I’m a Member of Technical Staff at Latent Labs.
Prior to this, I was an Immunoinformatics Research Scientist at Exscientia, focused on biologics.
I recently completed my DPhil at the University of Oxford supervised by Professor Xiaowen Dong and based in the Machine Learning Research Group. My research was focused on the robustness of graph-based machine learning models. I was also part of the EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems.
Updates
[01/07/24] I started as a Member of Technical Staff at Latent Labs.
[17/06/24] Our work “ABodyBuilder3: Improved and scalable antibody structure predictions” was accepted at two ICML workshops Accessible and Efficient Foundation Models for Biological Discovery and Machine Learning for Life and Material Science: From Theory to Industry applications..
[31/05/24] We released a pre-print “Large scale paired antibody language models.”. We also open-sourced the model weights on HuggingFace.
[21/09/23] Our Paper “Bayesian Optimisation of Functions on Graphs” was accepted at NeurIPS 2023.
[20/06/23] Our paper “Inverse folding for antibody sequence design using deep learning” was accepted at the 2023 ICML Workshop on Computational Biology.
[23/02/23] I passed my DPhil viva without corrections. I received a letter of commendation from the Division of Mathematical, Physical & Life Sciences for the feedback received. I’m Dr Kenlay now :).
[12/12/22] I started work as an AI Research Scientist in the immunoinformatics team at Exscientia.
[24/11/22] Our paper “On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features” was accepted to the first Learning On Graphs Conference
[08/10/22] I was recognised as a top reviewer for NeurIPS 2022.
[07/10/22] I handed in my DPhil thesis titled “Robustness analysis of graph-based machine learning”.
[04/08/22] Our paper “On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features” was accepted to the Data and Model Quality for Mining and Learning with Graphs Workshop @ECMLPKDD 2022. You can learn more about our work by looking at the preprint or blogpost. This is work I contributed to whilst interning at Twitter.
[21/07/22] Our paper “Structure-Aware Robustness Certificates for Graph Classification” (co-first author) was accepted at the international Workshop on Mining and Learning with Graphs @ECMLPKDD 2022. I will update this page with a camera-ready version when it is prepared. I will be at the workshop to present the poster, so if you’re interested please come and speak with me about it!
[17/07/22] I made this website. More coming soon…