2 code implementations • 28 Aug 2023 • Janosh Riebesell, Rhys E. A. Goodall, Philipp Benner, Yuan Chiang, Bowen Deng, Alpha A. Lee, Anubhav Jain, Kristin A. Persson
The top 3 models are UIPs, the winning methodology for ML-guided materials discovery, achieving F1 scores of ~0. 6 for crystal stability classification and discovery acceleration factors (DAF) of up to 5x on the first 10k most stable predictions compared to dummy selection from our test set.
1 code implementation • NeurIPS 2023 • Ryan-Rhys Griffiths, Leo Klarner, Henry B. Moss, Aditya Ravuri, Sang Truong, Samuel Stanton, Gary Tom, Bojana Rankovic, Yuanqi Du, Arian Jamasb, Aryan Deshwal, Julius Schwartz, Austin Tripp, Gregory Kell, Simon Frieder, Anthony Bourached, Alex Chan, Jacob Moss, Chengzhi Guo, Johannes Durholt, Saudamini Chaurasia, Felix Strieth-Kalthoff, Alpha A. Lee, Bingqing Cheng, Alán Aspuru-Guzik, Philippe Schwaller, Jian Tang
By defining such kernels in GAUCHE, we seek to open the door to powerful tools for uncertainty quantification and Bayesian optimisation in chemistry.
no code implementations • 6 May 2021 • Ryan-Rhys Griffiths, Philippe Schwaller, Alpha A. Lee
Datasets in the Natural Sciences are often curated with the goal of aiding scientific understanding and hence may not always be in a form that facilitates the application of machine learning.
1 code implementation • 11 Mar 2021 • Ryan-Rhys Griffiths, Jiachen Jiang, Douglas J. K. Buisson, Dan R. Wilkins, Luigi C. Gallo, Adam Ingram, Alpha A. Lee, Dirk Grupe, Erin Kara, Michael L. Parker, William Alston, Anthony Bourached, George Cann, Andrew Young, Stefanie Komossa
Such a reprocessing model would be characterised by lags between X-ray and optical/UV emission due to differences in light travel time.
Gaussian Processes High Energy Astrophysical Phenomena
1 code implementation • 19 Dec 2020 • Penelope Jones, Fabian Coupette, Andreas Härtel, Alpha A. Lee
Electrolytes play an important role in a plethora of applications ranging from energy storage to biomaterials.
1 code implementation • 24 Oct 2020 • William McCorkindale, Carl Poelking, Alpha A. Lee
Most approaches use molecular descriptors based on a 2D representation of molecules as a graph of atoms and bonds, abstracting away the molecular shape.
1 code implementation • 30 Jul 2020 • Shreshth A. Malik, Rhys E. A. Goodall, Alpha A. Lee
A common bottleneck for materials discovery is synthesis.
Computational Physics Materials Science
1 code implementation • 20 Apr 2020 • Rhys E. A. Goodall, Alpha A. Lee
Pioneering work in liquid state theory derived analytical closures for the framework.
Soft Condensed Matter Computational Physics
1 code implementation • 17 Oct 2019 • Ryan-Rhys Griffiths, Alexander A. Aldrick, Miguel Garcia-Ortegon, Vidhi R. Lalchand, Alpha A. Lee
Bayesian optimisation is a sample-efficient search methodology that holds great promise for accelerating drug and materials discovery programs.
3 code implementations • 1 Oct 2019 • Rhys E. A. Goodall, Alpha A. Lee
Machine learning has the potential to accelerate materials discovery by accurately predicting materials properties at a low computational cost.
no code implementations • 25 Sep 2019 • Ryan Rhys-Griffiths, Miguel Garcia-Ortegon, Alexander A. Aldrick, Alpha A. Lee
Bayesian Optimisation is an important decision-making tool for high-stakes applications in drug discovery and materials design.
2 code implementations • 28 May 2019 • Matthew C. Robinson, Robert C. Glen, Alpha A. Lee
Machine learning methods may have the potential to significantly accelerate drug discovery.
no code implementations • 3 Feb 2019 • Yao Zhang, Alpha A. Lee
Predicting bioactivity and physical properties of small molecules is a central challenge in drug discovery.
1 code implementation • 6 Nov 2018 • Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Costas Bekas, Alpha A. Lee
Organic synthesis is one of the key stumbling blocks in medicinal chemistry.
no code implementations • 1 Aug 2018 • Simon Becker, Yao Zhang, Alpha A. Lee
Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series.
no code implementations • 5 Mar 2018 • Yao Zhang, Andrew M. Saxe, Madhu S. Advani, Alpha A. Lee
We derive a correspondence between parameter inference and free energy minimisation in statistical physics.