Title:
METHOD AND DEVICE FOR DESIGNING COMPOUND
Document Type and Number:
WIPO Patent Application WO/2021/080295
Kind Code:
A1
Abstract:
A method for generating compound information in a calculation device according to an embodiment of the present specification comprises the steps of: obtaining a learning model for information on a partial structure; obtaining information on a source molecule to be subjected to a partial structure modification; obtaining information on a partial structure set including a plurality of partial structures of the source molecule; selecting a target partial structure to be modified among the partial structures of the partial structure set; obtaining information on the modified partial structure of the target partial structure by using the learning model; and outputting result information in which the modified partial structure has been applied to the target partial structure in the source molecule.
Inventors:
YOO JI HO (KR)
HA MIN KYU (KR)
CHAE JONG HWAN (KR)
SON CHI WON (KR)
JIN SANG HYUNG (KR)
SHIN JAE HONG (KR)
KIM HAN JO (KR)
KIM SI U (KR)
SONG SANG OK (KR)
HA MIN KYU (KR)
CHAE JONG HWAN (KR)
SON CHI WON (KR)
JIN SANG HYUNG (KR)
SHIN JAE HONG (KR)
KIM HAN JO (KR)
KIM SI U (KR)
SONG SANG OK (KR)
Application Number:
PCT/KR2020/014354
Publication Date:
April 29, 2021
Filing Date:
October 20, 2020
Export Citation:
Assignee:
STANDIGM INC (KR)
International Classes:
G16C20/50; G16C20/10; G16C20/30; G16C20/60; G16C20/70
Foreign References:
KR20190087898A | 2019-07-25 |
Other References:
STÅHL NICLAS, FALKMAN GÖRAN, KARLSSON ALEXANDER, MATHIASON GUNNAR, BOSTRÖM JONAS: "Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design", JOURNAL OF CHEMICAL INFORMATION AND MODELING, vol. 59, no. 7, 19 June 2019 (2019-06-19), pages 3166 - 3176, XP055803313, ISSN: 1549-9596, DOI: 10.1021/acs.jcim.9b00325
KAWAI KENTARO, NAGATA NAOYA, TAKAHASHI YOSHIMASA: "De novo design of drug-like molecules by a fragment-based molecular evolutionary approach", JOURNAL OF CHEMICAL INFORMATION AND MODELING, vol. 54, no. 1, 28 December 2013 (2013-12-28), pages 49 - 56, XP055805856, ISSN: 1549-9596, DOI: 10.1021/ci400418c
BORIS SATTAROV, IGOR I. BASKIN, DRAGOS HORVATH, GILLES MARCOU, ESBEN JANNIK BJERRUM, ALEXANDRE VARNEK: "De novo molecular design by combining deep autoencoder recurrent neural networks with generative topographic mapping", JOURNAL OF CHEMICAL INFORMATION AND MODELING, vol. 59, no. 3, 20 February 2019 (2019-02-20), pages 1182 - 1196, XP055731747, ISSN: 1549-9596, DOI: 10.1021/acs.jcim.8b00751
JUSTIN GILMER, SAMUEL S. SCHOENHOLZ, PATRICK F. RILEY, ORIOL VINYALS, GEORGE E. DAHL: "Neural message passing for quantum chemistry", COMPUTER SCIENCE, 4 April 2017 (2017-04-04), pages 1 - 14, XP055700744
KAWAI KENTARO, NAGATA NAOYA, TAKAHASHI YOSHIMASA: "De novo design of drug-like molecules by a fragment-based molecular evolutionary approach", JOURNAL OF CHEMICAL INFORMATION AND MODELING, vol. 54, no. 1, 28 December 2013 (2013-12-28), pages 49 - 56, XP055805856, ISSN: 1549-9596, DOI: 10.1021/ci400418c
BORIS SATTAROV, IGOR I. BASKIN, DRAGOS HORVATH, GILLES MARCOU, ESBEN JANNIK BJERRUM, ALEXANDRE VARNEK: "De novo molecular design by combining deep autoencoder recurrent neural networks with generative topographic mapping", JOURNAL OF CHEMICAL INFORMATION AND MODELING, vol. 59, no. 3, 20 February 2019 (2019-02-20), pages 1182 - 1196, XP055731747, ISSN: 1549-9596, DOI: 10.1021/acs.jcim.8b00751
JUSTIN GILMER, SAMUEL S. SCHOENHOLZ, PATRICK F. RILEY, ORIOL VINYALS, GEORGE E. DAHL: "Neural message passing for quantum chemistry", COMPUTER SCIENCE, 4 April 2017 (2017-04-04), pages 1 - 14, XP055700744
Attorney, Agent or Firm:
LEE & KO IP (KR)
Download PDF: