DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning
Abstract Rational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of deep learning in drug discovery, a variety of effective app...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-02-01
|
Series: | Journal of Cheminformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13321-023-00694-z |
_version_ | 1797863712978108416 |
---|---|
author | Xuhan Liu Kai Ye Herman W. T. van Vlijmen Adriaan P. IJzerman Gerard J. P. van Westen |
author_facet | Xuhan Liu Kai Ye Herman W. T. van Vlijmen Adriaan P. IJzerman Gerard J. P. van Westen |
author_sort | Xuhan Liu |
collection | DOAJ |
description | Abstract Rational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of deep learning in drug discovery, a variety of effective approaches have been developed for de novo drug design. In previous work we proposed a method named DrugEx, which can be applied in polypharmacology based on multi-objective deep reinforcement learning. However, the previous version is trained under fixed objectives and does not allow users to input any prior information (i.e. a desired scaffold). In order to improve the general applicability, we updated DrugEx to design drug molecules based on scaffolds which consist of multiple fragments provided by users. Here, a Transformer model was employed to generate molecular structures. The Transformer is a multi-head self-attention deep learning model containing an encoder to receive scaffolds as input and a decoder to generate molecules as output. In order to deal with the graph representation of molecules a novel positional encoding for each atom and bond based on an adjacency matrix was proposed, extending the architecture of the Transformer. The graph Transformer model contains growing and connecting procedures for molecule generation starting from a given scaffold based on fragments. Moreover, the generator was trained under a reinforcement learning framework to increase the number of desired ligands. As a proof of concept, the method was applied to design ligands for the adenosine A2A receptor (A2AAR) and compared with SMILES-based methods. The results show that 100% of the generated molecules are valid and most of them had a high predicted affinity value towards A2AAR with given scaffolds. |
first_indexed | 2024-04-09T22:40:08Z |
format | Article |
id | doaj.art-12e2403ede4e4bc28f5d4d15dd0d5517 |
institution | Directory Open Access Journal |
issn | 1758-2946 |
language | English |
last_indexed | 2024-04-09T22:40:08Z |
publishDate | 2023-02-01 |
publisher | BMC |
record_format | Article |
series | Journal of Cheminformatics |
spelling | doaj.art-12e2403ede4e4bc28f5d4d15dd0d55172023-03-22T12:13:20ZengBMCJournal of Cheminformatics1758-29462023-02-0115111410.1186/s13321-023-00694-zDrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learningXuhan Liu0Kai Ye1Herman W. T. van Vlijmen2Adriaan P. IJzerman3Gerard J. P. van Westen4Drug Discovery and Safety, Leiden Academic Centre for Drug ResearchSchool of Electrics and Information Engineering, Xi’an Jiaotong UniversityDrug Discovery and Safety, Leiden Academic Centre for Drug ResearchDrug Discovery and Safety, Leiden Academic Centre for Drug ResearchDrug Discovery and Safety, Leiden Academic Centre for Drug ResearchAbstract Rational drug design often starts from specific scaffolds to which side chains/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of deep learning in drug discovery, a variety of effective approaches have been developed for de novo drug design. In previous work we proposed a method named DrugEx, which can be applied in polypharmacology based on multi-objective deep reinforcement learning. However, the previous version is trained under fixed objectives and does not allow users to input any prior information (i.e. a desired scaffold). In order to improve the general applicability, we updated DrugEx to design drug molecules based on scaffolds which consist of multiple fragments provided by users. Here, a Transformer model was employed to generate molecular structures. The Transformer is a multi-head self-attention deep learning model containing an encoder to receive scaffolds as input and a decoder to generate molecules as output. In order to deal with the graph representation of molecules a novel positional encoding for each atom and bond based on an adjacency matrix was proposed, extending the architecture of the Transformer. The graph Transformer model contains growing and connecting procedures for molecule generation starting from a given scaffold based on fragments. Moreover, the generator was trained under a reinforcement learning framework to increase the number of desired ligands. As a proof of concept, the method was applied to design ligands for the adenosine A2A receptor (A2AAR) and compared with SMILES-based methods. The results show that 100% of the generated molecules are valid and most of them had a high predicted affinity value towards A2AAR with given scaffolds.https://doi.org/10.1186/s13321-023-00694-zDeep learningReinforcement learningPolicy gradientDrug designTransformerMulti-objective optimization |
spellingShingle | Xuhan Liu Kai Ye Herman W. T. van Vlijmen Adriaan P. IJzerman Gerard J. P. van Westen DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning Journal of Cheminformatics Deep learning Reinforcement learning Policy gradient Drug design Transformer Multi-objective optimization |
title | DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning |
title_full | DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning |
title_fullStr | DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning |
title_full_unstemmed | DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning |
title_short | DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning |
title_sort | drugex v3 scaffold constrained drug design with graph transformer based reinforcement learning |
topic | Deep learning Reinforcement learning Policy gradient Drug design Transformer Multi-objective optimization |
url | https://doi.org/10.1186/s13321-023-00694-z |
work_keys_str_mv | AT xuhanliu drugexv3scaffoldconstraineddrugdesignwithgraphtransformerbasedreinforcementlearning AT kaiye drugexv3scaffoldconstraineddrugdesignwithgraphtransformerbasedreinforcementlearning AT hermanwtvanvlijmen drugexv3scaffoldconstraineddrugdesignwithgraphtransformerbasedreinforcementlearning AT adriaanpijzerman drugexv3scaffoldconstraineddrugdesignwithgraphtransformerbasedreinforcementlearning AT gerardjpvanwesten drugexv3scaffoldconstraineddrugdesignwithgraphtransformerbasedreinforcementlearning |