Title:
DEEP LEARNING-BASED MOLECULE DESIGN METHOD, AND DEVICE AND COMPUTER PROGRAM FOR PERFORMING SAME
Document Type and Number:
WIPO Patent Application WO/2023/171886
Kind Code:
A1
Abstract:
A deep learning-based molecule design method, and a device and a computer program for performing same according to a preferred embodiment of the present invention pre-train a variational autoencoder (VAE) by using a Gumbel-Softmax function and design a molecule corresponding to a user-requested molecular characteristic by using the pre-trained VAE and a genetic algorithm (GA), thereby converting the SMILES representation of a molecular structure to a binary vector representation so that a search range of a latent space can be restricted to a limited space.
Inventors:
PARK SANG HYUN (KR)
CHOI JONG HWAN (KR)
SEO SANG MIN (KR)
PARK JIN UK (KR)
CHOI JONG HWAN (KR)
SEO SANG MIN (KR)
PARK JIN UK (KR)
Application Number:
PCT/KR2022/020117
Publication Date:
September 14, 2023
Filing Date:
December 12, 2022
Export Citation:
Assignee:
UIF UNIV INDUSTRY FOUNDATION YONSEI UNIV (KR)
International Classes:
G16C20/50; G06N3/04; G06N3/08; G16B10/00; G16B15/00; G16B40/20; G16C20/70
Domestic Patent References:
| WO2020190887A1 | 2020-09-24 |
Foreign References:
| KR20190087898A | 2019-07-25 | |||
| US20200401916A1 | 2020-12-24 |
Other References:
WUJIE WANG; RAFAEL GÓMEZ-BOMBARELLI: "Coarse-Graining Auto-Encoders for Molecular Dynamics", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 December 2018 (2018-12-06), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081124252
HANJUN DAI; YINGTAO TIAN; BO DAI; STEVEN SKIENA; LE SONG: "Syntax-Directed Variational Autoencoder for Structured Data", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 February 2018 (2018-02-24), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081218386
CHOI JONGHWAN; SEO SANGMIN; PARK JINUK; PARK SANGHYUN: "MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem", 2021 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), IEEE, 9 December 2021 (2021-12-09), pages 364 - 367, XP034066685, DOI: 10.1109/BIBM52615.2021.9669668
CHOI JONGHWAN; SEO SANGMIN; PARK JINUK; PARK SANGHYUN: "MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem", 2021 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), IEEE, 9 December 2021 (2021-12-09), pages 364 - 367, XP034066685, DOI: 10.1109/BIBM52615.2021.9669668
HANJUN DAI; YINGTAO TIAN; BO DAI; STEVEN SKIENA; LE SONG: "Syntax-Directed Variational Autoencoder for Structured Data", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 February 2018 (2018-02-24), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081218386
CHOI JONGHWAN; SEO SANGMIN; PARK JINUK; PARK SANGHYUN: "MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem", 2021 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), IEEE, 9 December 2021 (2021-12-09), pages 364 - 367, XP034066685, DOI: 10.1109/BIBM52615.2021.9669668
CHOI JONGHWAN; SEO SANGMIN; PARK JINUK; PARK SANGHYUN: "MolBit: De novo Drug Design via Binary Representations of SMILES for avoiding the Posterior Collapse Problem", 2021 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), IEEE, 9 December 2021 (2021-12-09), pages 364 - 367, XP034066685, DOI: 10.1109/BIBM52615.2021.9669668
Attorney, Agent or Firm:
WOOIN PATENT & LAW FIRM (KR)
Download PDF: