Sökning: id:"swepub:oai:gup.ub.gu.se/336880" >
Utilizing reinforce...
Utilizing reinforcement learning for de novo drug design
-
- Gummesson Svensson, Hampus, 1996 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för data- och informationsteknik (GU),Department of Computer Science and Engineering (GU),Chalmers tekniska högskola,Chalmers University of Technology,AstraZeneca AB
-
- Tyrchan, Christian (författare)
- AstraZeneca AB
-
- Engkvist, Ola, 1967 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för data- och informationsteknik (GU),Department of Computer Science and Engineering (GU),AstraZeneca AB,Chalmers tekniska högskola,Chalmers University of Technology
-
visa fler...
-
- Haghir Chehreghani, Morteza, 1982 (författare)
- Gothenburg University,Göteborgs universitet,Institutionen för data- och informationsteknik (GU),Department of Computer Science and Engineering (GU),Chalmers tekniska högskola,Chalmers University of Technology
-
visa färre...
-
(creator_code:org_t)
- 2024
- 2024
- Engelska.
-
Ingår i: MACHINE LEARNING. - 0885-6125 .- 1573-0565.
- Relaterad länk:
-
https://gup.ub.gu.se...
-
visa fler...
-
https://doi.org/10.1...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- De novo drug design
- Reinforcement learning
- Policy optimization
- Replay buffer
- Recurrent neural network
- Policy optimization
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas