The Physics-AI Dialogue in Drug Design

RSC Medicinal Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

A long path has led from the determination of first protein structure in 1960 to recent breakthroughs science. Protein prediction and design methodologies based on machine learning (ML) have been recognized with 2024 Nobel prize Chemistry, but they would not possible without previous work input many domain scientists. Challenges remain application ML tools for structural ensembles their usage within software pipelines by crystallography or cryogenic electron microscopy. In drug discovery workflow, techniques are being used diverse areas such as scoring docked poses, generation molecular descriptors. As become more widespread, novel applications emerge which can profit large amounts data available. Nevertheless, it is essential balance potential advantages against environmental costs deployment decide if when best apply it. For hit lead optimization efficiently interpolate between compounds chemical series free energy calculations dynamics simulations seem be superior designing derivatives. Importantly, complementarity and/or synergism physics-based methods (e.g., force field-based simulation models) data-hungry growing strongly. Current evolved decades research. It now necessary biologists, physicists, computer scientists fully understand limitations ensure that exploited design.

Language: Английский

---

Biological physics to uncover cell signaling

Biophysical Reviews, Journal Year: 2025, Volume and Issue: unknown

Published: April 10, 2025

Language: Английский

---

Machine learning stochastic dynamics

Zhongguo kexue. Wulixue Lixue Tianwenxue, Journal Year: 2025, Volume and Issue: 55(10), P. 100501 - 100501

Published: March 11, 2025

Language: Английский

---

Flow field reconstruction and prediction of the two-dimensional cylinder flow using data-driven physics-informed neural network combined with long short-term memory

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 149, P. 110547 - 110547

Published: March 18, 2025

Language: Английский

---

Fractal-constrained deep learning for super-resolution of turbulence with zero or few label data

Computer Physics Communications, Journal Year: 2025, Volume and Issue: 312, P. 109548 - 109548

Published: March 24, 2025

Language: Английский

---

State Estimation of Lithium-Ion Batteries via Physics-Machine Learning Combined Methods: A Methodological Review and Future Perspectives

eTransportation, Journal Year: 2025, Volume and Issue: unknown, P. 100420 - 100420

Published: April 1, 2025

Language: Английский

---

Symmetry Breaking in Neural Network Optimization: Insights from Input Dimension Expansion

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 23, 2025

Understanding how neural networks learn and optimize remains a central point in machine learning, with implications for designing better models. While techniques like dropout batch normalization are widely used, the underlying principles driving their success—such as symmetry breaking, concept physics—are underexplored. We propose breaking hypothesis, showing that symmetries during training (e.g., via input expansion) substantially improves performance across tasks. develop metric to quantify networks, revealing its role common optimization methods connection properties equivariance. This offers practical tool evaluate architectures without exhaustive or full datasets, enabling more efficient design choices. Our work positions unifying principle behind techniques, bridging theoretical gaps providing actionable insights improving model efficiency.

Language: Английский

---

Physics-Based Machine Learning Trains Hamiltonians and Decodes the Sequence–Conformation Relation in the Disordered Proteome

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: 20(22), P. 10266 - 10274

Published: Nov. 6, 2024

Intrinsically disordered proteins and regions (IDPs) are involved in vital biological processes. To understand the IDP function, often controlled by conformation, we need to find link between sequence conformation. We decode this integrating theory, simulation, machine learning (ML) where sequence-dependent electrostatics is modeled analytically while nonelectrostatic interaction extracted from simulations for many sequences subsequently trained using ML. The resulting Hamiltonian, combining physics-based machine-learned nonelectrostatics, accurately predicts sequence-specific global local measures of conformations beyond original observable used simulation. This contrast traditional ML approaches that train predict a specific observable, not Hamiltonian. Our formalism reproduces experimental measurements, multiple conformational features directly with high throughput will give insights into design evolution, illustrates broad utility unknown parts rather than combination known physics.

Language: Английский

---

Should Artificial Intelligence Play a Durable Role in Biomedical Research and Practice?

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(24), P. 13371 - 13371

Published: Dec. 13, 2024

During the last decade, artificial intelligence (AI) was applied to nearly all domains of human activity, including scientific research. It is thus warranted ask whether AI thinking should be durably involved in biomedical This problem addressed by examining three complementary questions (i) What are major barriers currently met investigators? suggested that during 2 decades there a shift towards growing need elucidate complex systems, and this not sufficiently fulfilled previously successful methods such as theoretical modeling or computer simulation (ii) potential meet aforementioned need? it recent well-suited perform classification prediction tasks on multivariate possibly help data interpretation, provided their efficiency properly validated. (iii) Recent representative results obtained with machine learning suggest may comparable displayed operators. concluded play an important role practice. Also, already other physics, combining conventional might generate further progress new applications, involving heuristic interpretation.

Language: Английский

---