On scientific understanding with artificial intelligence

Leveraging generative models with periodicity-aware, invertible and invariant representations for crystalline materials design

Designing periodicity-aware, invariant and invertible representations provides an opportunity for the inverse design of crystalline materials with desired properties by generative models. This objective requires optimizing representations and refining the architecture of generative models, yet its feasibility remains uncertain, given current progress in molecular inverse generation. In this Perspective, we highlight the progress of various methods for designing representations and generative schemes for crystalline materials, discuss the challenges in the field and propose a roadmap for future developments.

The ethics of using artificial intelligence in scientific research: new guidance needed for a new tool

Using artificial intelligence (AI) in research offers many important benefits for science and society but also creates novel and complex ethical issues. While these ethical issues do not necessitate changing established ethical norms of science, they require the scientific community to develop new guidance for the appropriate use of AI. In this article, we briefly introduce AI and explain how it can be used in research, examine some of the ethical issues raised when using it, and offer nine recommendations for responsible use, including: (1) Researchers are responsible for identifying, describing, reducing, and controlling AI-related biases and random errors; (2) Researchers should disclose, describe, and explain their use of AI in research, including its limitations, in language that can be understood by non-experts; (3) Researchers should engage with impacted communities, populations, and other stakeholders concerning the use of AI in research to obtain their advice and assistance and address their interests and concerns, such as issues related to bias; (4) Researchers who use synthetic data should (a) indicate which parts of the data are synthetic; (b) clearly label the synthetic data; (c) describe how the data were generated; and (d) explain how and why the data were used; (5) AI systems should not be named as authors, inventors, or copyright holders but their contributions to research should be disclosed and described; (6) Education and mentoring in responsible conduct of research should include discussion of ethical use of AI.

Sensory-biased autoencoder enables prediction of texture perception from food rheology

Understanding how the physical properties of food affect sensory perception remains a critical challenge for food design. Here, we present an innovative machine learning strategy to decode the complex relationships between non-Newtonian rheological attributes of liquid foods and their perceived texture. A unique and key aspect of our approach is the implementation of an autoencoder neural network that incorporates sensory scores as a decoder bias during training. This enables the autoencoder to effectively identify non-linear, non-injective relationships between shear-thinning properties and perceived thickness, even when trained on a small dataset. This strategy offers a promising approach for advancing food product development by aiding the design of carefully tailored sensory experiences.

Accurately Models the Relationship Between Physical Response and Structure Using Kolmogorov-Arnold Network

Artificial intelligence (AI) in science is a key area of modern research. However, many current machine learning methods lack interpretability, making it difficult to grasp the physical mechanisms behind various phenomena, which hampers progress in related fields. This study focuses on the Poisson's ratio of a hexagonal lattice elastic network as it varies with structural deformation. By employing the Kolmogorov-Arnold Network (KAN), the transition of the network's Poisson's ratio from positive to negative as the hexagonal structural element shifts from a convex polygon to a concave polygon was accurately predicted. The KAN provides a clear mathematical framework that describes this transition, revealing the connection between the Poisson's ratio and the geometric properties of the hexagonal element, and accurately identifying the geometric parameters at which the Poisson's ratio equals zero. This work demonstrates the significant potential of the KAN network to clarify the mathematical relationships that underpin physical responses and structural behaviors.

The potential for AI to revolutionize conservation: a horizon scan

Artificial Intelligence (AI) is an emerging tool that could be leveraged to identify the effective conservation solutions demanded by the urgent biodiversity crisis. We present the results of our horizon scan of AI applications likely to significantly benefit biological conservation. An international panel of conservation scientists and AI experts identified 21 key ideas. These included species recognition to uncover 'dark diversity', multimodal models to improve biodiversity loss predictions, monitoring wildlife trade, and addressing human-wildlife conflict. We consider the potential negative impacts of AI adoption, such as AI colonialism and loss of essential conservation skills, and suggest how the conservation field might adapt to harness the benefits of AI while mitigating its risks.

Empowering nanophotonic applications via artificial intelligence: pathways, progress, and prospects

Empowering nanophotonic devices via artificial intelligence (AI) has revolutionized both scientific research methodologies and engineering practices, addressing critical challenges in the design and optimization of complex systems. Traditional methods for developing nanophotonic devices are often constrained by the high dimensionality of design spaces and computational inefficiencies. This review highlights how AI-driven techniques provide transformative solutions by enabling the efficient exploration of vast design spaces, optimizing intricate parameter systems, and predicting the performance of advanced nanophotonic materials and devices with high accuracy. By bridging the gap between computational complexity and practical implementation, AI accelerates the discovery of novel nanophotonic functionalities. Furthermore, we delve into emerging domains, such as diffractive neural networks and quantum machine learning, emphasizing their potential to exploit photonic properties for innovative strategies. The review also examines AI's applications in advanced engineering areas, e.g., optical image recognition, showcasing its role in addressing complex challenges in device integration. By facilitating the development of highly efficient, compact optical devices, these AI-powered methodologies are paving the way for next-generation nanophotonic systems with enhanced functionalities and broader applications.

Towards Data-And Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing

Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the recent developments and important contributions of NeSy research. First, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Next, we briefly discuss the successful application of modern NeSy approaches in several domains. Then, we benchmark several NeSy methods on three representative application tasks. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly evolving field and accelerate the progress towards data-and knowledge-driven AI.

Open Science at the generative AI turn: An exploratory analysis of challenges and opportunities

Technology influences Open Science (OS) practices, because conducting science in transparent, accessible, and participatory ways requires tools and platforms for collaboration and sharing results. Due to this relationship, the characteristics of the employed technologies directly impact OS objectives. Generative Artificial Intelligence (GenAI) is increasingly used by researchers for tasks such as text refining, code generation/editing, reviewing literature, and data curation/analysis. Nevertheless, concerns about openness, transparency, and bias suggest that GenAI may benefit from greater engagement with OS. GenAI promises substantial efficiency gains but is currently fraught with limitations that could negatively impact core OS values, such as fairness, transparency, and integrity, and may harm various social actors. In this paper, we explore the possible positive and negative impacts of GenAI on OS. We use the taxonomy within the UNESCO Recommendation on Open Science to systematically explore the intersection of GenAI and OS. We conclude that using GenAI could advance key OS objectives by broadening meaningful access to knowledge, enabling efficient use of infrastructure, improving engagement of societal actors, and enhancing dialogue among knowledge systems. However, due to GenAI's limitations, it could also compromise the integrity, equity, reproducibility, and reliability of research. Hence, sufficient checks, validation, and critical assessments are essential when incorporating GenAI into research workflows.

Umbrella Sampling MD Simulations for Retention Prediction in Peptide Reversed-phase Liquid Chromatography

Reversed-phase liquid chromatography (RPLC) is an essential tool for separating complex mixtures such as proteolytic digests in bottom-up proteomics. There is growing interest in methods that can predict the RPLC retention behavior of peptides and other analytes. Already, existing algorithms provide excellent performance based on empirical rules or large sets of RPLC training data. Here we explored a new type of retention prediction strategy that relies on first-principles modeling of peptide interactions with a C18 stationary phase. We recently demonstrated that molecular dynamics (MD) simulations can provide atomistic insights into the behavior of peptides under RPLC conditions (Anal. Chem. 2023, 95, 3892). However, the current work found that it is problematic to use conventional MD data for retention prediction, evident from a poor correlation between experimental retention times and MD-generated "fraction bound" values. We thus turned to umbrella sampling MD, a complementary technique that has previously been applied to probe noncovalent contacts in other types of systems. By restraining the peptide dynamic motions at various positions inside a C18-lined pore, we determined the free energy of the system as a function of peptide-stationary phase distance. ΔGbinding values determined in this way under various mobile phase conditions were linearly correlated with experimental retention times of tryptic test peptides. This work opens retention prediction avenues for novel types of stationary and mobile phases, and for peptides (or other analytes) having arbitrary chemical properties, without the need for RPLC reference data. Umbrella sampling can be used as a stand-alone tool, or it may serve to enhance existing retention prediction algorithms.

Automated discovery of experimental designs in super-resolution microscopy with XLuminA

Driven by human ingenuity and creativity, the discovery of super-resolution techniques, which circumvent the classical diffraction limit of light, represent a leap in optical microscopy. However, the vast space encompassing all possible experimental configurations suggests that some powerful concepts and techniques might have not been discovered yet, and might never be with a human-driven direct design approach. Thus, AI-based exploration techniques could provide enormous benefit, by exploring this space in a fast, unbiased way. We introduce XLuminA, an open-source computational framework developed using JAX, a high-performance computing library in Python. XLuminA offers enhanced computational speed enabled by JAX's accelerated linear algebra compiler (XLA), just-in-time compilation, and its seamlessly integrated automatic vectorization, automatic differentiation capabilities and GPU compatibility. XLuminA demonstrates a speed-up of 4 orders of magnitude compared to well-established numerical optimization methods. We showcase XLuminA's potential by re-discovering three foundational experiments in advanced microscopy, and identifying an unseen experimental blueprint featuring sub-diffraction imaging capabilities. This work constitutes an important step in AI-driven scientific discovery of new concepts in optics and advanced microscopy.

Quantifying the use and potential benefits of artificial intelligence in scientific research

The rapid advancement of artificial intelligence (AI) is poised to reshape almost every line of work. Despite enormous efforts devoted to understanding AI's economic impacts, we lack a systematic understanding of the benefits to scientific research associated with the use of AI. Here we develop a measurement framework to estimate the direct use of AI and associated benefits in science. We find that the use and benefits of AI appear widespread throughout the sciences, growing especially rapidly since 2015. However, there is a substantial gap between AI education and its application in research, highlighting a misalignment between AI expertise supply and demand. Our analysis also reveals demographic disparities, with disciplines with higher proportions of women or Black scientists reaping fewer benefits from AI, potentially exacerbating existing inequalities in science. These findings have implications for the equity and sustainability of the research enterprise, especially as the integration of AI with science continues to deepen.

Exploring the cytotoxic and antioxidant properties of lanthanide-doped ZnO nanoparticles: a study with machine learning interpretation

BACKGROUND

Lanthanide-based nanomaterials offer a promising alternative for cancer therapy because of their selectivity and effectiveness, which can be modified and predicted by leveraging the improved accuracy and enhanced decision-making of machine learning (ML) modeling.

METHODS

In this study, erbium (Er3+) and ytterbium (Yb3+) were used to dope zinc oxide (ZnO) nanoparticles (NPs). Various characterization techniques and biological assays were employed to investigate the physicochemical and optical properties of the (Er, Yb)-doped ZnO NPs, revealing the influence of the lanthanide elements.

RESULTS

The (Er, Yb)-doped ZnO NPs exhibited laminar-type morphologies, negative surface charges, and optical bandgaps that vary with the presence of Er3+ and Yb3+. The incorporation of lanthanide ions reduced the cytotoxicity activity of ZnO against HEPG-2, CACO-2, and U87 cell lines. Conversely, doping with Er3+ and Yb3+ enhanced the antioxidant activity of the ZnO against DPPH, ABTS, and H2O2 radicals. The extra tree (ET) and random forest (RF) models predicted the relevance of the characterization results vis-à-vis the cytotoxic properties of the synthesized NPs.

CONCLUSION

This study demonstrates, for the first time, the synthesis of ZnO NPs doped with Er and Yb via a solution polymerization route. According to characterization results, it was unveiled that the effect of optical bandgap variations influenced the cytotoxic performance of the developed lanthanide-doped ZnO NPs, being the undoped ZnO NPs the most cytotoxic ones. The presence alone or in combination of Er and Yb enhanced their scavenging capacity. ML models such as ET and RF efficiently demonstrated that the concentration and cell line type are key parameters that influence the cytotoxicity of (Er, Yb)-doped ZnO NPs achieving high accuracy rates of 98.96% and 98.67%, respectively. This study expands the knowledge of lanthanides as dopants of nanomaterials for biological and medical applications and supports their potential in cancer therapy by integrating robust ML approaches.

Empowering biomedical discovery with AI agents

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

Science of science: A multidisciplinary field studying science

Science and knowledge are studied by researchers across many disciplines, examining how they are developed, what their current boundaries are and how we can advance them. By integrating evidence across disparate disciplines, the holistic field of science of science can address these foundational questions. This field illustrates how science is shaped by many interconnected factors: the cognitive processes of scientists, the historical evolution of science, economic incentives, institutional influences, computational approaches, statistical, mathematical and instrumental foundations of scientific inference, scientometric measures, philosophical and ethical dimensions of scientific concepts, among other influences. Achieving a comprehensive overview of a multifaceted field like the science of science requires pulling together evidence from the many sub-fields studying science across the natural and social sciences and humanities. This enables developing an interdisciplinary perspective of scientific practice, a more holistic understanding of scientific processes and outcomes, and more nuanced perspectives to how scientific research is conducted, influenced and evolves. It enables leveraging the strengths of various disciplines to create a holistic view of the foundations of science. Different researchers study science from their own disciplinary perspective and use their own methods, and there is a large divide between quantitative and qualitative researchers as they commonly do not read or cite research using other methodological approaches. A broader, synthesizing paper employing a qualitative approach can however help provide a bridge between disciplines by pulling together aspects of science (economic, scientometric, psychological, philosophical etc.). Such an approach enables identifying, across the range of fields, the powerful role of our scientific methods and instruments in shaping most aspects of our knowledge and science, whereas economic, social and historical influences help shape what knowledge we pursue. A unifying theory is then outlined for science of science - the new-methods-drive-science theory.

Recent advances and applications of artificial intelligence in 3D bioprinting

3D bioprinting techniques enable the precise deposition of living cells, biomaterials, and biomolecules, emerging as a promising approach for engineering functional tissues and organs. Meanwhile, recent advances in 3D bioprinting enable researchers to build in vitro models with finely controlled and complex micro-architecture for drug screening and disease modeling. Recently, artificial intelligence (AI) has been applied to different stages of 3D bioprinting, including medical image reconstruction, bioink selection, and printing process, with both classical AI and machine learning approaches. The ability of AI to handle complex datasets, make complex computations, learn from past experiences, and optimize processes dynamically makes it an invaluable tool in advancing 3D bioprinting. The review highlights the current integration of AI in 3D bioprinting and discusses future approaches to harness the synergistic capabilities of 3D bioprinting and AI for developing personalized tissues and organs.

Stimulus-induced dynamical states in an adaptive network with symmetric adaptation

We consider an adaptive network of identical phase oscillators with the symmetric adaptation rule for the evolution of the connection weights under the influence of an external force. We show that the adaptive network exhibits a plethora of self-organizing dynamical states such as the two-cluster state, multiantipodal clusters, splay cluster, splay chimera, forced entrained state, chimera state, bump state, coherent, and incoherent states in the two-parameter phase diagrams. The intriguing structures of the frequency clusters and instantaneous phases of the oscillators characterize the distinct self-organized synchronized and partial synchronized states. The hierarchical organization of the frequency clusters, resulting in strongly coupled subnetworks, is also evident from the dynamics of the coupling weights, where the frequency clusters are either very weakly coupled or even completely decoupled from each other. Additionally, we also deduce the stability condition for the forced entrained state.

Self-Driving Laboratories for Chemistry and Materials Science

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

Deductive machine learning models for product identification

Deductive solution strategies are required in prediction scenarios that are under determined, when contradictory information is available, or more generally wherever one-to-many non-functional mappings occur. In contrast, most contemporary machine learning (ML) in the chemical sciences is inductive learning from example, with a fixed set of features. Chemical workflows are replete with situations requiring deduction, including many aspects of lab automation and spectral interpretation. Here, a general strategy is described for designing and training machine learning models capable of deduction that consists of combining individual inductive models into a larger deductive network. The training and testing of these models is demonstrated on the task of deducing reaction products from a mixture of spectral sources. The resulting models can distinguish between intended and unintended reaction outcomes and identify starting material based on a mixture of spectral sources. The models also perform well on tasks that they were not directly trained on, like performing structural inference using real rather than simulated spectral inputs, predicting minor products from named organic chemistry reactions, identifying reagents and isomers as plausible impurities, and handling missing or conflicting information. A new dataset of 1 124 043 simulated spectra that were generated to train these models is also distributed with this work. These findings demonstrate that deductive bottlenecks for chemical problems are not fundamentally insuperable for ML models.

