When Metal Nanoclusters Meet Smart Synthesis DOI
Zhucheng Yang, Anye Shi, Ruixuan Zhang

et al.

ACS Nano, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 24, 2024

Atomically precise metal nanoclusters (MNCs) represent a fascinating class of ultrasmall nanoparticles with molecule-like properties, bridging conventional metal-ligand complexes and nanocrystals. Despite their potential for various applications, synthesis challenges such as understanding varied synthetic parameters property-driven persist, hindering full exploitation wider application. Incorporating smart methodologies, including closed-loop framework automation, data interpretation, feedback from AI, offers promising solutions to address these challenges. In this perspective, we summarize the that has been demonstrated in nanomaterials explore research frontiers MNCs. Moreover, perspectives on inherent opportunities MNCs are discussed, aiming provide insights directions future advancements emerging field AI Science, while integration deep learning algorithms stands substantially enrich by offering enhanced predictive capabilities, optimization strategies, control mechanisms, thereby extending MNC synthesis.

Language: Английский

Enzyme engineering for biocatalysis DOI Creative Commons
Caroline E. Paul, Ulf Hanefeld, Frank Hollmann

et al.

Molecular Catalysis, Journal Year: 2024, Volume and Issue: 555, P. 113874 - 113874

Published: Jan. 31, 2024

Contemporary Biocatalysis heavily relies on enzyme engineering as natural enzymes frequently lack the requisite attributes for effective organic synthesis. The inherent limitations in stability, catalytic activity, and selectivity of wild-type often hinder their suitability chemical Over past 25 years, there has been an unprecedented advancement protein tools, empowering enzymologists to customise precisely meet demands In this discussion, we delineate some most crucial techniques significance facilitating

Language: Английский

Citations

13
READRetro: natural product biosynthesis predicting with retrieval‐augmented dual‐view retrosynthesis DOI
Taein Kim, Seul Lee, Yejin Kwak

et al.

New Phytologist, Journal Year: 2024, Volume and Issue: 243(6), P. 2512 - 2527

Published: July 30, 2024

Summary Plants, as a sessile organism, produce various secondary metabolites to interact with the environment. These chemicals have fascinated plant science community because of their ecological significance and notable biological activity. However, predicting complete biosynthetic pathways from target molecules metabolic building blocks remains challenge. Here, we propose retrieval‐augmented dual‐view retrosynthesis (READRetro) practical bio‐retrosynthesis tool predict natural products. Conventional models been limited in ability for READRetro was optimized prediction complex by incorporating cutting‐edge deep learning architectures, an ensemble approach, two retrievers. Evaluation single‐ multi‐step showed that each component significantly improved its pathways. also able known such monoterpene indole alkaloids unknown pathway menisdaurilide, demonstrating applicability real‐world For researchers interested biosynthesis production metabolites, user‐friendly website ( https://readretro.net ) open‐source code made available.

Language: Английский

Citations

11
Cell factory design with advanced metabolic modelling empowered by artificial intelligence DOI Creative Commons
Hongzhong Lu,

Luchi Xiao,

Wenbin Liao

et al.

Metabolic Engineering, Journal Year: 2024, Volume and Issue: 85, P. 61 - 72

Published: July 20, 2024

Advances in synthetic biology and artificial intelligence (AI) have provided new opportunities for modern biotechnology. High-performance cell factories, the backbone of industrial biotechnology, are ultimately responsible determining whether a bio-based product succeeds or fails fierce competition with petroleum-based products. To date, one greatest challenges is creation high-performance factories consistent efficient manner. As so-called white-box models, numerous metabolic network models been developed used computational strain design. Moreover, great progress has made AI-powered engineering recent years. Both approaches advantages disadvantages. Therefore, deep integration AI crucial construction superior higher titres, yields production rates. The detailed applications latest advanced design summarized this review. Additionally, discussed. It anticipated that mechanistic powered by will pave way powerful chassis strains coming

Language: Английский

Citations

10
Enhanced Deep-Learning Model for Carbon Footprints of Chemicals DOI Creative Commons
Dachuan Zhang, Zhanyun Wang, Christopher Oberschelp

et al.

