Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments

Science Advances, Journal Year: 2024, Volume and Issue: 10(14)

Published: April 5, 2024

The GEMS method enables molecular dynamics simulations of large heterogeneous systems at ab initio quality.

Language: Английский

---

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials

Advanced Energy Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Abstract This review highlights recent advances in machine learning (ML)‐assisted design of energy materials. Initially, ML algorithms were successfully applied to screen materials databases by establishing complex relationships between atomic structures and their resulting properties, thus accelerating the identification candidates with desirable properties. Recently, development highly accurate interatomic potentials generative models has not only improved robust prediction physical but also significantly accelerated discovery In past couple years, methods have enabled high‐precision first‐principles predictions electronic optical properties for large systems, providing unprecedented opportunities science. Furthermore, ML‐assisted microstructure reconstruction physics‐informed solutions partial differential equations facilitated understanding microstructure–property relationships. Most recently, seamless integration various platforms led emergence autonomous laboratories that combine quantum mechanical calculations, language models, experimental validations, fundamentally transforming traditional approach novel synthesis. While highlighting aforementioned advances, existing challenges are discussed. Ultimately, is expected fully integrate atomic‐scale simulations, reverse engineering, process optimization, device fabrication, empowering system design. will drive transformative innovations conversion, storage, harvesting technologies.

Language: Английский

---

Pharmaceutical Digital Design: From Chemical Structure through Crystal Polymorph to Conceptual Crystallization Process

Crystal Growth & Design, Journal Year: 2024, Volume and Issue: 24(13), P. 5417 - 5438

Published: June 24, 2024

A workflow for the digital design of crystallization processes starting from chemical structure active pharmaceutical ingredient (API) is a multistep, multidisciplinary process. simple version would be to first predict API crystal and, it, corresponding properties solubility, morphology, and growth rates, assuming that nucleation controlled by seeding, then use these parameters This usually an oversimplification as most APIs are polymorphic, stable alone may not have required development into drug product. perspective, experience Lilly Digital Design project, considers fundamental theoretical basis prediction (CSP), free energy, rate prediction, current state simulation. illustrated applying modeling techniques real examples, olanzapine succinic acid. We demonstrate promise using ab initio computer solid form selection process in development. also identify open problems application computational achieving accuracy immediate implementation currently limit applicability approach.

Language: Английский

---

A robust crystal structure prediction method to support small molecule drug development with large scale validation and blind study

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

Published: March 5, 2025

Crystal polymorphism is an important and fascinating aspect of solid state chemistry with far reaching implications in the pharmaceuticals, agrisciences, nutraceuticals, battery aviation industries. Late appearing more stable polymorphs have caused numerous issues pharmaceutical industry. Experimental polymorph screening can be very expensive time consuming, sometimes may miss low energy due to inability exhaust all crystallization conditions. In this paper, we report a crystal structure prediction (CSP) method art accuracy efficiency, validated on large diverse dataset including 66 molecules 137 experimentally known polymorphic forms. The combines novel systematic packing search algorithm use machine learning force fields hierarchical ranking. Our not only reproduces polymorphs, but also suggests new yet discovered by experiment that might pose potential risks development currently forms these compounds. addition, results blinded study, for Target XXXI from seventh CSP blind test, demonstrate how used accelerate clinical formulation design derisk downstream processing.

Language: Английский

---

A fast and efficient machine learning assisted prediction of urea and its derivatives to screen crystal propensity with experimental validation

Materials Today Communications, Journal Year: 2025, Volume and Issue: unknown, P. 111692 - 111692

Published: Jan. 1, 2025

Language: Английский

---

Application of an Interdisciplinary Approach to Form Selection in Drug Development

Organic Process Research & Development, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 25, 2025

Language: Английский

---

Accelerating Structure Prediction of Molecular Crystals using Actively Trained Moment Tensor Potential

Physical Chemistry Chemical Physics, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

We present a methodology that exploits moment tensor potentials (MTP) and active learning (based on the maxvol algorithm) to accelerate structure prediction of molecular crystals.

Language: Английский

---

Accurate Lattice Free Energies of Packing Polymorphs from Probabilistic Generative Models

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

Published: Feb. 21, 2025

Finite-temperature lattice free energy differences between polymorphs of molecular crystals are fundamental to understanding and predicting the relative stability relationships underpinning polymorphism, yet computationally expensive obtain. Here, we implement critically assess machine-learning-enabled targeted calculations derived from flow-based generative models compute difference two ice crystal (Ice XI Ic), modeled with a fully flexible empirical classical force field. We demonstrate that even when remapping an analytical reference distribution, such methods enable cost-effective accurate calculation disconnected metastable ensembles trained on locally ergodic data sampled exclusively interest. Unlike perturbation methods, as Einstein method, approach analyzed in this work requires no additional sampling intermediate perturbed Hamiltonians, offering significant computational savings. To systematically accuracy monitored convergence estimates during training by implementing overfitting-aware weighted averaging strategy. By comparing our results ground-truth computed efficiency different model architectures, employing representations supercell degrees freedom (Cartesian vs quaternion-based). conduct assessment supercells sizes temperatures assessing extrapolating energies thermodynamic limit. While at low small system sizes, perform similar accuracy. note for larger systems high temperatures, choice representation is key obtaining generalizable quality comparable obtained method. believe be stepping stone toward efficient larger, more complex crystals.

Language: Английский

---

What Has Carbamazepine Taught Crystal Engineers?

Crystal Growth & Design, Journal Year: 2024, Volume and Issue: 24(17), P. 7342 - 7360

Published: June 21, 2024

The antiepilepsy drug carbamazepine is one of the most studied pharmaceuticals in world. rich story its solid forms, cocrystals, and formulation a microcosm topical world pharmaceutical materials. Understanding has required time, money, dedication from numerous researchers companies worldwide. This wealth knowledge provides opportunity to reflect on progress within crystal engineering field general. Perspective covers extensive form landscape applies these examples discuss answer fundamental questions discipline. encompasses screening methods, computational discovery, power influence understanding controlling crystals amorphous state, environmental legacy modern pharmaceuticals. broad but in-depth analysis vehicle into engineering, not only own right across spectrum organic materials science formulation. Discoveries demonstrate potential richness chemistry every drug.

Language: Английский

---

Assessing the Accuracy and Efficiency of Free Energy Differences Obtained from Reweighted Flow-Based Probabilistic Generative Models

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: 20(14), P. 5913 - 5922

Published: July 10, 2024

Computing free energy differences between metastable states characterized by nonoverlapping Boltzmann distributions is often a computationally intensive endeavor, usually requiring chains of intermediate to connect them. Targeted perturbation (TFEP) can significantly lower the computational cost FEP calculations choosing set invertible maps used directly interest, achieving necessary statistically significant overlaps without sampling any states. Probabilistic generative models (PGMs) based on normalizing flow architectures make it much easier via machine learning train needed for TFEP. However, accuracy and applicability approaches empirically learned depend crucially choice reweighting method adopted estimate differences. In this work, we assess accuracy, rate convergence, data efficiency different estimators, including exponential averaging, Bennett acceptance ratio (BAR), multistate (MBAR), in PGMs trained maximum likelihood limited amounts molecular dynamics sampled only from end-states interest. We carry out comparisons simple but representative case studies, conformational ensembles alanine dipeptide ibuprofen. Our results indicate that BAR MBAR are both efficient robust, even presence model overfitting generation maps. This analysis serve as stepping stone deployment quantitatively accurate ML-based calculation methods complex systems.

Language: Английский

---