Multi-Objective Drug Design Based on Graph-Fragment Molecular Representation and Deep Evolutionary Learning

Mukaidaisi, Muhetaer; Vu, Andrew; Grantham, Karl; Tchagang, Alain B.; Li, Yifeng

doi:10.3389/fphar.2022.920747

Cited by 21 publications

(22 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computational de novo drug design involves the use of techniques such as genetic algorithms, − reinforcement learning, including deep reinforcement learning, − generative deep learning models, − or other deep learning methods, e.g., graph transformers, , models that blend deep learning and evolutionary algorithms, ,, and string-based transformers (i.e., operating on a simplified molecular-input line-entry system (SMILES) string representation of molecules). , The algorithms “computationally synthesize” novel drug molecules, either by starting from scratch and adding atoms to form a novel molecule or by modifying or adding atoms to an existing chemical structure (“scaffold”). The result is the creation of novel molecules by (a) simulating chemical modifications that optimize for the single objective of improving binding efficiency to a target or (b) multiobjective optimization including drug-likeness objectives, e.g., solubility and other drug-likeness factors. ,− …”

Section: Introductionmentioning

confidence: 99%

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Chandraghatgi,

Ji,

Rosen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug−target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

show abstract

Section: Introductionmentioning

confidence: 99%

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Chandraghatgi,

Ji,

Rosen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Recently, some research utilized genomic algorithms (GAs), such as Monte-Carlo Tree Search (MCTS), instead of DGM, demonstrating that GAs served as potent candidates for searching for desired chemical compounds [ 19 , 20 ]. These search-based methods generally regard molecule fragments as tree nodes, and the whole process can be viewed as searching for a feasible connection between the existing root and leaves [ 21 , 22 ]. Feasible connections not only ensure the validity of generated molecules but also make the molecular exploring process more efficient.…”

Section: Introductionmentioning

confidence: 99%

“…Feasible connections not only ensure the validity of generated molecules but also make the molecular exploring process more efficient. However, the search process needs to get feedback from third-part supervision, which could be a scoring function, a neural network [ 22 ], or some mechanism such as expectation maximization [ 23 ]. This step requires extra training and must be devised precisely to ensure it leads the search process in the right direction.…”

Section: Introductionmentioning

confidence: 99%

Magicmol: a light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration

2023

View full text Add to dashboard Cite

The flourishment of machine learning and deep learning methods has boosted the development of cheminformatics, especially regarding the application of drug discovery and new material exploration. Lower time and space expenses make it possible for scientists to search the enormous chemical space. Recently, some work combined reinforcement learning strategies with recurrent neural network (RNN)-based models to optimize the property of generated small molecules, which notably improved a batch of critical factors for these candidates. However, a common problem among these RNN-based methods is that several generated molecules have difficulty in synthesizing despite owning higher desired properties such as binding affinity. However, RNN-based framework better reproduces the molecule distribution among the training set than other categories of models during molecule exploration tasks. Thus, to optimize the whole exploration process and make it contribute to the optimization of specified molecules, we devised a light-weighted pipeline called Magicmol; this pipeline has a re-mastered RNN network and utilize SELFIES presentation instead of SMILES. Our backbone model achieved extraordinary performance while reducing the training cost; moreover, we devised reward truncate strategies to eliminate the model collapse problem. Additionally, adopting SELFIES presentation made it possible to combine STONED-SELFIES as a post-processing procedure for specified molecule optimization and quick chemical space exploration.

show abstract

“…Recently, some research utilized GA (Genomic Algorithm) such as Monte-Carlo Tree Search (MCTS) instead of DGM and proved GAs served as a potent candidate for searching for the desired chemical compounds [18,19]. This search-based methods generally regard molecule fragments as the tree nodes, and the whole process can be viewed as searching for a feasible connection between the generated midbody and the nodes [20,21]. The possibility for feasible connections not only ensure the validity of generated molecules but also make the search process efficient.…”

Section: Introductionmentioning

confidence: 99%

“…The possibility for feasible connections not only ensure the validity of generated molecules but also make the search process efficient. However, the search process needs to get feedback from the thirdpart supervision, which could be a scoring function, a neural network [21], or some mechanism such as Expectation Maximization [22]. This step needs extra training and devise precisely for a reason to ensure it will lead the search process in the right direction.…”

Section: Introductionmentioning

confidence: 99%

Magicmol - A light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration

Chen

Shen

Lou

2022

Preprint

View full text Add to dashboard Cite

The flourishment of machine learning and deep learning methods have boosted the development of cheminformatics, especially when it comes to the application of drug discovery and new materials exploration. Lower time and space expenses make it possible for scientists to search the enormous chemical space. Recently, some work combines reinforcement learning strategies with an RNN-based (Recurrent Neural Networks) model to optimize the property of generated drug-like molecules, which notably improved a batch of critical factors for these drug candidates. However, a common problem of these RNN-based methods is that several generated molecules have difficulty in synthesizing even if owning higher desired properties such as binding affinity. But still, the RNN-based framework appears well in reproducing the molecule distribution among the training set than other categories of models when it comes to the molecule exploration tasks. Thus, to optimize the whole exploring process and make it contribute to the optimization of specified molecules. In this paper, we devised a light-weighted pipeline called - Magicmol with a re-mastered RNN network and use SELFIES presentation instead of SMILES. Our backbone model achieve extraordinary performance in evaluating metrics meanwhile reduced the training cost and we devised reward truncate strategies to eliminate the ”model collapse” problem. Also, adopting SELFIES presentation makes it possible for combining STONED-SELFIES as a post-processing procedure for specified molecule optimization and quick chemical space exploration.

show abstract

Multi-Objective Drug Design Based on Graph-Fragment Molecular Representation and Deep Evolutionary Learning

Cited by 21 publications

References 37 publications

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Magicmol: a light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration

Magicmol - A light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration

Contact Info

Product

Resources

About