Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC). Benjamin Sanchez-Lengeling, Carlos Outeiral, Gabriel L. Guimaraes, & Alan Aspuru-Guzik ChemRxiv, August, 2017. ![Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC) [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 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.
@article{benjamin_sanchez-lengeling_optimizing_2017,
title = {Optimizing distributions over molecular space. {An} {Objective}-{Reinforced} {Generative} {Adversarial} {Network} for {Inverse}-design {Chemistry} ({ORGANIC})},
url = {https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668},
doi = {10.26434/chemrxiv.5309668.v3},
abstract = {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.},
journal = {ChemRxiv},
author = {{Benjamin Sanchez-Lengeling} and {Carlos Outeiral} and {Gabriel L. Guimaraes} and {Alan Aspuru-Guzik}},
month = aug,
year = {2017},
keywords = {Adversarial Networks, Chemistry, Deep Learning, Generative Model, Information And Computing Sciences, Inverse design, Machine Learning, Mathematics, Molecular generation, Reinforcement Learning},
}
Downloads: 0
{"_id":"vLv7tzPiisFFrH3zj","bibbaseid":"benjaminsanchezlengeling-carlosouteiral-gabriellguimaraes-alanaspuruguzik-optimizingdistributionsovermolecularspaceanobjectivereinforcedgenerativeadversarialnetworkforinversedesignchemistryorganic-2017","author_short":["Benjamin Sanchez-Lengeling","Carlos Outeiral","Gabriel L. Guimaraes","Alan Aspuru-Guzik"],"bibdata":{"bibtype":"article","type":"article","title":"Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC)","url":"https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668","doi":"10.26434/chemrxiv.5309668.v3","abstract":"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.","journal":"ChemRxiv","author":[{"firstnames":[],"propositions":[],"lastnames":["Benjamin Sanchez-Lengeling"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Carlos Outeiral"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Gabriel L. Guimaraes"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["Alan Aspuru-Guzik"],"suffixes":[]}],"month":"August","year":"2017","keywords":"Adversarial Networks, Chemistry, Deep Learning, Generative Model, Information And Computing Sciences, Inverse design, Machine Learning, Mathematics, Molecular generation, Reinforcement Learning","bibtex":"@article{benjamin_sanchez-lengeling_optimizing_2017,\n\ttitle = {Optimizing distributions over molecular space. {An} {Objective}-{Reinforced} {Generative} {Adversarial} {Network} for {Inverse}-design {Chemistry} ({ORGANIC})},\n\turl = {https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668},\n\tdoi = {10.26434/chemrxiv.5309668.v3},\n\tabstract = {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.},\n\tjournal = {ChemRxiv},\n\tauthor = {{Benjamin Sanchez-Lengeling} and {Carlos Outeiral} and {Gabriel L. Guimaraes} and {Alan Aspuru-Guzik}},\n\tmonth = aug,\n\tyear = {2017},\n\tkeywords = {Adversarial Networks, Chemistry, Deep Learning, Generative Model, Information And Computing Sciences, Inverse design, Machine Learning, Mathematics, Molecular generation, Reinforcement Learning},\n}\n\n","author_short":["Benjamin Sanchez-Lengeling","Carlos Outeiral","Gabriel L. Guimaraes","Alan Aspuru-Guzik"],"key":"benjamin_sanchez-lengeling_optimizing_2017","id":"benjamin_sanchez-lengeling_optimizing_2017","bibbaseid":"benjaminsanchezlengeling-carlosouteiral-gabriellguimaraes-alanaspuruguzik-optimizingdistributionsovermolecularspaceanobjectivereinforcedgenerativeadversarialnetworkforinversedesignchemistryorganic-2017","role":"author","urls":{"Paper":"https://chemrxiv.org/articles/ORGANIC_1_pdf/5309668"},"keyword":["Adversarial Networks","Chemistry","Deep Learning","Generative Model","Information And Computing Sciences","Inverse design","Machine Learning","Mathematics","Molecular generation","Reinforcement Learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/kjelljorner","dataSources":["64RFiGdCa5JLg5kLH"],"keywords":["adversarial networks","chemistry","deep learning","generative model","information and computing sciences","inverse design","machine learning","mathematics","molecular generation","reinforcement learning"],"search_terms":["optimizing","distributions","over","molecular","space","objective","reinforced","generative","adversarial","network","inverse","design","chemistry","organic","benjamin sanchez-lengeling","carlos outeiral","gabriel l. guimaraes","alan aspuru-guzik"],"title":"Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC)","year":2017}