AI-Assisted Rational Design and Activity Prediction of Biological Elements for Optimizing Transcription-Factor-Based Biosensors

The rational design, activity prediction, and adaptive application of biological elements (bio-elements) are crucial research fields in synthetic biology. Currently, a major challenge in the field is efficiently designing desired bio-elements and accurately predicting their activity using vast datasets. The advancement of artificial intelligence (AI) technology has enabled machine learning and deep learning algorithms to excel in uncovering patterns in bio-element data and predicting their performance. This review explores the application of AI algorithms in the rational design of bio-elements, activity prediction, and the regulation of transcription-factor-based biosensor response performance using AI-designed elements. We discuss the advantages, adaptability, and biological challenges addressed by the AI algorithms in various applications, highlighting their powerful potential in analyzing biological data. Furthermore, we propose innovative solutions to the challenges faced by AI algorithms in the field and suggest future research directions. By consolidating current research and demonstrating the practical applications and future potential of AI in synthetic biology, this review provides valuable insights for advancing both academic research and practical applications in biotechnology.

Learning interpretable dynamics of stochastic complex systems from experimental data

Complex systems with many interacting nodes are inherently stochastic and best described by stochastic differential equations. Despite increasing observation data, inferring these equations from empirical data remains challenging. Here, we propose the Langevin graph network approach to learn the hidden stochastic differential equations of complex networked systems, outperforming five state-of-the-art methods. We apply our approach to two real systems: bird flock movement and tau pathology diffusion in brains. The inferred equation for bird flocks closely resembles the second-order Vicsek model, providing unprecedented evidence that the Vicsek model captures genuine flocking dynamics. Moreover, our approach uncovers the governing equation for the spread of abnormal tau proteins in mouse brains, enabling early prediction of tau occupation in each brain region and revealing distinct pathology dynamics in mutant mice. By learning interpretable stochastic dynamics of complex systems, our findings open new avenues for downstream applications such as control.

Interfacing consciousness

The current stage of consciousness science has reached an impasse. We blame the physicalist worldview for this and propose a new perspective to make progress on the problems of consciousness. Our perspective is rooted in the theory of conscious agents. We thereby stress the fundamentality of consciousness outside of spacetime, the importance of agency, and the mathematical character of the theory. For conscious agent theory (CAT) to achieve the status of a robust scientific framework, it needs to be integrated with a good explanation of perception and cognition. We argue that this role is played by the interface theory of perception (ITP), an evolutionary-based model of perception that has been previously formulated and defended by the authors. We are specifically interested in what this tells us about the possibility of AI consciousness and conclude with a somewhat counter-intuitive proposal: we live inside a simulation instantiated, not digitally, but in consciousness. Such a simulation is just an interface representation of the dynamics of conscious agents for a conscious agent. This paves the way for employing AI in consciousness science through customizing our interface.

APACE: AlphaFold2 and advanced computing as a service for accelerated discovery in biophysics

The prediction of protein 3D structure from amino acid sequence is a computational grand challenge in biophysics and plays a key role in robust protein structure prediction algorithms, from drug discovery to genome interpretation. The advent of AI models, such as AlphaFold, is revolutionizing applications that depend on robust protein structure prediction algorithms. To maximize the impact, and ease the usability, of these AI tools we introduce APACE, AlphaFold2 and advanced computing as a service, a computational framework that effectively handles this AI model and its TB-size database to conduct accelerated protein structure prediction analyses in modern supercomputing environments. We deployed APACE in the Delta and Polaris supercomputers and quantified its performance for accurate protein structure predictions using four exemplar proteins: 6AWO, 6OAN, 7MEZ, and 6D6U. Using up to 300 ensembles, distributed across 200 NVIDIA A100 GPUs, we found that APACE is up to two orders of magnitude faster than off-the-self AlphaFold2 implementations, reducing time-to-solution from weeks to minutes. This computational approach may be readily linked with robotics laboratories to automate and accelerate scientific discovery.

A practical guide to the implementation of artificial intelligence in orthopaedic research-Part 2: A technical introduction

Recent advances in artificial intelligence (AI) present a broad range of possibilities in medical research. However, orthopaedic researchers aiming to participate in research projects implementing AI-based techniques require a sound understanding of the technical fundamentals of this rapidly developing field. Initial sections of this technical primer provide an overview of the general and the more detailed taxonomy of AI methods. Researchers are presented with the technical basics of the most frequently performed machine learning (ML) tasks, such as classification, regression, clustering and dimensionality reduction. Additionally, the spectrum of supervision in ML including the domains of supervised, unsupervised, semisupervised and self-supervised learning will be explored. Recent advances in neural networks (NNs) and deep learning (DL) architectures have rendered them essential tools for the analysis of complex medical data, which warrants a rudimentary technical introduction to orthopaedic researchers. Furthermore, the capability of natural language processing (NLP) to interpret patterns in human language is discussed and may offer several potential applications in medical text classification, patient sentiment analysis and clinical decision support. The technical discussion concludes with the transformative potential of generative AI and large language models (LLMs) on AI research. Consequently, this second article of the series aims to equip orthopaedic researchers with the fundamental technical knowledge required to engage in interdisciplinary collaboration in AI-driven orthopaedic research.

LEVEL OF EVIDENCE

Level IV.

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

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

Application of a Machine Learning-Based Classification Approach for Developing Host Protein Diagnostic Models for Infectious Disease

In recent years, infectious disease diagnosis has increasingly turned to host-centered approaches as a complement to pathogen-directed ones. The former, however, typically requires the interpretation of complex multiple biomarker datasets to arrive at an informative diagnostic outcome. This report describes a machine learning (ML)-based classification workflow that is intended as a template for researchers seeking to apply ML approaches for developing host-based infectious disease biomarker classifiers. As an example, we built a classification model that could accurately distinguish between three disease etiology classes: bacterial, viral, and normal in human sera using host protein biomarkers of known diagnostic utility. After collecting protein data from known disease samples, we trained a series of increasingly complex Auto-ML models until arriving at an optimized classifier that could differentiate viral, bacterial, and non-disease samples. Even when limited to a relatively small training set size, the model had robust diagnostic characteristics and performed well when faced with a blinded sample set. We present here a flexible approach for applying an Auto-ML-based workflow for the identification of host biomarker classifiers with diagnostic utility for infectious disease, and which can readily be adapted for multiple biomarker classes and disease states.

