Seeking innovative concepts in development of antiviral drug combinations

Antiviral Research, Journal Year: 2025, Volume and Issue: 234, P. 106079 - 106079

Published: Jan. 9, 2025

Language: Английский

---

Restoring Homeostasis: Treating Amyotrophic Lateral Sclerosis by Resolving Dynamic Regulatory Instability

International Journal of Molecular Sciences, Journal Year: 2025, Volume and Issue: 26(3), P. 872 - 872

Published: Jan. 21, 2025

Amyotrophic lateral sclerosis (ALS) has an interactive, multifactorial etiology that makes treatment success elusive. This study evaluates how regulatory dynamics impact disease progression and treatment. Computational models of wild-type (WT) transgenic SOD1-G93A mouse physiology were built using the first-principles-based first-order feedback framework dynamic meta-analysis with parameter optimization. Two in silico developed: a WT model to simulate normal homeostasis ALS pathology their response treatments. The simulates functional molecular mechanisms for apoptosis, metal chelation, energetics, excitotoxicity, inflammation, oxidative stress, proteomics curated data from published experiments. Temporal measures (rotarod, grip strength, body weight) used validation. Results illustrate untreated cannot maintain due mathematical oscillating instability as determined by eigenvalue analysis. onset magnitude homeostatic corresponded progression. Oscillations associated high gain hypervigilant regulation. Multiple combination treatments stabilized near-normal homeostasis. However, timing effect size critical stabilization corresponding therapeutic success. dynamics-based approach redefines strategies emphasizing restoration through precisely timed stabilizing therapies, presenting promising application other neurodegenerative diseases.

Language: Английский

---

Unified 2D and 3D Pre-Training of Molecular Representations

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Journal Year: 2022, Volume and Issue: unknown, P. 2626 - 2636

Published: Aug. 12, 2022

Molecular representation learning has attracted much attention recently. A molecule can be viewed as a 2D graph with nodes/atoms connected by edges/bonds, and also represented 3D conformation 3-dimensional coordinates of all atoms. We note that most previous work handles information separately, while jointly leveraging these two sources may foster more informative representation. In this work, we explore appealing idea propose new method based on unified pre-training. Atom interatomic distances are encoded then fused atomic representations through neural networks. The model is pre-trained three tasks: reconstruction masked atoms coordinates, generation conditioned graph, conformation. evaluate our 11 downstream molecular property prediction 7 only 4 both information. Our achieves state-of-the-art results 10 tasks, the average improvement 2D-only tasks 8.3%. significant tasks.

Language: Английский

---

Machine Learning and Artificial Intelligence: A Paradigm Shift in Big Data-Driven Drug Design and Discovery

Current Topics in Medicinal Chemistry, Journal Year: 2022, Volume and Issue: 22(20), P. 1692 - 1727

Published: July 4, 2022

Background: The lengthy and expensive process of developing a novel medicine often takes many years entails significant financial burden due to its poor success rate. Furthermore, the processing analysis quickly expanding massive data necessitate use cutting-edge methodologies. As result, Artificial Intelligence-driven methods that have been shown improve efficiency accuracy drug discovery grown in favor. Objective: goal this thorough is provide an overview development timeline, various approaches design, Intelligence aspects discovery. Methods: Traditional their disadvantages explored paper, followed by introduction AI-based technology. Also, advanced used Machine Learning Deep are examined detail. A few examples big research has transformed field medication also presented. Also covered databases, toolkits, software available for constructing Intelligence/Machine models, as well some standard model evaluation parameters. Finally, recent advances uses thoroughly examined, along with limitations future potential. Conclusion: Intelligence-based technologies enhance decision-making utilizing abundantly high-quality data, thereby reducing time cost involved process. We anticipate review would be useful researchers interested development.

Language: Английский

---

Trustworthy Graph Neural Networks: Aspects, Methods and Trends

arXiv (Cornell University), Journal Year: 2022, Volume and Issue: unknown

Published: Jan. 1, 2022

Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such drug discovery in life sciences n-body simulation astrophysics. However, task performance is not the only requirement GNNs. Performance-oriented GNNs exhibited potential adverse effects vulnerability adversarial attacks, unexplainable discrimination against disadvantaged groups, or excessive resource consumption edge computing environments. To avoid these unintentional harms, it necessary build characterised by trustworthiness. this end, we propose comprehensive roadmap trustworthy view various involved. In survey, introduce basic concepts comprehensively summarise existing efforts six aspects, including robustness, explainability, privacy, fairness, accountability, environmental well-being. Additionally, highlight intricate cross-aspect relations between above aspects Finally, present thorough overview trending directions facilitating research industrialisation

Language: Английский

---