Scientific discovery in the age of artificial intelligence

Wang, Hanchen; Fu, Tianfan; Du, Yuanqi; Gao, Wenhao; Huang, Kexin; Liu, Ziming; Chandak, Payal; Liu, Shengchao; Katwyk, Peter Van; Deac, Andreea; Anandkumar, Anima; Bergen, Karianne J.; Gomes, Carla P.; Ho, Shirley; Kohli, Pushmeet; Lasenby, Joan; Leskovec, Jure; Liu, Tie-Yan; Manrai, Arjun K.; Marks, Daniel; Ramsundar, Bharath; Song, Le; Sun, Jimeng; Tang, Jian; Veličković, Petar; Welling, Max; Zhang, Linfeng; Coley, Connor W.; Bengio, Yoshua; Žitnik, Marinka

doi:10.1038/s41586-023-06221-2

Cited by 499 publications

(141 citation statements)

References 170 publications

Supporting

Mentioning

138

Contrasting

Unclassified

Order By: Relevance

“…These tasks encompass learning, understanding natural language, recognizing patterns, solving problems and making decisions. AI algorithms are designed to learn from the data they process, thereby improving their performance over time (Wang et al , 2023). This learning ability, coupled with the vast amount of data available today, makes AI an incredibly powerful tool for various fields, including education and library science.…”

Section: Artificial Intelligencementioning

confidence: 99%

Metaverse-infused academic libraries: a glimpse into the future

Amzat,

Adewojo

2023

LHTN

View full text Add to dashboard Cite

Purpose This study aims to explore the transformative potential of integrating artificial intelligence (AI) and the metaverse into academic libraries, envisioning a future where personalized, immersive and accessible user experiences redefine the traditional concept of libraries. The purpose is to analyse the synergy between AI and the metaverse in enhancing library services and user interactions. Design/methodology/approach The study uses a literature review approach to synthesize current knowledge on AI, the metaverse and their integration into academic libraries. It delves into the functionalities of AI in cataloguing, personalization and predictive analysis, coupled with the immersive experiences offered by the metaverse. The design envisions metaverse-infused academic libraries as digital spaces hosting AI-driven virtual assistants, personalized learning paths and collaborative environments. Findings The integration of AI and the metaverse in academic libraries presents opportunities for personalized learning experiences, efficient resource management and global collaboration. The findings suggest that the synergy enhances accessibility, inclusivity and efficiency in library services, albeit with challenges such as the digital divide, privacy concerns and technical complexities. Originality/value This study contributes to the discourse on the future of academic libraries by proposing a comprehensive vision of metaverse-infused libraries empowered by AI. It underscores the originality and value of the integration, emphasizing the potential for personalized, interactive and globally accessible learning and research environments.

show abstract

Section: Artificial Intelligencementioning

confidence: 99%

Metaverse-infused academic libraries: a glimpse into the future

Amzat,

Adewojo

2023

LHTN

View full text Add to dashboard Cite

show abstract

“…Recent advances in machine learning (ML), especially deep learning (DL), offer an exciting opportunity to reshape scientific research within the domains of chemical and materials science. 6–8 This is particularly evident in facilitating rapid analysis of intricate data, including but not limited to XRD, 9,10 IR/FTIR, 11,12 Raman, 13,14 and MS data. 15,16 For example, Oviedo and coworkers have demonstrated deployment of convolutional neural networks (CNNs) to effectively classify the dimensionalities and space groups of thin-film metal halides from XRD spectra.…”

Section: Introductionmentioning

confidence: 99%

An interpretable and transferrable vision transformer model for rapid materials spectra classification

Chen,

Xie,

et al. 2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…Rapid advances in artificial intelligence (AI) inevitably will reshape chemistry and what chemists do in the laboratory. − In particular, the recent development of large language models (LLMs) and machine learning (ML) algorithms will provide chemists with robust new means to address material discovery challenges. ,− However, the complexity of laboratory routines often results in AI participation in isolated parts of the research process (e.g., predictive modeling, literature mining, robotic operations, and data analysis), resulting in a fragmented workflow that requires extensive human intervention in terms of coding, which is less accessible to chemists with limited programming experience. Bridging this gap demands innovative strategies that harness the AI’s real-time learning and self-instruction capabilities toward more comprehensive research automation. − …”

Section: Introductionmentioning

confidence: 99%

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs

Zheng,

Zhang,

Nguyen

et al. 2023

ACS Cent. Sci.

View full text Add to dashboard Cite

We leveraged the power of ChatGPT and Bayesian optimization in the development of a multi-AI-driven system, backed by seven large language model-based assistants and equipped with machine learning algorithms, that seamlessly orchestrates a multitude of research aspects in a chemistry laboratory (termed the ChatGPT Research Group). Our approach accelerated the discovery of optimal microwave synthesis conditions, enhancing the crystallinity of MOF-321, MOF-322, and COF-323 and achieving the desired porosity and water capacity. In this system, human researchers gained assistance from these diverse AI collaborators, each with a unique role within the laboratory environment, spanning strategy planning, literature search, coding, robotic operation, labware design, safety inspection, and data analysis. Such a comprehensive approach enables a single researcher working in concert with AI to achieve productivity levels analogous to those of an entire traditional scientific team. Furthermore, by reducing human biases in screening experimental conditions and deftly balancing the exploration and exploitation of synthesis parameters, our Bayesian search approach precisely zeroed in on optimal synthesis conditions from a pool of 6 million within a significantly shortened time scale. This work serves as a compelling proof of concept for an AI-driven revolution in the chemistry laboratory, painting a future where AI becomes an efficient collaborator, liberating us from routine tasks to focus on pushing the boundaries of innovation.

show abstract

Scientific discovery in the age of artificial intelligence

Cited by 499 publications

References 170 publications

Metaverse-infused academic libraries: a glimpse into the future

Metaverse-infused academic libraries: a glimpse into the future

An interpretable and transferrable vision transformer model for rapid materials spectra classification

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs

Contact Info

Product

Resources

About