Equivariant Flows: exact likelihood generative learning for symmetric densities.

no code implementations • ICML 2020 • Jonas Köhler, Leon Klein, Frank Noe

We provide a theoretical sufficient criterium showing that the distribution generated by \textit{equivariant} normalizing flows is invariant with respect to these symmetries by design.

TorchMD: A deep learning framework for molecular simulations

2 code implementations • 22 Dec 2020 • Stefan Doerr, Maciej Majewsk, Adrià Pérez, Andreas Krämer, Cecilia Clementi, Frank Noe, Toni Giorgino, Gianni de Fabritiis

Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials.

BIG-bench Machine Learning Protein Folding

Machine Learning of coarse-grained Molecular Dynamics Force Fields

no code implementations • 4 Dec 2018 • Jiang Wang, Simon Olsson, Christoph Wehmeyer, Adria Perez, Nicholas E. Charron, Gianni de Fabritiis, Frank Noe, Cecilia Clementi

We show that CGnets can capture all-atom explicit-solvent free energy surfaces with models using only a few coarse-grained beads and no solvent, while classical coarse-graining methods fail to capture crucial features of the free energy surface.

BIG-bench Machine Learning Dimensionality Reduction +1

Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations

2 code implementations • journal 2018 • Robin Winter, Floriane Montanari, Frank Noe, and Djork-Arne Clevert

In this work, we propose to exploit the powerful ability of deep neural networks to learn a feature representation from low-level encodings of a huge corpus of chemical structures.

Machine Translation molecular representation

Deep Generative Markov State Models

2 code implementations • NeurIPS 2018 • Hao Wu, Andreas Mardt, Luca Pasquali, Frank Noe

We propose a deep generative Markov State Model (DeepGenMSM) learning framework for inference of metastable dynamical systems and prediction of trajectories.

Time Series Time Series Analysis +1