Timothy Atkinson

Sep 26, 2024 | biorxiv.org | Timothy Atkinson |Thomas Barrett |Scott Cameron |Bora Guloglu

AbstractExploring the vast and largely uncharted territory of amino acid sequences is crucial for understanding complex protein functions and the engineering of novel therapeutic proteins. Whilst generative machine learning has advanced protein sequence modelling, no existing approach is proficient for both unconditional and conditional generation. In this work, we propose that Bayesian Flow Networks (BFNs), a recently introduced framework for generative modelling, can address these challenges.

Sep 26, 2024 | biorxiv.org | Timothy Atkinson |Thomas Barrett |Scott Cameron |Bora Guloglu

AbstractExploring the vast and largely uncharted territory of amino acid sequences is crucial for understanding complex protein functions and the engineering of novel therapeutic proteins. Whilst generative machine learning has advanced protein sequence modelling, no existing approach is proficient for both unconditional and conditional generation. In this work, we propose that Bayesian Flow Networks (BFNs), a recently introduced framework for generative modelling, can address these challenges.

Aug 28, 2024 | medrxiv.org | Timothy Atkinson |Justin Petway |Whitney L Forbes |Hannah Thorfinnson

The authors have declared no competing interest. Retrospective nested case-control study using administrative dataAll authors are federal government employees and received no funding for this study. I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Jan 29, 2024 | airedale.com | Timothy Atkinson

Airedale by ModineTM, the critical cooling specialists, today announced the completion of delivery of their largest ever bespoke free cooling chillers, each measuring a significant 22 metres long (73 feet), and housing 36 fans. The vast order, for an undisclosed data center operator, is believed to be one of the largest single, colocation orders taken by Airedale in their 50 year history.

Dec 4, 2023 | biorxiv.org | Louis Robinson |Timothy Atkinson |Liviu Copoiu |Patrick Bordes

AbstractUnderstanding protein function is vital for drug discovery, disease diagnosis, and protein engineering. While Protein Language Models (PLMs) pre-trained on vast protein sequence datasets have achieved remarkable success, equivalent Protein Structure Models (PSMs) remain underrepresented. We attribute this to the relative lack of high-confidence structural data and suitable pre-training objectives.