Towards quantifying catalytic activity of homogeneous Brønsted acid catalysts

Molecular Catalysis, Journal Year: 2025, Volume and Issue: 573, P. 114846 - 114846

Published: Jan. 20, 2025

Language: Английский

---

Recommending reaction conditions with label ranking

Chemical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Label ranking is introduced as a conceptually new means for prioritizing experiments. Their simplicity, ease of application, and the use aggregation facilitate their ability to make accurate predictions with small datasets.

Language: Английский

---

Advancements in Machine Learning Predicting Activation and Gibbs Free Energies in Chemical Reactions

International Journal of Quantum Chemistry, Journal Year: 2025, Volume and Issue: 125(7)

Published: March 19, 2025

ABSTRACT Machine learning has revolutionized computational chemistry by improving the accuracy of predicting thermodynamic and kinetic properties like activation energies Gibbs free energies, accelerating materials discovery optimizing reaction conditions in both academic industrial applications. This review investigates recent strides applying advanced machine techniques, including transfer learning, for accurately within complex chemical reactions. It thoroughly provides an extensive overview pivotal methods utilized this domain, sophisticated neural networks, Gaussian processes, symbolic regression. Furthermore, prominently highlights commonly adopted frameworks, such as Chemprop, SchNet, DeepMD, which have consistently demonstrated remarkable exceptional efficiency properties. Moreover, it carefully explores numerous influential studies that notably reported substantial successes, particularly focusing on predictive performance, diverse datasets, innovative model architectures profoundly contributed to enhancing methodologies. Ultimately, clearly underscores transformative potential significantly power intricate systems, bearing considerable implications cutting‐edge theoretical research practical

Language: Английский

---

PoseidonQ: A Free Machine Learning Platform for the Development, Analysis, and Validation of Efficient and Portable QSAR Models for Drug Discovery

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: April 9, 2025

The advent of powerful machine learning algorithms as well the availability high volume pharmacological data has given new fuel to QSAR, opening unprecedented options for deriving highly predictive models assisting rationale design bioactive compounds, screening and prioritizing large molecular libraries, repurposing drugs toward clinical uses. Here, we present PoseidonQ (an acronym Personal Optimization Software Efficient Implementation Derivation Online QSAR), a user-friendly software solution designed simplify derivation QSAR model drug discovery. incorporates 22 algorithms, 17 types fingerprints, 208 RDKit descriptors enables quick both regression classification along with calculated easily interpretable applicability domain. Importantly, platform is automatically linked latest version ChEMBL database, thus providing streamlined access amounts curated bioactivity data. user also option gathering high-quality experimental based on customizable filtering settings. Noteworthy, facilitates deployment trained web-based applications through seamless integration Streamlit Cloud GitHub, empowering users share, refine, integrate effortlessly. Interestingly, translation into makes them free accessible, portable, ready volumes without limits. By unifying preparation, generation, an intuitive workflow, advanced modeling discovery accessible wide audience researchers irrespective their skill levels. bridges gap between complex techniques practical applications, enhancing efficiency, collaboration, adoption approaches in modern programs. available Windows Linux (ubuntu 22.04 distro) operating systems can be downloaded at https://github.com/Muzatheking12/PoseidonQ.

Language: Английский

---

Machine learning workflows beyond linear models in low-data regimes

Chemical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

This work presents automated non-linear workflows for studying problems in low-data regimes alongside traditional linear models.

Language: Английский

---

Computational methods for asymmetric catalysis

Nature Catalysis, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 3, 2024

Language: Английский

---