User profiles for Benjamin Sanchez-Lengeling
Benjamin Sanchez-LengelingResearch Scientist at Google Deepmind Verified email at google.com Cited by 8707 |
Inverse molecular design using machine learning: Generative models for matter engineering
B Sanchez-Lengeling, A Aspuru-Guzik - Science, 2018 - science.org
The discovery of new materials can bring enormous societal and technological progress. In
this context, exploring completely the large space of potential materials is computationally …
this context, exploring completely the large space of potential materials is computationally …
Objective-reinforced generative adversarial networks (organ) for sequence generation models
GL Guimaraes, B Sanchez-Lengeling… - arXiv preprint arXiv …, 2017 - arxiv.org
In unsupervised data generation tasks, besides the generation of a sample based on
previous observations, one would often like to give hints to the model in order to bias the …
previous observations, one would often like to give hints to the model in order to bias the …
Automatic chemical design using a data-driven continuous representation of molecules
…, JM Hernández-Lobato, B Sánchez-Lengeling… - ACS central …, 2018 - ACS Publications
We report a method to convert discrete representations of molecules to and from a
multidimensional continuous representation. This model allows us to generate new molecules for …
multidimensional continuous representation. This model allows us to generate new molecules for …
Inverse design of nanoporous crystalline reticular materials with deep generative models
Reticular frameworks are crystalline porous materials that form via the self-assembly of
molecular building blocks in different topologies, with many having desirable properties for gas …
molecular building blocks in different topologies, with many having desirable properties for gas …
[HTML][HTML] Molecular sets (MOSES): a benchmarking platform for molecular generation models
…, A Zhebrak, B Sanchez-Lengeling… - Frontiers in …, 2020 - frontiersin.org
Generative models are becoming a tool of choice for exploring the molecular space. These
models learn on a large training dataset and produce novel molecular structures with similar …
models learn on a large training dataset and produce novel molecular structures with similar …
Reinforced Adversarial Neural Computer for de Novo Molecular Design
…, V Aladinskiy, B Sanchez-Lengeling… - Journal of chemical …, 2018 - ACS Publications
In silico modeling is a crucial milestone in modern drug design and development. Although
computer-aided approaches in this field are well-studied, the application of deep learning …
computer-aided approaches in this field are well-studied, the application of deep learning …
Rational design of layered oxide materials for sodium-ion batteries
Sodium-ion batteries have captured widespread attention for grid-scale energy storage
owing to the natural abundance of sodium. The performance of such batteries is limited by …
owing to the natural abundance of sodium. The performance of such batteries is limited by …
Optimizing distributions over molecular space. An objective-reinforced generative adversarial network for inverse-design chemistry (ORGANIC)
B Sanchez-Lengeling, C Outeiral, GL Guimaraes… - 2017 - chemrxiv.org
Molecular discovery seeks to generate chemical species tailored to very specific needs. In
this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative …
this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative …
[PDF][PDF] Inverse design of solid-state materials via a continuous representation
The non-serendipitous discovery of materials with targeted properties is the ultimate goal of
materials research, but to date, materials design lacks the incorporation of all available …
materials research, but to date, materials design lacks the incorporation of all available …
[PDF][PDF] Evaluating attribution for graph neural networks
Interpretability of machine learning models is critical to scientific understanding, AI safety, as
well as debugging. Attribution is one approach to interpretability, which highlights input …
well as debugging. Attribution is one approach to interpretability, which highlights input …