activity
20202023
most citedLanguage models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files

22 citations · 44 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2023★ 22 cited

Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files

Daniel Flam-Shepherd, Alán Aspuru-Guzik

Language models are powerful tools for molecular design. Currently, the dominant paradigm is to parse molecular graphs into linear string representations that can easily be trained…

cs.LG2022★ 7 cited

Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning

Daniel Flam-Shepherd, Alexander Zhigalin, Alán Aspuru-Guzik

Machine learning has the potential to automate molecular design and drastically accelerate the discovery of new functional compounds. Towards this goal, generative models and reinf…

cs.LG2021

Keeping it Simple: Language Models can learn Complex Molecular Distributions

Daniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik

Deep generative models of molecules have grown immensely in popularity, trained on relevant datasets, these models are used to search through chemical space. The downstream utility…

cs.LG2021

Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Models

Daniel Flam-Shepherd, Tony Wu, Xuemei Gu +3

Quantum physics experiments produce interesting phenomena such as interference or entanglement, which are core properties of numerous future quantum technologies. The complex relat…

cs.LG2020★ 2 cited

Bayesian Variational Optimization for Combinatorial Spaces

Tony C. Wu, Daniel Flam-Shepherd, Alán Aspuru-Guzik

This paper focuses on Bayesian Optimization in combinatorial spaces. In many applications in the natural science. Broad applications include the study of molecules, proteins, DNA,…

cs.LG2020

Neural Message Passing on High Order Paths

Daniel Flam-Shepherd, Tony Wu, Pascal Friederich +1

Graph neural network have achieved impressive results in predicting molecular properties, but they do not directly account for local and hidden structures in the graph such as func…