2021
DOI: 10.1186/s13321-021-00572-6
|View full text |Cite
|
Sign up to set email alerts
|

MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning

Abstract: The hit-to-lead process makes the physicochemical properties of the hit molecules that show the desired type of activity obtained in the screening assay more drug-like. Deep learning-based molecular generative models are expected to contribute to the hit-to-lead process. The simplified molecular input line entry system (SMILES), which is a string of alphanumeric characters representing the chemical structure of a molecule, is one of the most commonly used representations of molecules, and molecular generative … Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
11
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
8
2

Relationship

2
8

Authors

Journals

citations
Cited by 22 publications
(11 citation statements)
references
References 27 publications
0
11
0
Order By: Relevance
“…In recent years, with the rapid development of artificial intelligence (AI) technology, its application to molecular design has attracted considerable attention. In particular, deep learning models such as recurrent neural networks (RNNs), [18][19][20] variational autoencoders (VAEs), 21,22 generative adversarial networks (GANs), [23][24][25] and graph neural networks (GNNs) 26 have successfully generated novel compounds using molecular graphs and simplified molecular input line entry system (SMILES) 27 representations and are expected to be powerful tools for molecular design.…”
Section: Introductionmentioning
confidence: 99%
“…In recent years, with the rapid development of artificial intelligence (AI) technology, its application to molecular design has attracted considerable attention. In particular, deep learning models such as recurrent neural networks (RNNs), [18][19][20] variational autoencoders (VAEs), 21,22 generative adversarial networks (GANs), [23][24][25] and graph neural networks (GNNs) 26 have successfully generated novel compounds using molecular graphs and simplified molecular input line entry system (SMILES) 27 representations and are expected to be powerful tools for molecular design.…”
Section: Introductionmentioning
confidence: 99%
“…Ligand-based drug design (LBDD) is based on activity values (such as half-maximal inhibitory concentration, IC 50 ), and known compound properties involved in drug binding. Representative methods in LBDD include quantitative structure-activity relationship (QSAR) and machine learning. Alternatively, structure-based drug design (SBDD) bases the design process on a target protein structure. In SBDD, the discovery of the target protein binding site is a fundamental starting point. , Typically, the protein binding site is identified by X-ray analysis and the drug is designed or optimized based on information from that analysis.…”
Section: Introductionmentioning
confidence: 99%
“…With recent advances in machine learning-aided drug discovery, , many in silico methods have been proposed to help accelerate the drug discovery process due to their prediction power with high efficiency and low cost compared with wet-lab experiments, such as virtual screening, compound property prediction, molecule generation, and molecule optimization. There are also machine learning-based QSAR models developed for analyzing and predicting compound activities. …”
Section: Introductionmentioning
confidence: 99%