A transfer learning approach for reaction discovery in small data situations using generative model

Summary: Sustainable practices in chemical sciences can be better realized by adopting interdisciplinary approaches that combine the advantages of machine learning (ML) on the initially acquired small data in reaction discovery. Developing new reactions generally remains heuristic and even time and...

Full description

Bibliographic Details
Main Authors: Sukriti Singh, Raghavan B. Sunoj
Format: Article
Language:English
Published: Elsevier 2022-07-01
Series:iScience
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589004222009336
_version_ 1828517027818504192
author Sukriti Singh
Raghavan B. Sunoj
author_facet Sukriti Singh
Raghavan B. Sunoj
author_sort Sukriti Singh
collection DOAJ
description Summary: Sustainable practices in chemical sciences can be better realized by adopting interdisciplinary approaches that combine the advantages of machine learning (ML) on the initially acquired small data in reaction discovery. Developing new reactions generally remains heuristic and even time and resource intensive. For instance, synthesis of fluorine-containing compounds, which constitute ∼20% of the marketed drugs, relies on deoxyfluorination of abundantly available alcohols. Herein, we demonstrate the use of a recurrent neural network-based deep generative model built on a library of just 37 alcohols for effective learning and exploration of the chemical space. The proof-of-concept ML model is able to generate good quality, synthetically accessible, higher-yielding novel alcohol molecules. This protocol would have superior utility for deployment into a practical reaction discovery pipeline.
first_indexed 2024-12-11T18:35:58Z
format Article
id doaj.art-31a2ed378fd74741a10e82211622f63c
institution Directory Open Access Journal
issn 2589-0042
language English
last_indexed 2024-12-11T18:35:58Z
publishDate 2022-07-01
publisher Elsevier
record_format Article
series iScience
spelling doaj.art-31a2ed378fd74741a10e82211622f63c2022-12-22T00:54:46ZengElsevieriScience2589-00422022-07-01257104661A transfer learning approach for reaction discovery in small data situations using generative modelSukriti Singh0Raghavan B. Sunoj1Department of Chemistry, Indian Institute of Technology Bombay, Mumbai 400076, India; Corresponding authorDepartment of Chemistry, Indian Institute of Technology Bombay, Mumbai 400076, India; Centre for Machine Intelligence and Data Science, Indian Institute of Technology Bombay, Mumbai 400076, India; Corresponding authorSummary: Sustainable practices in chemical sciences can be better realized by adopting interdisciplinary approaches that combine the advantages of machine learning (ML) on the initially acquired small data in reaction discovery. Developing new reactions generally remains heuristic and even time and resource intensive. For instance, synthesis of fluorine-containing compounds, which constitute ∼20% of the marketed drugs, relies on deoxyfluorination of abundantly available alcohols. Herein, we demonstrate the use of a recurrent neural network-based deep generative model built on a library of just 37 alcohols for effective learning and exploration of the chemical space. The proof-of-concept ML model is able to generate good quality, synthetically accessible, higher-yielding novel alcohol molecules. This protocol would have superior utility for deployment into a practical reaction discovery pipeline.http://www.sciencedirect.com/science/article/pii/S2589004222009336Artificial intelligenceComputational chemistryFunctional group chemistryModeling chemical reactivity
spellingShingle Sukriti Singh
Raghavan B. Sunoj
A transfer learning approach for reaction discovery in small data situations using generative model
iScience
Artificial intelligence
Computational chemistry
Functional group chemistry
Modeling chemical reactivity
title A transfer learning approach for reaction discovery in small data situations using generative model
title_full A transfer learning approach for reaction discovery in small data situations using generative model
title_fullStr A transfer learning approach for reaction discovery in small data situations using generative model
title_full_unstemmed A transfer learning approach for reaction discovery in small data situations using generative model
title_short A transfer learning approach for reaction discovery in small data situations using generative model
title_sort transfer learning approach for reaction discovery in small data situations using generative model
topic Artificial intelligence
Computational chemistry
Functional group chemistry
Modeling chemical reactivity
url http://www.sciencedirect.com/science/article/pii/S2589004222009336
work_keys_str_mv AT sukritisingh atransferlearningapproachforreactiondiscoveryinsmalldatasituationsusinggenerativemodel
AT raghavanbsunoj atransferlearningapproachforreactiondiscoveryinsmalldatasituationsusinggenerativemodel
AT sukritisingh transferlearningapproachforreactiondiscoveryinsmalldatasituationsusinggenerativemodel
AT raghavanbsunoj transferlearningapproachforreactiondiscoveryinsmalldatasituationsusinggenerativemodel