Generative Models for Automatic Chemical Design
© 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. Materials discovery is decisive for tackling urgent challenges related to energy, the environment, health care, and many others. In chemistry, conventional methodologies for innovation...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Book |
Language: | English |
Published: |
Springer International Publishing
2022
|
Online Access: | https://hdl.handle.net/1721.1/142509.2 |
_version_ | 1811001794882437120 |
---|---|
author | Schwalbe-Koda, Daniel Gómez-Bombarelli, Rafael |
author2 | Massachusetts Institute of Technology. Department of Materials Science and Engineering |
author_facet | Massachusetts Institute of Technology. Department of Materials Science and Engineering Schwalbe-Koda, Daniel Gómez-Bombarelli, Rafael |
author_sort | Schwalbe-Koda, Daniel |
collection | MIT |
description | © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. 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 incremental strategies to optimize properties from molecular structures. On the other hand, inverse approaches map properties to structures, thus expediting the design of novel useful compounds. In this chapter, we examine the way in which current deep generative models are addressing the inverse chemical discovery paradigm. We begin by revisiting early inverse design algorithms. Then, we introduce generative models for molecular systems and categorize them according to their architecture and molecular representation. Using this classification, we review the evolution and performance of important molecular generation schemes reported in the literature. Finally, we conclude highlighting the prospects and challenges of generative models as cutting edge tools in materials discovery. |
first_indexed | 2024-09-23T15:38:18Z |
format | Book |
id | mit-1721.1/142509.2 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T15:38:18Z |
publishDate | 2022 |
publisher | Springer International Publishing |
record_format | dspace |
spelling | mit-1721.1/142509.22024-06-12T20:31:16Z Generative Models for Automatic Chemical Design Schwalbe-Koda, Daniel Gómez-Bombarelli, Rafael Massachusetts Institute of Technology. Department of Materials Science and Engineering © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG. 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 incremental strategies to optimize properties from molecular structures. On the other hand, inverse approaches map properties to structures, thus expediting the design of novel useful compounds. In this chapter, we examine the way in which current deep generative models are addressing the inverse chemical discovery paradigm. We begin by revisiting early inverse design algorithms. Then, we introduce generative models for molecular systems and categorize them according to their architecture and molecular representation. Using this classification, we review the evolution and performance of important molecular generation schemes reported in the literature. Finally, we conclude highlighting the prospects and challenges of generative models as cutting edge tools in materials discovery. 2022-07-13T20:14:10Z 2022-05-12T19:21:30Z 2022-07-13T20:14:10Z 2020-06 2022-05-12T19:15:19Z Book http://purl.org/eprint/type/BookItem 9783030402440 9783030402457 0075-8450 1616-6361 https://hdl.handle.net/1721.1/142509.2 Schwalbe-Koda, D and Gómez-Bombarelli, R. 2020. "Generative Models for Automatic Chemical Design." 968. en http://dx.doi.org/10.1007/978-3-030-40245-7_21 Machine Learning Meets Quantum Physics Attribution-NonCommercial-ShareAlike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/ application/octet-stream Springer International Publishing arXiv |
spellingShingle | Schwalbe-Koda, Daniel Gómez-Bombarelli, Rafael Generative Models for Automatic Chemical Design |
title | Generative Models for Automatic Chemical Design |
title_full | Generative Models for Automatic Chemical Design |
title_fullStr | Generative Models for Automatic Chemical Design |
title_full_unstemmed | Generative Models for Automatic Chemical Design |
title_short | Generative Models for Automatic Chemical Design |
title_sort | generative models for automatic chemical design |
url | https://hdl.handle.net/1721.1/142509.2 |
work_keys_str_mv | AT schwalbekodadaniel generativemodelsforautomaticchemicaldesign AT gomezbombarellirafael generativemodelsforautomaticchemicaldesign |