Application of the artificial intelligence system based on graphics and vision in ethnic tourism of subtropical grasslands

This study aims to optimize the evaluation and decision-making of ethnic tourism resources through the utilization of deep learning algorithms and Internet of Things (IoT) technology. Specifically, emphasis is placed on the recognition and feature extraction of Mongolian decorative patterns, providing new insights for the deep application of cultural heritage and visual design. In this study, the existing DL algorithm is improved, integrating the feature extraction algorithm of ResNet + Canny + Local Binary Pattern (LBP), and utilizing an intelligent decision method to analyze the intelligent development of indigenous tourism resources. Simultaneously, the DL algorithm and IoT technology are combined with visual design and convolutional neural networks to perform feature extraction and technology recognition. Visual design offers an intuitive representation of tourism resources, while fuzzy decision-making provides a more accurate evaluation in the face of uncertainty. By implementing an intelligent decision-making system, this study achieves a multiplier effect. The integration of intelligent methods not only enhances the accuracy of tourism resource evaluation and decision-making but also elevates the quality and efficiency of the tourism experience. This multiplier effect is evident in the system's capacity to manage substantial datasets and deliver prompt, precise decision support, thus playing a pivotal role in tourism resource management and planning. The findings of this study demonstrate that optimizing intelligent development technology for rural tourism through IoT can enhance the efficacy of intelligent solutions. In terms of pattern recognition accuracy, AlexNet, VGGNet, and ResNet achieve accuracies of 90.8 %, 94.5 %, and 96.9 %, respectively, while the proposed fusion algorithm attains an accuracy of 98.8 %. These results offer practical insights for rural tourism brand strategy and underscore the utility of applying fuzzy decision systems in urban tourism and visual design. Moreover, the research outcomes hold significant practical implications for the advancement of Mongolian cultural tourism and provide valuable lessons for exploring novel paradigms in image analysis and pattern recognition. This study contributes beneficial insights for future research endeavors in related domains.

Combining Bayesian optimization and automation to simultaneously optimize reaction conditions and routes

Reaching optimal reaction conditions is crucial to achieve high yields, minimal by-products, and environmentally sustainable chemical reactions. With the recent rise of artificial intelligence, there has been a shift from traditional Edisonian trial-and-error optimization to data-driven and automated approaches, which offer significant advantages. Here, we showcase the capabilities of an integrated platform; we conducted simultaneous optimizations of four different terminal alkynes and two reaction routes using an automation platform combined with a Bayesian optimization platform. Remarkably, we achieved a conversion rate of over 80% for all four substrates in 23 experiments, covering ca. 0.2% of the combinatorial space. Further analysis allowed us to identify the influence of different reaction parameters on the reaction outcomes, demonstrating the potential for expedited reaction condition optimization and the prospect of more efficient chemical processes in the future.

CIME4R: Exploring iterative, AI-guided chemical reaction optimization campaigns in their parameter space

Chemical reaction optimization (RO) is an iterative process that results in large, high-dimensional datasets. Current tools allow for only limited analysis and understanding of parameter spaces, making it hard for scientists to review or follow changes throughout the process. With the recent emergence of using artificial intelligence (AI) models to aid RO, another level of complexity has been added. Helping to assess the quality of a model's prediction and understand its decision is critical to supporting human-AI collaboration and trust calibration. To address this, we propose CIME4R-an open-source interactive web application for analyzing RO data and AI predictions. CIME4R supports users in (i) comprehending a reaction parameter space, (ii) investigating how an RO process developed over iterations, (iii) identifying critical factors of a reaction, and (iv) understanding model predictions. This facilitates making informed decisions during the RO process and helps users to review a completed RO process, especially in AI-guided RO. CIME4R aids decision-making through the interaction between humans and AI by combining the strengths of expert experience and high computational precision. We developed and tested CIME4R with domain experts and verified its usefulness in three case studies. Using CIME4R the experts were able to produce valuable insights from past RO campaigns and to make informed decisions on which experiments to perform next. We believe that CIME4R is the beginning of an open-source community project with the potential to improve the workflow of scientists working in the reaction optimization domain. SCIENTIFIC CONTRIBUTION: To the best of our knowledge, CIME4R is the first open-source interactive web application tailored to the peculiar analysis requirements of reaction optimization (RO) campaigns. Due to the growing use of AI in RO, we developed CIME4R with a special focus on facilitating human-AI collaboration and understanding of AI models. We developed and evaluated CIME4R in collaboration with domain experts to verify its practical usefulness.

Developing a predictive science of the biosphere requires the integration of scientific cultures

Increasing the speed of scientific progress is urgently needed to address the many challenges associated with the biosphere in the Anthropocene. Consequently, the critical question becomes: How can science most rapidly progress to address large, complex global problems? We suggest that the lag in the development of a more predictive science of the biosphere is not only because the biosphere is so much more complex, or because we do not have enough data, or are not doing enough experiments, but, in large part, because of unresolved tension between the three dominant scientific cultures that pervade the research community. We introduce and explain the concept of the three scientific cultures and present a novel analysis of their characteristics, supported by examples and a formal mathematical definition/representation of what this means and implies. The three cultures operate, to varying degrees, across all of science. However, within the biosciences, and in contrast to some of the other sciences, they remain relatively more separated, and their lack of integration has hindered their potential power and insight. Our solution to accelerating a broader, predictive science of the biosphere is to enhance integration of scientific cultures. The process of integration-Scientific Transculturalism-recognizes that the push for interdisciplinary research, in general, is just not enough. Unless these cultures of science are formally appreciated and their thinking iteratively integrated into scientific discovery and advancement, there will continue to be numerous significant challenges that will increasingly limit forecasting and prediction efforts.

