1 code implementation • 13 Oct 2022 • Xiang Fu, Zhenghao Wu, Wujie Wang, Tian Xie, Sinan Keten, Rafael Gomez-Bombarelli, Tommi Jaakkola
We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics.
1 code implementation • 16 Sep 2022 • Wujie Wang, Zhenghao Wu, Rafael Gómez-Bombarelli
We show that our methods can be used to simultaneously fit potentials for simulations at different compositions and temperatures to improve the transferability of the learned potentials.
1 code implementation • 28 Jan 2022 • Wujie Wang, Minkai Xu, Chen Cai, Benjamin Kurt Miller, Tess Smidt, Yusu Wang, Jian Tang, Rafael Gómez-Bombarelli
Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation.
1 code implementation • 15 May 2021 • Minkai Xu, Wujie Wang, Shitong Luo, Chence Shi, Yoshua Bengio, Rafael Gomez-Bombarelli, Jian Tang
Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program.
2 code implementations • 28 Jul 2020 • Jurgis Ruza, Wujie Wang, Daniel Schwalbe-Koda, Simon Axelrod, William H. Harris, Rafael Gomez-Bombarelli
The potential of mean force is expressed as two jointly-trained neural network interatomic potentials that learn the coupled short-range and the many-body long range molecular interactions.
Computational Physics Materials Science
2 code implementations • ICLR Workshop DeepDiffEq 2019 • Wujie Wang, Simon Axelrod, Rafael Gómez-Bombarelli
From the perspective of engineering, one wishes to control the Hamiltonian to achieve desired simulation outcomes and structures, as in self-assembly and optical control, to then realize systems with the desired Hamiltonian in the lab.
1 code implementation • 6 Dec 2018 • Wujie Wang, Rafael Gómez-Bombarelli
Autograin is trained to learn the optimal mapping between all-atom and reduced representation, using the reconstruction loss to facilitate the learning of coarse-grained variables.