Congratulations to 2nd Year DPhil in Statistics student Ísak Valsson on winning the People’s Poster Prize at the RSC’s 7th "AI in Chemistry" symposium held at Churchill College, Cambridge 16th-18th September, 2024.
Research on AEV-PLIG
Ísak completed his MSc in Statistical Science under the supervision of Prof. Garrett M. Morris, developing AEV-PLIG which incorporates atomic environment vectors into protein-ligand interaction GNNs for binding affinity prediction. By predicting how tightly a small molecule will bind to a protein, we can computationally screen large numbers of molecules to find lead compounds faster and thus accelerate drug discovery.
Ísak continued his work on AEV-PLIG with Prof. Morris and Prof. Charlotte Deane in the Oxford Protein Informatics Group, successfully improving its accuracy and demonstrating its improved ability to generalize on a new “OOD Test” benchmark he has also developed.
In a collaboration with Prof. Philip Biggin in the Department of Biochemistry, Prof. Biggin's former postdoc Dr Matthew Warren, and Dr Aniket Anighoro at Boehringer Ingelheim, Ísak has shown AEV-PLIG is approaching the accuracy of much slower free energy perturbation methods which are widely used in pharma to predict differences in ΔG of binding for compounds in congeneric series of potential drugs. You can read more about the AEV-PLIG method on ChemRxiv ("How to make machine learning scoring functions competitive with FEP”, https://doi.org/10.26434/chemrxiv-2024-bth5z).
When presenting the award, Dr Swain commented that there had been a large number of very high-quality poster submissions and that People’s Prize was the most prestigious of the three awards.
Well done, Ísak!
-
Words and images provided by Professor Garrett Morris.
What does a statistician do for the England football team?
From squad selection to modelling how footballs behave at altitude, statistician Matt Penn explains how data is helping shape the modern game, and why coaches will always matter more than the numbers.
New evidence suggests vast hidden magma systems inside Mars
Researchers from the Departments of Earth Science and Statistics have found evidence that Mars once hosted enormous, Earth-like magmatic systems deep below its surface – even though the planet lacks the plate tectonics long considered essential for this kind of geological complexity. The findings open up new possibilities for how rocky planets become habitable.
Finding a needle in the genomic haystack: Targeting rare genes using statistical outliers
In statistical modelling, extreme outliers are often written off as 'noise'. But a new study by researchers from Oxford's Department of Statistics and Big Data Institute published this week in The American Journal of Human Genetics reverses that principle, using these outliers as the basis of a targeting system for locating rare, high-impact genetic mutations.