130 citations · 297 across the 22 of their papers we have counts for
24 papers
Emyx: Fast and efficient all-atom protein generation
Nicholas J. Williams, Ward Haddadin, Matteo P. Ferla +7
Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the…
Global properties of the energy landscape: a testing and training arena for machine learned potentials
Vlad Cărare, Fabian L. Thiemann, Joe Morrow +3
Machine learning interatomic potentials (MLIPs) have achieved remarkable accuracy on standard benchmarks, yet their ability to reproduce molecular kinetics -- critical for reaction…
Refining embeddings with fill-tuning: data-efficient generalised performance improvements for materials foundation models
Matthew P. Wilson, Edward O. Pyzer-Knapp, Nicolas Galichet +1
Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate a…
Providing Machine Learning Potentials with High Quality Uncertainty Estimates
Zeynep Sumer, James L. McDonagh, Clyde Fare +4
Computational chemistry has come a long way over the course of several decades, enabling subatomic level calculations particularly with the development of Density Functional Theory…
Hessian QM9: A quantum chemistry database of molecular Hessians in implicit solvents
Nicholas J. Williams, Lara Kabalan, Ljiljana Stojanovic +2
A significant challenge in computational chemistry is developing approximations that accelerate \emph{ab initio} methods while preserving accuracy. Machine learning interatomic pot…
Further Understanding of a Local Gaussian Process Approximation: Characterising Convergence in the Finite Regime
Anthony Stephenson, Robert Allison, Edward Pyzer-Knapp
We show that common choices of kernel functions for a highly accurate and massively scalable nearest-neighbour based GP regression model (GPnn: \cite{GPnn}) exhibit gradual converg…
Physics Inspired Approaches To Understanding Gaussian Processes
Maximilian P. Niroomand, Luke Dicks, Edward O. Pyzer-Knapp +1
Prior beliefs about the latent function to shape inductive biases can be incorporated into a Gaussian Process (GP) via the kernel. However, beyond kernel choices, the decision-maki…
Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression
Robert Allison, Anthony Stephenson, Samuel F +1
The accurate predictions and principled uncertainty measures provided by GP regression incur O(n^3) cost which is prohibitive for modern-day large-scale applications. This has moti…
Evaluating the roughness of structure-property relationships using pretrained molecular representations
David E. Graff, Edward O. Pyzer-Knapp, Kirk E. Jordan +2
Quantitative structure-property relationships (QSPRs) aid in understanding molecular properties as a function of molecular structure. When the correlation between structure and pro…
Provably Reliable Large-Scale Sampling from Gaussian Processes
Anthony Stephenson, Robert Allison, Edward Pyzer-Knapp
When comparing approximate Gaussian process (GP) models, it can be helpful to be able to generate data from any GP. If we are interested in how approximate methods perform at scale…
A Principled Method for the Creation of Synthetic Multi-fidelity Data Sets
Clyde Fare, Peter Fenner, Edward O. Pyzer-Knapp
Multifidelity and multioutput optimisation algorithms are of active interest in many areas of computational design as they allow cheaper computational proxies to be used intelligen…
Roughness of molecular property landscapes and its impact on modellability
Matteo Aldeghi, David E. Graff, Nathan Frey +4
In molecular discovery and drug design, structure-property relationships and activity landscapes are often qualitatively or quantitatively analyzed to guide the navigation of chemi…
Self-focusing virtual screening with active design space pruning
David E. Graff, Matteo Aldeghi, Joseph A. Morrone +3
High-throughput virtual screening is an indispensable technique utilized in the discovery of small molecules. In cases where the library of molecules is exceedingly large, the cost…
Using Bayesian Optimization to Accelerate Virtual Screening for the Discovery of Therapeutics Appropriate for Repurposing for COVID-19
Edward O. Pyzer-Knapp
The novel Wuhan coronavirus known as SARS-CoV-2 has brought almost unprecedented effects for a non-wartime setting, hitting social, economic and health systems hard.~ Being able to…
Privacy-Preserving Gaussian Process Regression -- A Modular Approach to the Application of Homomorphic Encryption
Peter Fenner, Edward O. Pyzer-Knapp
Much of machine learning relies on the use of large amounts of data to train models to make predictions. When this data comes from multiple sources, for example when evaluation of…
Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning
Matt Benatan, Edward O. Pyzer-Knapp
Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box pre…
Combining human cell line transcriptome analysis and Bayesian inference to build trustworthy machine learning models for prediction of animal toxicity in drug development
Laura-Jayne Gardiner, Anna Paola Carrieri, Jenny Wilshaw +3
Biomedical data, particularly in the field of genomics, has characteristics which make it challenging for machine learning applications - it can be sparse, high dimensional and noi…
Powerful, transferable representations for molecules through intelligent task selection in deep multitask networks
Clyde Fare, Lukas Turcani, Edward O. Pyzer-Knapp
Chemical representations derived from deep learning are emerging as a powerful tool in areas such as drug discovery and materials innovation. Currently, this methodology has three…
Dynamic Control of Explore/Exploit Trade-Off In Bayesian Optimization
Dipti Jasrasaria, Edward O. Pyzer-Knapp
Bayesian optimization offers the possibility of optimizing black-box operations not accessible through traditional techniques. The success of Bayesian optimization methods such as…
Efficient and Scalable Batch Bayesian Optimization Using K-Means
Matthew Groves, Edward O. Pyzer-Knapp
We present K-Means Batch Bayesian Optimization (KMBBO), a novel batch sampling algorithm for Bayesian Optimization (BO). KMBBO uses unsupervised learning to efficiently estimate pe…
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp +1
Chemical space is so large that brute force searches for new interesting molecules are infeasible. High-throughput virtual screening via computer cluster simulations can speed up t…
Space-Filling Curves as a Novel Crystal Structure Representation for Machine Learning Models
Dipti Jasrasaria, Edward O. Pyzer-Knapp, Dmitrij Rappoport +1
A fundamental problem in applying machine learning techniques for chemical problems is to find suitable representations for molecular and crystal structures. While the structure re…
Machine Learning Exciton Dynamics
Florian Häse, Stéphanie Valleau, Edward Pyzer-Knapp +1
Obtaining the exciton dynamics of large photosynthetic complexes by using mixed quantum mechanics/molecular mechanics (QM/MM) is computationally demanding. We propose a machine lea…
A Bayesian Approach to Calibrating High-Throughput Virtual Screening Results and Application to Organic Photovoltaic Materials
Edward O. Pyzer-Knapp, Gregor N. Simm, Alan Aspuru-Guzik
A novel approach for calibrating quantum-chemical properties determined as part of a high-throughput virtual screen to experimental analogs is presented. Information on the molecul…