ACS Sustainable Chemistry & Engineering, Journal Year: 2024, Volume and Issue: 12(7), P. 2700 - 2708

Published: Feb. 5, 2024

Millions of chemicals have been designed; however, their product carbon footprints (PCFs) are largely unknown, leaving questions about sustainability. This general lack PCF data is because the needed for comprehensive environmental analyses typically not available in early molecular design stages. Several predictive tools developed to estimate chemicals, which applicable only a narrow range common and limited ability. Here, we propose FineChem 2, based on novel transformer framework first-hand industry data, accurately predicting chemicals. Compared previous tools, 2 demonstrates significantly better power, its applicability domains improved by ∼75% diverse set global market, including high-production-volume identified regulators, daily chemical additives food plastics. In addition, through interpretability from attention mechanism, may successfully identify PCF-intensive substructures critical raw materials providing insights into more sustainable molecules processes. Therefore, highlight estimating contributing advancements transition industry.

Language: Английский

Citations

9
The Impact of AI Adoption on R&D Productivity: Evidence from Chinese Pharmaceutical Manufacturing Industry DOI
Yifan Wu,

Yiming Yuan,

Xueyin Song

et al.

Journal of Asian Economics, Journal Year: 2025, Volume and Issue: unknown, P. 101890 - 101890

Published: Feb. 1, 2025

Language: Английский

Citations

1
A novel interpretability framework for enzyme turnover number prediction boosted by pre-trained enzyme embeddings and adaptive gate network DOI

Bing-Xue Du,

Haoyang Yu, Bei Zhu

et al.

Methods, Journal Year: 2025, Volume and Issue: 237, P. 45 - 52

Published: Feb. 26, 2025

Language: Английский

Citations

1
Advances in AI-based strategies and tools to facilitate natural product and drug development DOI
Buddha Bahadur Basnet, Zhen‐Yi Zhou, Bin Wei

et al.

Critical Reviews in Biotechnology, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 32

Published: March 30, 2025

Natural products and their derivatives have been important for treating diseases in humans, animals, plants. However, discovering new structures from natural sources is still challenging. In recent years, artificial intelligence (AI) has greatly aided the discovery development of drugs. AI facilitates to: connect genetic data to chemical or vice-versa, repurpose known products, predict metabolic pathways, design optimize metabolites biosynthesis. More recently, emergence improvement neural networks such as deep learning ensemble automated web based bioinformatics platforms sped up process. Meanwhile, also improves identification structure elucidation unknown compounds raw like mass spectrometry nuclear magnetic resonance. This article reviews these AI-driven methods tools, highlighting practical applications guide efficient product drug development.

Language: Английский

Citations

1
Physics-based modeling in the new era of enzyme engineering DOI
Christopher Jurich, Qianzhen Shao, Xinchun Ran

et al.

Nature Computational Science, Journal Year: 2025, Volume and Issue: 5(4), P. 279 - 291

Published: April 24, 2025

Language: Английский

Citations

1
Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products DOI
Yujie Yuan, Chengyou Shi, Huimin Zhao

et al.

ACS Synthetic Biology, Journal Year: 2023, Volume and Issue: 12(9), P. 2650 - 2662

Published: Aug. 22, 2023

Natural products (NPs) produced by microorganisms and plants are a major source of drugs, herbicides, fungicides. Thanks to recent advances in DNA sequencing, bioinformatics, genome mining tools, vast amount data on NP biosynthesis has been generated over the years, which increasingly exploited develop machine learning (ML) tools for discovery. In this review, we discuss latest developing applying ML exploring potential NPs that can be encoded genomic language predicting types bioactivities NPs. We also examine technical challenges associated with development application research.

Language: Английский

Citations

23
Harnessing generative AI to decode enzyme catalysis and evolution for enhanced engineering DOI Creative Commons
Wen Jun Xie, Arieh Warshel

National Science Review, Journal Year: 2023, Volume and Issue: 10(12)

Published: Nov. 6, 2023

Enzymes, as paramount protein catalysts, occupy a central role in fostering remarkable progress across numerous fields. However, the intricacy of sequence-function relationships continues to obscure our grasp enzyme behaviors and curtails capabilities rational engineering. Generative artificial intelligence (AI), known for its proficiency handling intricate data distributions, holds potential offer novel perspectives research. models could discern elusive patterns within vast sequence space uncover new functional sequences. This review highlights recent advancements employing generative AI analysis. We delve into impact predicting mutation effects on fitness, catalytic activity stability, rationalizing laboratory evolution

Language: Английский

Citations

17