a co-supervisor for a UNIQ+ project on Nanobody Language Modelling based in Oxford Statistics




MolSnapper has now been published in JCIM & JCTC Journals! MolSnapper integrates expert knowledge into diffusion models for structure-based drug design using a conditioning approach. Congratulations Yael Ziv, Fergus Imrie, Brian Marsden, and Charlotte Deane. pubs.acs.org/doi/10.1021/ac…

This work is such 🔥 Nicholas Runcie is now banned from Chat GPT Check out this thread and our preprint! arxiv.org/abs/2505.07735

MolSnapper: Conditioning Diffusion for Structure-Based Drug Design #DrugDesign pubs.acs.org/doi/10.1021/ac… Yael Ziv Fergus Imrie Brian Marsden Oxford Protein Informatics Group (OPIG) #JCIM Vol65 Issue9 #MachineLearning #DeepLearning