paper-with-me

홈 › Papers

Inverse design of 3d molecular structures with conditional generative neural networks

2021-09-10 · Niklas W. A. Gebauer, Michael Gastegger, Stefaan S. P. Hessmann, Klaus-Robert Müller, Kristof T. Schütt

The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel molecules from a learned distribution. Here, we propose a conditional generative neural network for 3d molecular structures with specified chemical and structural properties. This approach is agnostic to chemical bonding and enables targeted sampling of novel molecules from conditional distributions, even in domains where reference calculations are sparse. We demonstrate the utility of our method for inverse design by generating molecules with specified motifs or composition, discovering particularly stable molecules, and jointly targeting multiple electronic properties beyond the training regime.

📄 PDF Abstract BibTeX arXiv:2109.04824

Code (1)

atomistic-machine-learning/cg-schnet 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Generative Models for Automatic Chemical Design

2019-07-02 · Daniel Schwalbe-Koda, Rafael Gómez-Bombarelli

Materials discovery is decisive for tackling urgent challenges related to energy, the environment, health care and many others. In chemistry, conventional methodologies for innovation usually rely on expensive and increm…

molecular representation

Property-Guided Molecular Generation and Optimization via Latent Flows

2026-03-27 · Alexander Arjun Lobo, Urvi Awasthi, Leonid Zhukov arxiv

Molecular discovery is increasingly framed as an inverse design problem: identifying molecular structures that satisfy desired property profiles under feasibility constraints. While recent generative models provide conti…

Improving Molecular Design by Stochastic Iterative Target Augmentation

2020-02-11 · ICML 2020 1 · Kevin Yang, Wengong Jin, Kyle Swanson, Regina Barzilay 외

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the …

Program Synthesis

Multiple-objective Reinforcement Learning for Inverse Design and Identification

2019-10-09 · Hao-Ran Wei, Mariefel Olarte, Garrett B. Goh

The aim of the inverse chemical design is to develop new molecules with given optimized molecular properties or objectives. Recently, generative deep learning (DL) networks are considered as the state-of-the-art in inver…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design

2021-06-07 · AkshatKumar Nigam, Robert Pollice, Alan Aspuru-Guzik

Inverse molecular design, i.e., designing molecules with specific target properties, can be posed as an optimization problem. High-dimensional optimization tasks in the natural sciences are commonly tackled via populatio…

Active LearningEvolutionary AlgorithmsMetaheuristic Optimizationmolecular representation