Acceleration of Graph Neural Network-Based Prediction Models in Chemistry via Co-Design Optimization on Intelligence Processing Units

Atomic structure prediction and associated property calculations are the bedrock of chemical physics. Since high-fidelity ab initio modeling techniques for computing the structure and properties can be prohibitively expensive, this motivates the development of machine-learning (ML) models that make these predictions more efficiently. Training graph neural networks over large atomistic databases introduces unique computational challenges, such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs, such as social networks. We demonstrate a novel hardware-software codesign approach to scale up the training of atomistic graph neural networks (GNN) for structure and property prediction. First, to eliminate redundant computation and memory associated with alternative padding techniques and to improve throughput via minimizing communication, we formulate the effective coalescing of the batches of variable-size atomistic graphs as the bin packing problem and introduce a hardware-agnostic algorithm to pack these batches. In addition, we propose hardware-specific optimizations, including a planner and vectorization for the gather-scatter operations targeted for Graphcore's Intelligence Processing Unit (IPU), as well as model-specific optimizations such as merged communication collectives and optimized softplus. Putting these all together, we demonstrate the effectiveness of the proposed codesign approach by providing an implementation of a well-established atomistic GNN on the Graphcore IPUs. We evaluate the training performance on multiple atomistic graph databases with varying degrees of graph counts, sizes, and sparsity. We demonstrate that such a codesign approach can reduce the training time of atomistic GNNs and can improve their performance by up to 1.5× compared to the baseline implementation of the model on the IPUs. Additionally, we compare our IPU implementation with a Nvidia GPU-based implementation and show that our atomistic GNN implementation on the IPUs can run 1.8× faster on average compared to the execution time on the GPUs.

Artificial intelligence and illusions of understanding in scientific research

Scientists are enthusiastically imagining ways in which artificial intelligence (AI) tools might improve research. Why are AI tools so attractive and what are the risks of implementing them across the research pipeline? Here we develop a taxonomy of scientists' visions for AI, observing that their appeal comes from promises to improve productivity and objectivity by overcoming human shortcomings. But proposed AI solutions can also exploit our cognitive limitations, making us vulnerable to illusions of understanding in which we believe we understand more about the world than we actually do. Such illusions obscure the scientific community's ability to see the formation of scientific monocultures, in which some types of methods, questions and viewpoints come to dominate alternative approaches, making science less innovative and more vulnerable to errors. The proliferation of AI tools in science risks introducing a phase of scientific enquiry in which we produce more but understand less. By analysing the appeal of these tools, we provide a framework for advancing discussions of responsible knowledge production in the age of AI.

Accelerated chemical science with AI

In light of the pressing need for practical materials and molecular solutions to renewable energy and health problems, to name just two examples, one wonders how to accelerate research and development in the chemical sciences, so as to address the time it takes to bring materials from initial discovery to commercialization. Artificial intelligence (AI)-based techniques, in particular, are having a transformative and accelerating impact on many if not most, technological domains. To shed light on these questions, the authors and participants gathered in person for the ASLLA Symposium on the theme of 'Accelerated Chemical Science with AI' at Gangneung, Republic of Korea. We present the findings, ideas, comments, and often contentious opinions expressed during four panel discussions related to the respective general topics: 'Data', 'New applications', 'Machine learning algorithms', and 'Education'. All discussions were recorded, transcribed into text using Open AI's Whisper, and summarized using LG AI Research's EXAONE LLM, followed by revision by all authors. For the broader benefit of current researchers, educators in higher education, and academic bodies such as associations, publishers, librarians, and companies, we provide chemistry-specific recommendations and summarize the resulting conclusions.

Autonomous nanomanufacturing of lead-free metal halide perovskite nanocrystals using a self-driving fluidic lab

Lead-based metal halide perovskite (MHP) nanocrystals (NCs) have emerged as a promising class of semiconducting nanomaterials for a wide range of optoelectronic and photoelectronic applications. However, the intrinsic lead toxicity of MHP NCs has significantly hampered their large-scale device applications. Copper-base MHP NCs with composition-tunable optical properties have emerged as a prominent lead-free MHP NC candidate. However, comprehensive synthesis space exploration, development, and synthesis science studies of copper-based MHP NCs have been limited by the manual nature of flask-based synthesis and characterization methods. In this study, we present an autonomous approach for the development of lead-free MHP NCs via seamless integration of a modular microfluidic platform with machine learning-assisted NC synthesis modeling and experiment selection to establish a self-driving fluidic lab for accelerated NC synthesis science studies. For the first time, a successful and reproducible in-flow synthesis of Cs3Cu2I5 NCs is presented. Autonomous experimentation is then employed for rapid in-flow synthesis science studies of Cs3Cu2I5 NCs. The autonomously generated experimental NC synthesis dataset is then utilized for fast-tracked synthetic route optimization of high-performing Cs3Cu2I5 NCs.

Darwinian evolution has become dogma; AI can rescue what is salvageable

Artificial Intelligence (AI), as an academic discipline, is traceable to the mid-1950s but it is currently exploding in applications with successes and concerns. AI can be defined as intelligence demonstrated by computers, with intelligence difficult to define but it must include concepts of ability to learn, reason, and generalize from a vast amount of information and, we propose, to infer meaning. The type of AI known as general AI, has strong, but unrealized potential both for assessing and also for solving major problems with the scientific theory of Darwinian evolution, including its modern variants and for origin of life studies. Specifically, AI should be applied first to evaluate the strengths and weaknesses of the assumptions and empirical information underpinning theories of the origin of life and probability of its evolution. AI should then be applied to assess the scientific validity of the theory of how abundant life came to be on earth.

