Generative AI Models for Drug Discovery

Tang, Bowen; Ewalt, John; Ng, Ho Leung

doi:10.1007/7355_2021_124

Cited by 15 publications

(8 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generative deep learning has become a promising method for chemistry and drug discovery. − Generative models learn the pattern distribution of the input data and generate new data instances based on learned probabilities . Among the proposed generative frameworks that have been applied to de novo molecular design, − chemical language models (CLMs) have gained attention because of their ability to generate focused virtual chemical libraries and bioactive compounds. ,, CLMs are trained on string representations of molecules, e.g ., simplified molecular input line entry system (SMILES) strings (Figure a), to iteratively predict the next SMILES character using all the preceding portions of the SMILES string (Figure b). In this process, CLMs learn the conditional probability of sampling any SMILES character based on the preceding characters in the string.…”

Section: Introductionmentioning

confidence: 99%

Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models

Moret

Grisoni

Katzberger

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Chemical language models (CLMs) can be employed to design molecules with desired properties. CLMs generate new chemical structures in the form of textual representations, such as the simplified molecular input line entry system (SMILES) strings. However, the quality of these de novo generated molecules is difficult to assess a priori. In this study, we apply the perplexity metric to determine the degree to which the molecules generated by a CLM match the desired design objectives. This model-intrinsic score allows identifying and ranking the most promising molecular designs based on the probabilities learned by the CLM. Using perplexity to compare “greedy” (beam search) with “explorative” (multinomial sampling) methods for SMILES generation, certain advantages of multinomial sampling become apparent. Additionally, perplexity scoring is performed to identify undesired model biases introduced during model training and allows the development of a new ranking system to remove those undesired biases.

show abstract

Section: Introductionmentioning

confidence: 99%

Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models

Moret

Grisoni

Katzberger

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…A novel fragment-based molecular graph is utilized by CAFE-MPP, a self-supervised contrastive learning framework, to represent the topological relationship between chemistry-aware substructures comprising a molecule . Generative pretrained transformers (GPT), an advanced AI technique that understands and generates complex patterns, optimizes FBDD ligands in the APEX-FBDD model . The ADQN-FBDD model efficiently designs molecules by adding fragments using an advanced version of deep Q-learning, a reinforcement learning technique, to develop covalent inhibitors. , PharmHGT uses graph-based generative models and deep evolutionary learning to optimize molecules for drug design properties and binding affinities at scale .…”

Section: Rational Drug Design Technologiesmentioning

confidence: 99%

“…Generative pretrained transformers (GPT), an advanced AI technique that understands and generates complex patterns, optimizes FBDD ligands in the APEX-FBDD model . The ADQN-FBDD model efficiently designs molecules by adding fragments using an advanced version of deep Q-learning, a reinforcement learning technique, to develop covalent inhibitors. , PharmHGT uses graph-based generative models and deep evolutionary learning to optimize molecules for drug design properties and binding affinities at scale . The performance of this framework (Figure ) has been shown to be at the forefront of its field on multiple benchmark data sets …”

Section: Rational Drug Design Technologiesmentioning

confidence: 99%

Deciphering the Lexicon of Protein Targets: A Review on Multifaceted Drug Discovery in the Era of Artificial Intelligence

Nandi,

Bhaduri,

Das

et al. 2024

Mol. Pharmaceutics

View full text Add to dashboard Cite

Understanding protein sequence and structure is essential for understanding protein−protein interactions (PPIs), which are essential for many biological processes and diseases. Targeting protein binding hot spots, which regulate signaling and growth, with rational drug design is promising. Rational drug design uses structural data and computational tools to study protein binding sites and protein interfaces to design inhibitors that can change these interactions, thereby potentially leading to therapeutic approaches. Artificial intelligence (AI), such as machine learning (ML) and deep learning (DL), has advanced drug discovery and design by providing computational resources and methods. Quantum chemistry is essential for drug reactivity, toxicology, drug screening, and quantitative structure−activity relationship (QSAR) properties. This review discusses the methodologies and challenges of identifying and characterizing hot spots and binding sites. It also explores the strategies and applications of artificial-intelligence-based rational drug design technologies that target proteins and protein−protein interaction (PPI) binding hot spots. It provides valuable insights for drug design with therapeutic implications. We have also demonstrated the pathological conditions of heat shock protein 27 (HSP27) and matrix metallopoproteinases (MMP2 and MMP9) and designed inhibitors of these proteins using the drug discovery paradigm in a case study on the discovery of drug molecules for cancer treatment. Additionally, the implications of benzothiazole derivatives for anticancer drug design and discovery are deliberated.

show abstract

“…It would be more productive if candidate molecules are generated, rather than screened from libraries, with suitable absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties as prerequisites at the beginning of the molecule design process . AI molecule generation models are widely used for designing drug candidates using prior biological and chemical knowledge in drug discovery. , By using a combination of AI generative techniques and reinforcement learning, Insilico Medicine successfully created new discoidin domain receptor 1 (DDR1) kinase inhibitors to treat fibrosis in only 21 days . Despite all generated molecules being chemically meaningful, they may be too difficult/expensive to synthesize and have poor drug-like properties.…”

Section: Introductionmentioning

confidence: 99%

“… 11 AI molecule generation models are widely used for designing drug candidates using prior biological and chemical knowledge in drug discovery. 11 , 12 By using a combination of AI generative techniques and reinforcement learning, Insilico Medicine successfully created new discoidin domain receptor 1 (DDR1) kinase inhibitors to treat fibrosis in only 21 days. 13 Despite all generated molecules being chemically meaningful, they may be too difficult/expensive to synthesize and have poor drug-like properties.…”

Section: Introductionmentioning

confidence: 99%

MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery

Yang,

Xie,

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

show abstract

Generative AI Models for Drug Discovery

Cited by 15 publications

References 55 publications

Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models

Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models

Deciphering the Lexicon of Protein Targets: A Review on Multifaceted Drug Discovery in the Era of Artificial Intelligence

MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery

Contact Info

Product

Resources

About