Machine learning for molecular and materials science

Clinical translation of nanomedicine with integrated digital medicine and machine learning interventions

Nanomaterials based therapeutics transform the ways of disease prevention, diagnosis and treatment with increasing sophistications in nanotechnology at a breakneck pace, but very few could reach to the clinic due to inconsistencies in preclinical studies followed by regulatory hinderances. To tackle this, integrating the nanomedicine discovery with digital medicine provide technologies as tools of specific biological activity measurement. Hence, overcome the redundancies in nanomedicine discovery by the on-site data acquisition and analytics through integrating intelligent sensors and artificial intelligence (AI) or machine learning (ML). Integrated AI/ML wearable sensors directly gather clinically relevant biochemical information from the subject's body and process data for physicians to make right clinical decision(s) in a time and cost-effective way. This review summarizes insights and recommend the infusion of actionable big data computation enabled sensors in burgeoning field of nanomedicine at academia, research institutes, and pharmaceutical industries, with a potential of clinical translation. Furthermore, many blind spots are present in modern clinically relevant computation, one of which could prevent ML-guided low-cost new nanomedicine development from being successfully translated into the clinic was also discussed.

Crystal Composition Transformer: Self-Learning Neural Language Model for Generative and Tinkering Design of Materials

Self-supervised neural language models have recently achieved unprecedented success from natural language processing to learning the languages of biological sequences and organic molecules. These models have demonstrated superior performance in the generation, structure classification, and functional predictions for proteins and molecules with learned representations. However, most of the masking-based pre-trained language models are not designed for generative design, and their black-box nature makes it difficult to interpret their design logic. Here a Blank-filling Language Model for Materials (BLMM) Crystal Transformer is proposed, a neural network-based probabilistic generative model for generative and tinkering design of inorganic materials. The model is built on the blank-filling language model for text generation and has demonstrated unique advantages in learning the "materials grammars" together with high-quality generation, interpretability, and data efficiency. It can generate chemically valid materials compositions with as high as 89.7% charge neutrality and 84.8% balanced electronegativity, which are more than four and eight times higher compared to a pseudo-random sampling baseline. The probabilistic generation process of BLMM allows it to recommend materials tinkering operations based on learned materials chemistry, which makes it useful for materials doping. The model is applied to discover a set of new materials as validated using the Density Functional Theory (DFT) calculations. This work thus brings the unsupervised transformer language models based generative artificial intelligence to inorganic materials. A user-friendly web app for tinkering materials design has been developed and can be accessed freely at www.materialsatlas.org/blmtinker.

Accelerated discovery of perovskite solid solutions through automated materials synthesis and characterization

Accelerating perovskite solid solution discovery and sustainable synthesis is crucial for addressing challenges in wireless communication and biosensors. However, the vast array of chemical compositions and their dependence on factors such as crystal structure, and sintering temperature require time-consuming manual processes. To overcome these constraints, we introduce an automated materials discovery approach encompassing machine learning (ML) assisted material screening, robotic synthesis, and high-throughput characterization. Our proposed platform for rapid sintering and dielectric analysis streamlines the characterization of perovskites and the discovery of disordered materials. The setup has been successfully validated, demonstrating processing materials within minutes, in stark contrast to conventional procedures that can take hours or days. Following setup validation with established samples, we showcase synthesizing single-phase solid solutions within the barium family, such as (BaxSr1-x)CeO3, identified through ML-guided chemistry.

Understanding the relationship between sequences and kinetics of DNA strand displacements

Precisely modulating the kinetics of toehold-mediated DNA strand displacements (TMSD) is essential for its application in DNA nanotechnology. The sequence in the toehold region significantly influences the kinetics of TMSD. However, due to the large sample space resulting from various arrangements of base sequences and the resulted complex secondary structures, such a correlation is not intuitive. Herein, machine learning was employed to reveal the relationship between the kinetics of TMSD and the toehold sequence as well as the correlated secondary structure of invader strands. Key factors that influence the rate constant of TMSD were identified, such as the number of free hydrogen bonding sites in the invader, the number of free bases in the toehold, and the number of hydrogen bonds in intermediates. Moreover, a predictive model was constructed, which successfully achieved semi-quantitative prediction of rate constants of TMSD even with subtle distinctions in toehold sequence.