Exploiting redundancy in large materials datasets for efficient machine learning with less data

Extensive efforts to gather materials data have largely overlooked potential data redundancy. In this study, we present evidence of a significant degree of redundancy across multiple large datasets for various material properties, by revealing that up to 95% of data can be safely removed from machine learning training with little impact on in-distribution prediction performance. The redundant data is related to over-represented material types and does not mitigate the severe performance degradation on out-of-distribution samples. In addition, we show that uncertainty-based active learning algorithms can construct much smaller but equally informative datasets. We discuss the effectiveness of informative data in improving prediction performance and robustness and provide insights into efficient data acquisition and machine learning training. This work challenges the "bigger is better" mentality and calls for attention to the information richness of materials data rather than a narrow emphasis on data volume.

Knowledge-driven learning, optimization, and experimental design under uncertainty for materials discovery

Significant acceleration of the future discovery of novel functional materials requires a fundamental shift from the current materials discovery practice, which is heavily dependent on trial-and-error campaigns and high-throughput screening, to one that builds on knowledge-driven advanced informatics techniques enabled by the latest advances in signal processing and machine learning. In this review, we discuss the major research issues that need to be addressed to expedite this transformation along with the salient challenges involved. We especially focus on Bayesian signal processing and machine learning schemes that are uncertainty aware and physics informed for knowledge-driven learning, robust optimization, and efficient objective-driven experimental design.

An international consensus on effective, inclusive, and career-spanning short-format training in the life sciences and beyond

Science, technology, engineering, mathematics, and medicine (STEMM) fields change rapidly and are increasingly interdisciplinary. Commonly, STEMM practitioners use short-format training (SFT) such as workshops and short courses for upskilling and reskilling, but unaddressed challenges limit SFT's effectiveness and inclusiveness. Education researchers, students in SFT courses, and organizations have called for research and strategies that can strengthen SFT in terms of effectiveness, inclusiveness, and accessibility across multiple dimensions. This paper describes the project that resulted in a consensus set of 14 actionable recommendations to systematically strengthen SFT. A diverse international group of 30 experts in education, accessibility, and life sciences came together from 10 countries to develop recommendations that can help strengthen SFT globally. Participants, including representation from some of the largest life science training programs globally, assembled findings in the educational sciences and encompassed the experiences of several of the largest life science SFT programs. The 14 recommendations were derived through a Delphi method, where consensus was achieved in real time as the group completed a series of meetings and tasks designed to elicit specific recommendations. Recommendations cover the breadth of SFT contexts and stakeholder groups and include actions for instructors (e.g., make equity and inclusion an ethical obligation), programs (e.g., centralize infrastructure for assessment and evaluation), as well as organizations and funders (e.g., professionalize training SFT instructors; deploy SFT to counter inequity). Recommendations are aligned with a purpose-built framework-"The Bicycle Principles"-that prioritizes evidenced-based teaching, inclusiveness, and equity, as well as the ability to scale, share, and sustain SFT. We also describe how the Bicycle Principles and recommendations are consistent with educational change theories and can overcome systemic barriers to delivering consistently effective, inclusive, and career-spanning SFT.

Accurate, interpretable predictions of materials properties within transformer language models

Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability. Here, we present an elegant way to make their reasoning transparent. Human-readable text-based descriptions automatically generated within a suite of open-source tools are proposed as materials representation. Transformer language models pretrained on 2 million peer-reviewed articles take as input well-known terms such as chemical composition, crystal symmetry, and site geometry. Our approach outperforms crystal graph networks by classifying four out of five analyzed properties if one considers all available reference data. Moreover, fine-tuned text-based models show high accuracy in the ultra-small data limit. Explanations of their internal machinery are produced using local interpretability techniques and are faithful and consistent with domain expert rationales. This language-centric framework makes accurate property predictions accessible to people without artificial-intelligence expertise.

14 examples of how LLMs can transform materials science and chemistry: a reflection on a large language model hackathon

Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, we organized a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications. The diverse topics and the fact that working prototypes could be generated in less than two days highlight that LLMs will profoundly impact the future of our fields. The rich collection of ideas and projects also indicates that the applications of LLMs are not limited to materials science and chemistry but offer potential benefits to a wide range of scientific disciplines.

Raising awareness of sex and gender bias in artificial intelligence and health

Historically, biomedical research has been led by and focused on men. The recent introduction of Artificial Intelligence (AI) in this area has further proven this practice to be discriminatory for other sexes and genders, more noticeably for women. To move towards a fair AI development, it is essential to include sex and gender diversity both in research practices and in the workplace. In this context, the Bioinfo4women (B4W) program of the Barcelona Supercomputing Center (i) promotes the participation of women scientists by improving their visibility, (ii) fosters international collaborations between institutions and programs and (iii) advances research on sex and gender bias in AI and health. In this article, we discuss methodology and results of a series of conferences, titled “Sex and Gender Bias in Artificial Intelligence and Health, organized by B4W and La Caixa Foundation from March to June 2021 in Barcelona, Spain. The series consisted of nine hybrid events, composed of keynote sessions and seminars open to the general audience, and two working groups with invited experts from different professional backgrounds (academic fields such as biology, engineering, and sociology, as well as NGOs, journalists, lawyers, policymakers, industry). Based on this awareness-raising action, we distilled key recommendations to facilitate the inclusion of sex and gender perspective into public policies, educational programs, industry, and biomedical research, among other sectors, and help overcome sex and gender biases in AI and health.

