Machine Learning Guided AQFEP: A Fast and Efficient Absolute Free Energy Perturbation Solution for Virtual Screening

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 15, 2024

Structure-based methods in drug discovery have become an integral part of the modern process. The power virtual screening lies its ability to rapidly and cost-effectively explore enormous chemical spaces select promising ligands for further experimental investigation. Relative free energy perturbation (RFEP) similar are gold standard binding affinity prediction hit-to-lead lead optimization phases, but high computational cost requirement a structural analog with known activity. Without reference molecule requirement, absolute FEP (AFEP) has, theory, better accuracy hit ID, practice, slow throughput is not compatible VS, where fast docking unreliable scoring functions still standard. Here, we present integrated workflow virtually screen large diverse libraries efficiently, combining active learning physics-based function based on method. We validated performance approach ranking structurally related ligands, rate enrichment, space exploration; disclosing largest reported collection simulations date.

Language: Английский

---

Strategies for in Silico Drug Discovery to Modulate Macromolecular Interactions Altered by Mutations

Frontiers in Bioscience-Landmark, Journal Year: 2025, Volume and Issue: 30(4)

Published: April 16, 2025

Most human diseases have genetic components, frequently single nucleotide variants (SNVs), which alter the wild type characteristics of macromolecules and their interactions. A straightforward approach for correcting such SNVs-related alterations is to seek small molecules, potential drugs, that can eliminate disease-causing effects. Certain disorders are caused by altered protein-protein interactions, example, Snyder-Robinson syndrome, therapy focuses on development molecules restore homodimerization spermine synthase. Other originate from protein-nucleic acid as in case cancer; these cases, elimination effects requires effect mutation p53-DNA affinity. Overall, especially complex diseases, pathogenic mutations macromolecular This be direct, i.e., alteration affinity specificity, or indirect via concentration binding partners. Here, we outline progress made methods strategies computationally identify capable altering interactions a desired manner, reducing increasing affinity, eliminating effect. When applicable, provide examples outlined general strategy. Successful cases presented at end work.

Language: Английский

---

How does machine learning augment alchemical binding free energy calculations?

Future Medicinal Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 3

Published: Feb. 8, 2025

Language: Английский

---

Uncertainty quantification with graph neural networks for efficient molecular design

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 5, 2025

Optimizing molecular design across expansive chemical spaces presents unique challenges, especially in maintaining predictive accuracy under domain shifts. This study integrates uncertainty quantification (UQ), directed message passing neural networks (D-MPNNs), and genetic algorithms (GAs) to address these challenges. We systematically evaluate whether UQ-enhanced D-MPNNs can effectively optimize broad, open-ended identify the most effective implementation strategies. Using benchmarks from Tartarus GuacaMol platforms, our results show that UQ integration via probabilistic improvement optimization (PIO) enhances success cases, supporting more reliable exploration of chemically diverse regions. In multi-objective tasks, PIO proves advantageous, balancing competing objectives outperforming uncertainty-agnostic approaches. work provides practical guidelines for integrating computational-aided (CAMD).

Language: Английский

---

Machine Learning and Statistical Mechanics: Shared Synergies for Next Generation of Chemical Theory and Computation

Journal of Chemical Theory and Computation, Journal Year: 2025, Volume and Issue: unknown

Published: May 9, 2025

Language: Английский

---