In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back DOI
Abdulrahman Aldossary, Jorge A. Campos-Gonzalez-Angulo, Sergio Pablo‐García

et al.

Advanced Materials, Journal Year: 2024, Volume and Issue: 36(30)

Published: May 25, 2024

Abstract Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving Schrödinger equations increasing cost with size molecular system. In response, there has been a surge interest in leveraging artificial intelligence (AI) machine learning (ML) techniques silico experiments. Integrating AI ML into increases scalability speed exploration space. remain, particularly regarding reproducibility transferability models. This review highlights evolution from, complementing, or replacing energy property predictions. Starting from models trained entirely on numerical data, journey set forth toward ideal model incorporating physical laws quantum mechanics. paper also reviews existing their intertwining, outlines roadmap future research, identifies areas improvement innovation. Ultimately, goal develop architectures capable accurate transferable solutions equation, thereby revolutionizing experiments within materials science.

Language: Английский

Augmenting large language models with chemistry tools DOI Creative Commons

Andres M. Bran,

Sam Cox,

Oliver Schilter

et al.

Nature Machine Intelligence, Journal Year: 2024, Volume and Issue: 6(5), P. 525 - 535

Published: May 8, 2024

Abstract Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These also lack access to external knowledge sources, limiting their usefulness scientific applications. We introduce ChemCrow, an LLM chemistry agent designed accomplish organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools using GPT-4 as the LLM, ChemCrow augments chemistry, new capabilities emerge. Our autonomously planned executed syntheses of insect repellent three organocatalysts guided a novel chromophore. evaluation, including both expert assessments, demonstrates ChemCrow’s effectiveness automating diverse set chemical tasks. work not only aids chemists lowers barriers for non-experts fosters advancement by bridging gap between experimental computational chemistry.

Language: Английский

Citations

141
Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering DOI Creative Commons
Jason Yang, Francesca-Zhoufan Li, Frances H. Arnold

et al.

ACS Central Science, Journal Year: 2024, Volume and Issue: 10(2), P. 226 - 241

Published: Feb. 5, 2024

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even unlock new activities not found in nature. Because search space possible proteins is vast, enzyme engineering usually involves discovering an starting point that has some desired activity followed by directed evolution improve its "fitness" for a application. Recently, machine learning (ML) emerged powerful tool complement this empirical process. ML models contribute (1) discovery functional annotation known protein or generating novel with functions (2) navigating fitness landscapes optimization mappings between associated values. In Outlook, we explain how complements discuss future potential improved outcomes.

Language: Английский

Citations

70
A guide to artificial intelligence for cancer researchers DOI
Raquel Pérez-López, Narmin Ghaffari Laleh, Faisal Mahmood

et al.

Nature reviews. Cancer, Journal Year: 2024, Volume and Issue: 24(6), P. 427 - 441

Published: May 16, 2024

Language: Английский

Citations

67
Machine learning in preclinical drug discovery DOI

Denise B. Catacutan,

Jeremie Alexander,

Autumn Arnold

et al.

Nature Chemical Biology, Journal Year: 2024, Volume and Issue: 20(8), P. 960 - 973

Published: July 19, 2024

Language: Английский

Citations

41
Self-Driving Laboratories for Chemistry and Materials Science DOI Creative Commons
Gary Tom, Stefan P. Schmid, Sterling G. Baird

et al.

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

Citations

39
Larger and more instructable language models become less reliable DOI Creative Commons
Lexin Zhou, Wout Schellaert, Fernando Martínez‐Plumed

et al.

Nature, Journal Year: 2024, Volume and Issue: 634(8032), P. 61 - 68

Published: Sept. 25, 2024

Abstract The prevailing methods to make large language models more powerful and amenable have been based on continuous scaling up (that is, increasing their size, data volume computational resources 1 ) bespoke shaping (including post-filtering 2,3 , fine tuning or use of human feedback 4,5 ). However, larger instructable may become less reliable. By studying the relationship between difficulty concordance, task avoidance prompting stability several model families, here we show that easy instances for participants are also models, but scaled-up, shaped-up do not secure areas low in which either does err supervision can spot errors. We find early often avoid user questions tend give an apparently sensible yet wrong answer much often, including errors difficult supervisors frequently overlook. Moreover, observe different natural phrasings same question is improved by scaling-up shaping-up interventions, pockets variability persist across levels. These findings highlight need a fundamental shift design development general-purpose artificial intelligence, particularly high-stakes predictable distribution paramount.

Language: Английский

Citations

29
Materials science in the era of large language models: a perspective DOI Creative Commons
Ge Lei, R. Docherty, Samuel J. Cooper

et al.

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(7), P. 1257 - 1272

Published: Jan. 1, 2024

This perspective paper explores the potential of Large Language Models (LLMs) in materials science, highlighting their abilities to handle ambiguous tasks, automate processes, and extract knowledge at scale across various disciplines.

Language: Английский

Citations

24
Strongly-confined colloidal lead-halide perovskite quantum dots: from synthesis to applications DOI Creative Commons
Junzhi Ye,

Deepika Gaur,

Chenjia Mi

et al.

Chemical Society Reviews, Journal Year: 2024, Volume and Issue: 53(16), P. 8095 - 8122

Published: Jan. 1, 2024

Reducing the dimensionality of lead-halide perovskite nanocrystals from 3D to 0D leads fascinating properties. This tutorial review discusses synthesis, optical properties and applications such strongly-confined quantum dots.

Language: Английский

Citations

24
Leveraging generative AI for urban digital twins: a scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement DOI Creative Commons
Haowen Xu, Olufemi A. Omitaomu, Soheil Sabri

et al.

Urban Informatics, Journal Year: 2024, Volume and Issue: 3(1)

Published: Oct. 14, 2024

Abstract The digital transformation of modern cities by integrating advanced information, communication, and computing technologies has marked the epoch data-driven smart city applications for efficient sustainable urban management. Despite their effectiveness, these often rely on massive amounts high-dimensional multi-domain data monitoring characterizing different sub-systems, presenting challenges in application areas that are limited quality availability, as well costly efforts generating scenarios design alternatives. As an emerging research area deep learning, Generative Artificial Intelligence (GenAI) models have demonstrated unique values content generation. This paper aims to explore innovative integration GenAI techniques twins address planning management built environments with focuses various such transportation, energy, water, building infrastructure. survey starts introduction cutting-edge generative AI models, Adversarial Networks (GAN), Variational Autoencoders (VAEs), Pre-trained Transformer (GPT), followed a scoping review existing science leverage intelligent autonomous capability facilitate research, operations, critical subsystems, holistic environment. Based review, we discuss potential opportunities technical strategies integrate into next-generation more intelligent, scalable, automated development

Language: Английский

Citations

23
Empowering biomedical discovery with AI agents DOI Creative Commons

Shanghua Gao,

Ada Fang,

Yepeng Huang

et al.

Cell, Journal Year: 2024, Volume and Issue: 187(22), P. 6125 - 6151

Published: Oct. 1, 2024

We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents integrate AI models tools with experimental platforms. Rather than taking humans out the discovery process, combine human creativity expertise AI's ability to analyze large datasets, navigate hypothesis spaces, execute repetitive tasks. are poised be proficient in various tasks, planning workflows performing self-assessment identify mitigate gaps their knowledge. These use language generative feature structured memory for continual machine incorporate scientific knowledge, biological principles, theories. can impact areas ranging from virtual cell simulation, programmable control phenotypes, design cellular circuits developing new therapies.

Language: Английский

Citations

21