Exploring the role of topological descriptors to predict physicochemical properties of anti-HIV drugs by using supervised machine learning algorithms

BMC Chemistry, Journal Year: 2024, Volume and Issue: 18(1)

Published: Sept. 12, 2024

Language: Английский

---

Meta-MolNet: A Cross-Domain Benchmark for Few Examples Drug Discovery

IEEE Transactions on Neural Networks and Learning Systems, Journal Year: 2024, Volume and Issue: 36(3), P. 4849 - 4863

Published: Feb. 14, 2024

Predicting the pharmacological activity, toxicity, and pharmacokinetic properties of molecules is a central task in drug discovery. Existing machine learning methods are transferred from one resource rich molecular property to another data scarce same scaffold dataset. However, existing models may produce fragile highly uncertain predictions for new molecules. And these were tested on different benchmarks, which seriously affected quality their evaluation results. In this article, we introduce Meta-MolNet, collection benchmark algorithms, standard platform measuring model generalization uncertainty quantification capabilities. Meta-MolNet manages wide range datasets with high ratio molecules/scaffolds, often leads more difficult shift problems. Furthermore, propose graph attention network based cross-domain meta-learning, Meta-GAT, uses bilevel optimization learn meta-knowledge family dataset source domain. Meta-GAT benefits that reduces requirement sample complexity enable reliable target domain through internal iteration few examples. We evaluate as baselines community, demonstrates effectiveness proposed algorithm quantification. Extensive experiments demonstrate has state-of-the-art performance robustly estimates under examples constraints. By publishing AI-ready data, frameworks, baseline results, hope see suite become comprehensive AI-assisted discovery community. freely accessible at https://github.com/lol88/Meta-MolNet.

Language: Английский

---

AI Empowering Traditional Chinese Medicine?

Chemical Science, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

AI-powered analysis of TCM chemical data enhances component identification, drug discovery, personalized treatment, and pharmacological action elucidation, driving the modernization sustainable development TCM.

Language: Английский

---

Systems Theory-Driven Framework for AI Integration into the Holistic Material Basis Research of Traditional Chinese Medicine

Engineering, Journal Year: 2024, Volume and Issue: 40, P. 28 - 50

Published: April 26, 2024

This research introduces a systems theory-driven framework to integration artificial intelligence (AI) into traditional Chinese medicine (TCM) research, enhancing the understanding of TCM's holistic material basis while adhering evidence-based principles. Utilizing System Function Decoding Model (SFDM), progresses through define, quantify, infer, and validate phases systematically explore basis. It employs dual analytical approach that combines top-down, theory-guided perspectives with bottom-up, elements–structure–function methodologies, provides comprehensive insights Moreover, examines AI's role in quantitative assessment predictive analysis components, proposing two specific AI-driven technical applications. interdisciplinary effort underscores potential enhance our establishes foundation for future at intersection wisdom modern technology.

Language: Английский

---

Emerging opportunities of using large language models for translation between drug molecules and indications

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: May 10, 2024

Abstract A drug molecule is a substance that changes an organism’s mental or physical state. Every approved has indication, which refers to the therapeutic use of for treating particular medical condition. While Large Language Model (LLM), generative Artificial Intelligence (AI) technique, recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains gap research regarding application facilitating translation indications (which describes disease, condition symptoms used), vice versa. Addressing this challenge could greatly benefit discovery process. The capability generating from given indication would allow drugs targeting specific diseases targets ultimately provide patients with better treatments. In paper, we first propose new task, corresponding indications, then test existing LLMs on task. Specifically, consider nine variations T5 LLM evaluate them two public datasets obtained ChEMBL DrugBank. Our experiments show early results using task perspective state-of-the-art. We also emphasize current limitations discuss future work potential improve performance creation versa, will more efficient significantly reduce cost discovery, revolutionize field era AI.

Language: Английский

---

Big Data Analytics in Bioinformatics and Healthcare

Studies in big data, Journal Year: 2025, Volume and Issue: unknown, P. 71 - 95

Published: Jan. 1, 2025

Language: Английский

---

TCMKD: From ancient wisdom to modern insights-A comprehensive platform for traditional Chinese medicine knowledge discovery

Journal of Pharmaceutical Analysis, Journal Year: 2025, Volume and Issue: unknown, P. 101297 - 101297

Published: April 1, 2025

Language: Английский

---

Artificial intelligence in traditional Chinese medicine: advances in multi-metabolite multi-target interaction modeling

Frontiers in Pharmacology, Journal Year: 2025, Volume and Issue: 16

Published: April 15, 2025

Traditional Chinese Medicine (TCM) utilizes multi-metabolite and multi-target interventions to address complex diseases, providing advantages over single-target therapies. However, the active metabolites, therapeutic targets, especially combination mechanisms remain unclear. The integration of advanced data analysis nonlinear modeling capabilities artificial intelligence (AI) is driving transformation TCM into precision medicine. This review concentrates on application AI in target prediction, including multi-omics techniques, TCM-specialized databases, machine learning (ML), deep (DL), cross-modal fusion strategies. It also critically analyzes persistent challenges such as heterogeneity, limited model interpretability, causal confounding, insufficient robustness validation practical applications. To enhance reliability scalability future research should prioritize continuous optimization algorithms using zero-shot learning, end-to-end architectures, self-supervised contrastive learning.

Language: Английский

---

Quantifying compatibility mechanisms in traditional Chinese medicine with interpretable graph neural networks

Journal of Pharmaceutical Analysis, Journal Year: 2025, Volume and Issue: unknown, P. 101342 - 101342

Published: May 1, 2025

Language: Английский

---

Artificial intelligence-driven metabolic engineering is applied to the development of active ingredients in Traditional Chinese Medicine

BIO Web of Conferences, Journal Year: 2025, Volume and Issue: 174, P. 03013 - 03013

Published: Jan. 1, 2025

Metabolic engineering serves as a pivotal component in establishing microbial platforms for the effective biosynthesis of expensive compounds, therapeutic agents, and vegetative production systems. This field necessitates thorough comprehension intracellular biochemical networks (encompassing molecular transformation routes corresponding catalytic proteins). Nevertheless, critical catalysts that control numerous high-value target molecules have not been fully characterized, which is main bottleneck heterologous synthesis chemicals. To address this limitation, scientists devised optimized circuits through artificial biocatalysts de novo reaction sequences. With continuous accumulation biological big data, data-driven methods intelligence (AI) technology are promoting further development protein metabolic pathway design. In paper, we introduce AI-driven machine learning algorithms prediction models, also review recent research progress on AI-assisted design focusing how to use AI achieve directed evolution strains.

Language: Английский

---