Self-Driving Laboratories for Chemistry and Materials Science

Chemical Reviews, Journal Year: 2024, Volume and Issue: 124(16), P. 9633 - 9732

Published: Aug. 13, 2024

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through automation experimental workflows, along with autonomous planning, SDLs hold potential to greatly accelerate research in chemistry and materials discovery. This review provides in-depth analysis state-of-the-art SDL technology, its applications across various disciplines, implications for industry. additionally overview enabling technologies SDLs, including their hardware, software, integration laboratory infrastructure. Most importantly, this explores diverse range domains where have made significant contributions, from drug discovery science genomics chemistry. We provide a comprehensive existing real-world examples different levels automation, challenges limitations associated each domain.

Language: Английский

---

Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data

Journal of Cheminformatics, Journal Year: 2024, Volume and Issue: 16(1)

Published: July 30, 2024

Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, scarcity labeled data poses significant challenge training advanced machine models. This study showcases potential utilizing databases drug-like small molecules and chemical reactions pretrain BERT model, enhancing performance in materials. By fine-tuning models with from five tasks, version pretrained USPTO–SMILES dataset achieved R2 scores exceeding 0.94 three tasks 0.81 two others. surpasses that on molecule or outperforms trained directly data. The success model can be attributed diverse array building blocks USPTO database, offering broader exploration space. further suggests accessing reaction database wider range than could enhance performance. Overall, this research validates feasibility applying transfer across different domains efficient Scientific contribution verifies large language fields help perform screening. Through comparison variety material molecules, high precision realized.

Language: Английский

---

Transfer contrastive learning for Raman spectra data of urine: Detection of glucose, protein, and prediction of kidney disorders

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2025, Volume and Issue: unknown, P. 105384 - 105384

Published: March 1, 2025

Language: Английский

---

Transfer learning accelerated discovery of conjugated oligomers for advanced organic photovoltaics

Molecular Systems Design & Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Transfer learning followed by density functional theory accelerates material discovery of conjugated oligomers for high-efficiency organic photovoltaic materials.

Language: Английский

---

Enhancing chemical reaction search through contrastive representation learning and human-in-the-loop

Journal of Cheminformatics, Journal Year: 2025, Volume and Issue: 17(1)

Published: April 10, 2025

Language: Английский

---

Chiral Intelligence: The Artificial Intelligence‐Driven Future of Chiroptical Properties

ChemPhotoChem, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Chirality plays a fundamental role in molecular sciences, with chiroptical properties offering valuable insights into the interaction between chiral molecules and polarized light. Designing materials enhanced requires deep understanding of underlying physical principles, often revealed only through large datasets. In this context, artificial intelligence (AI) emerges as powerful tool for accelerating discovery optimization, efficiently exploring vast chemical spaces. This work explores synergy AI properties, highlighting recent advances data‐driven approaches circular dichroism circularly luminescence. has demonstrated its ability to predict these phenomena accurately while uncovering structure–property relationships that can remain hidden under traditional methods. Various strategies are examined integrating challenges future directions field discussed. conclusion, combining intuition offers great potential rational design next‐generation materials. integration not promises unlock novel compounds but also provides new opportunities deepen our phenomena.

Language: Английский

---

Graph Neural Network for 3‐Dimensional Structures Including Dihedral Angles for Molecular Property Prediction

Journal of Computational Chemistry, Journal Year: 2025, Volume and Issue: 46(13)

Published: May 14, 2025

ABSTRACT The prediction of molecular properties using graph neural network (GNN)‐ based approaches has attracted great attention in recent years. Topological graphs are commonly used for representing molecules machine learning (ML). However, the challenge is to utilize complete geometry information, such as, bonds, angles, and dihedral angles while processing a graph. In this work, we present predictive GNN accounting three‐dimensional structures including (GNN3Dihed) systematic manner. Additionally, demonstrate that usage autoencoders generate latent space embeddings usually sparse atomic bond vectors reduces number parameters message passing stage not reducing performance. We compare performance GNN3Dihed with state‐of‐the‐art baselines on several tasks (regression classification), example, solubility prediction, toxicity binding affinity, quantum mechanical property showed architecture often outperforms other models—demonstrating importance 3D structural information ML chemistry.

Language: Английский

---

Bridging odorants and olfactory perception through machine learning: A review

Trends in Food Science & Technology, Journal Year: 2024, Volume and Issue: 153, P. 104700 - 104700

Published: Sept. 5, 2024

Language: Английский

---

Computational Tools for the Prediction of Site- and Regioselectivity of Organic Reactions

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

Published: Jan. 1, 2025

This article reviews computational tools for the prediction of regio- and site-selectivity organic reactions. It spans from quantum chemical procedures to deep learning models showcases application presented tools.

Language: Английский

---

A focus on molecular representation learning for the prediction of chemical properties

Chemical Science, Journal Year: 2024, Volume and Issue: 15(14), P. 5052 - 5055

Published: Jan. 1, 2024

Molecular representation learning (MRL) holds significant potential for predicting diverse chemical properties. In this focus article, we will provide context applications of MRL in chemistry and the significance King-Smith's recently published work within evolving field.

Language: Английский

---