his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. (Skövde Artificial Intelligence Lab (SAIL))ORCID-id: 0000-0003-2128-7090
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. (Skövde Artificial Intelligence Lab (SAIL))ORCID-id: 0000-0001-8884-2154
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. (Skövde Artificial Intelligence Lab (SAIL))ORCID-id: 0000-0003-2973-3112
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. (Skövde Artificial Intelligence Lab (SAIL))ORCID-id: 0000-0001-7106-0025
Vise andre og tillknytning
2019 (engelsk)Inngår i: Journal of Chemical Information and Modeling, ISSN 1549-9596, E-ISSN 1549-960X, Vol. 59, nr 7, s. 3166-3176Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex, and difficult multiparameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modeled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improving these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output toward structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid and more than a third satisfy the targeted objectives, while there were none in the initial set.

sted, utgiver, år, opplag, sider
American Chemical Society (ACS), 2019. Vol. 59, nr 7, s. 3166-3176
Emneord [en]
algorithms, molecules
HSV kategori
Forskningsprogram
Skövde Artificial Intelligence Lab (SAIL)
Identifikatorer
URN: urn:nbn:se:his:diva-17503DOI: 10.1021/acs.jcim.9b00325ISI: 000477074900010PubMedID: 31273995Scopus ID: 2-s2.0-85070180995OAI: oai:DiVA.org:his-17503DiVA, id: diva2:1341460
Tilgjengelig fra: 2019-08-08 Laget: 2019-08-08 Sist oppdatert: 2019-11-13bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstPubMedScopus

Personposter BETA

Ståhl, NiclasFalkman, GöranKarlsson, AlexanderMathiason, Gunnar

Søk i DiVA

Av forfatter/redaktør
Ståhl, NiclasFalkman, GöranKarlsson, AlexanderMathiason, Gunnar
Av organisasjonen
I samme tidsskrift
Journal of Chemical Information and Modeling

Søk utenfor DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric

doi
pubmed
urn-nbn
Totalt: 270 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf