Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC)

By Benjamín Sánchez-Lengeling, Carlos Outeiral, Gabriel Lima Guimaraes, Alán Aspuru-Guzik. 2017

287 citations recorded by the source corpus.

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 Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Subfields: Computational Theory and Mathematics, Environmental Chemistry, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Environmental Chemistry

In Materials Chemistry

Citations in the corpus

Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation (2018, background): “Recently, there has been signiﬁcant advances in applying deep learning models to molecule generation [15, 38, 7, 9, 22, 4, 31, 27, 34, 42].”
Improved Training with Curriculum GANs (2018, background): “…synthetic data across a wide diversity of data modalities, including natural images (Radford et al., 2015; Karras et al., 2017), natural language (Yu et al., 2016; Press et al., 2017; Fedus et al., 2018), medical records (Esteban et al., 2017) and molecules (Sanchez-Lengeling et al., 2017).”
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns (2019, background): “…ML approaches can be found in Kowalik et al. (2012), Houben and Lapkin (2015), Houben et al. (2015), Cortés-Borda et al. (2016), Wei et al. (2016), Benjamin et al. (2017), Ahneman et al. (2018), Gao et al. (2018), Granda et al. (2018), Min et al. (2018), Ahn et al. (2019), Elton et al. (2019),…”
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models (2018, unknown): “There have been several demonstrations of being able to bias the generative process of models using reinforcement learning [93–95], often these methods (e.g. Monte Carlo Tree Search) are data intensive, so more efﬁcient RL optimization methods are needed.”
Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models (2020, methodology): “GANs have also been applied to molecular generative models and used with reinforcement learning to successfully generate novel molecules with desired properties [34, 35].”
A de novo molecular generation method using latent vector based generative adversarial network (2019, background): “The first use in molecule generation was ORGAN [28] and its improved version, ORGANIC [29].”
GuacaMol: Benchmarking Models for De Novo Molecular Design (2018, unknown): “…models based on neural networks have since been further explored, with work on VAEs, 17,36–45 RNNs, 46–58 generative adversarial networks (GANs), 54,55,59,60 adversarial au-toencoders (AAEs), 61–64 and graph convolutional networks, 16,57,60,65 using SMILES strings or graphs to represent molecules.”