High-Throughput Synthesis and Machine Learning Assisted Design of Photodegradable Hydrogels

Due to the large chemical space, the design of functional and responsive soft materials poses many challenges but also offers a wide range of opportunities in terms of the scope of possible properties. Herein, an experimental workflow for miniaturized combinatorial high-throughput screening of functional hydrogel libraries is reported. The data created from the analysis of the photodegradation process of more than 900 different types of hydrogel pads are used to train a machine learning model for automated decision making. Through iterative model optimization based on Bayesian optimization, a substantial improvement in response properties is achieved and thus expanded the scope of material properties obtainable within the chemical space of hydrogels in the study. It is therefore demonstrated that the potential of combining miniaturized high-throughput experiments with smart optimization algorithms for cost and time efficient optimization of materials properties.

The central role of density functional theory in the AI age

Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.

Perspectives on adaptive dynamical systems

Adaptivity is a dynamical feature that is omnipresent in nature, socio-economics, and technology. For example, adaptive couplings appear in various real-world systems, such as the power grid, social, and neural networks, and they form the backbone of closed-loop control strategies and machine learning algorithms. In this article, we provide an interdisciplinary perspective on adaptive systems. We reflect on the notion and terminology of adaptivity in different disciplines and discuss which role adaptivity plays for various fields. We highlight common open challenges and give perspectives on future research directions, looking to inspire interdisciplinary approaches.

Development of Antiepileptic Drugs throughout History: From Serendipity to Artificial Intelligence

This article provides a comprehensive narrative review of the history of antiepileptic drugs (AEDs) and their development over time. Firstly, it explores the significant role of serendipity in the discovery of essential AEDs that continue to be used today, such as phenobarbital and valproic acid. Subsequently, it delves into the historical progression of crucial preclinical models employed in the development of novel AEDs, including the maximal electroshock stimulation test, pentylenetetrazol-induced test, kindling models, and other animal models. Moving forward, a concise overview of the clinical advancement of major AEDs is provided, highlighting the initial milestones and the subsequent refinement of this process in recent decades, in line with the emergence of evidence-based medicine and the implementation of increasingly rigorous controlled clinical trials. Lastly, the article explores the contributions of artificial intelligence, while also offering recommendations and discussing future perspectives for the development of new AEDs.

Quantum Similarity Testing with Convolutional Neural Networks

The task of testing whether two uncharacterized quantum devices behave in the same way is crucial for benchmarking near-term quantum computers and quantum simulators, but has so far remained open for continuous variable quantum systems. In this Letter, we develop a machine learning algorithm for comparing unknown continuous variable states using limited and noisy data. The algorithm works on non-Gaussian quantum states for which similarity testing could not be achieved with previous techniques. Our approach is based on a convolutional neural network that assesses the similarity of quantum states based on a lower-dimensional state representation built from measurement data. The network can be trained off-line with classically simulated data from a fiducial set of states sharing structural similarities with the states to be tested, with experimental data generated by measurements on the fiducial states, or with a combination of simulated and experimental data. We test the performance of the model on noisy cat states and states generated by arbitrary selective number-dependent phase gates. Our network can also be applied to the problem of comparing continuous variable states across different experimental platforms, with different sets of achievable measurements, and to the problem of experimentally testing whether two states are equivalent up to Gaussian unitary transformations.

A Perspective on Explanations of Molecular Prediction Models

Chemists can be skeptical in using deep learning (DL) in decision making, due to the lack of interpretability in "black-box" models. Explainable artificial intelligence (XAI) is a branch of artificial intelligence (AI) which addresses this drawback by providing tools to interpret DL models and their predictions. We review the principles of XAI in the domain of chemistry and emerging methods for creating and evaluating explanations. Then, we focus on methods developed by our group and their applications in predicting solubility, blood-brain barrier permeability, and the scent of molecules. We show that XAI methods like chemical counterfactuals and descriptor explanations can explain DL predictions while giving insight into structure-property relationships. Finally, we discuss how a two-step process of developing a black-box model and explaining predictions can uncover structure-property relationships.

Combining Fractional Derivatives and Machine Learning: A Review

Fractional calculus has gained a lot of attention in the last couple of years. Researchers have discovered that processes in various fields follow fractional dynamics rather than ordinary integer-ordered dynamics, meaning that the corresponding differential equations feature non-integer valued derivatives. There are several arguments for why this is the case, one of which is that fractional derivatives inherit spatiotemporal memory and/or the ability to express complex naturally occurring phenomena. Another popular topic nowadays is machine learning, i.e., learning behavior and patterns from historical data. In our ever-changing world with ever-increasing amounts of data, machine learning is a powerful tool for data analysis, problem-solving, modeling, and prediction. It has provided many further insights and discoveries in various scientific disciplines. As these two modern-day topics hold a lot of potential for combined approaches in terms of describing complex dynamics, this article review combines approaches from fractional derivatives and machine learning from the past, puts them into context, and thus provides a list of possible combined approaches and the corresponding techniques. Note, however, that this article does not deal with neural networks, as there is already extensive literature on neural networks and fractional calculus. We sorted past combined approaches from the literature into three categories, i.e., preprocessing, machine learning and fractional dynamics, and optimization. The contributions of fractional derivatives to machine learning are manifold as they provide powerful preprocessing and feature augmentation techniques, can improve physically informed machine learning, and are capable of improving hyperparameter optimization. Thus, this article serves to motivate researchers dealing with data-based problems, to be specific machine learning practitioners, to adopt new tools, and enhance their existing approaches.

Graph neural networks for materials science and chemistry

Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.