Stochastic machine learning via sigma profiles to build a digital chemical space

This work establishes a different paradigm on digital molecular spaces and their efficient navigation by exploiting sigma profiles. To do so, the remarkable capability of Gaussian processes (GPs), a type of stochastic machine learning model, to correlate and predict physicochemical properties from sigma profiles is demonstrated, outperforming state-of-the-art neural networks previously published. The amount of chemical information encoded in sigma profiles eases the learning burden of machine learning models, permitting the training of GPs on small datasets which, due to their negligible computational cost and ease of implementation, are ideal models to be combined with optimization tools such as gradient search or Bayesian optimization (BO). Gradient search is used to efficiently navigate the sigma profile digital space, quickly converging to local extrema of target physicochemical properties. While this requires the availability of pretrained GP models on existing datasets, such limitations are eliminated with the implementation of BO, which can find global extrema with a limited number of iterations. A remarkable example of this is that of BO toward boiling temperature optimization. Holding no knowledge of chemistry except for the sigma profile and boiling temperature of carbon monoxide (the worst possible initial guess), BO finds the global maximum of the available boiling temperature dataset (over 1,000 molecules encompassing more than 40 families of organic and inorganic compounds) in just 15 iterations (i.e., 15 property measurements), cementing sigma profiles as a powerful digital chemical space for molecular optimization and discovery, particularly when little to no experimental data is initially available.

Minimizing Redundancy and Data Requirements of Machine Learning Potential: A Case Study in Interface Combustion

The machine learning potential has emerged as a promising approach for addressing the accuracy-versus-efficiency dilemma in molecular modeling. Efficiently exploring chemical spaces with high accuracy presents a significant challenge, particularly for the interface reaction system. This study introduces a workflow aimed at achieving this goal by incorporating the classical SOAP descriptor and practical PCA strategy to minimize redundancy and data requirements, while successfully capturing the features of complex potential energy surfaces. Specifically, the study focuses on interface combustion behaviors within promising alloy-based solid propellants. A neural network potential model tailored for modeling AlLi-AP interface reactions under varying conditions is constructed, showcasing excellent predictive capabilities in energy prediction, force estimation, and bond energies. A series of large-scale MD simulations reveal that Li doping significantly influences the initial combustion stage, enhancing reactivity and reducing thermal conductivity. Mass transfer analysis also highlights the considerably higher diffusion coefficient of Li compared to Al, with the former being three times greater. Consequently, the overall combustion process is accelerated by approximately 10%. These breakthroughs pave the way for virtual screening and the rational design of advanced propellant formulations and microstructures incorporating alloy-formula propellants.

Integrating Prior Chemical Knowledge into the Graph Transformer Network to Predict the Stability Constants of Chelating Agents and Metal Ions

The latest advancements in nuclear medicine indicate that radioactive isotopes and associated metal chelators play crucial roles in the diagnosis and treatment of diseases. The development of metal chelators mainly relies on traditional trial-and-error methods, lacking rational guidance and design. In this study, we propose the structure-aware transformer (SAT) combined with molecular fingerprint (SATCMF), a novel graph transformer network framework that incorporates prior chemical knowledge to construct coordination edges and learns the interactions between chelating agents and metal ions. SATCMF is trained on stability data collected from metal ion-ligand complexes, leveraging the SAT network to extract structural features relevant to the binding of ligands with metal ions. It further integrates molecular fingerprint features to refine the prediction of the stability constants of the chelating agents and metal ions. The experimental results on benchmark data set demonstrate that SATCMF achieves state-of-the-art performance based on four different graph neural network architectures. Additionally, visualizing the learned molecular attention distribution provides interpretable insights from the prediction results, offering valuable guidance for the development of novel metal chelators.

Discovery of Crystallizable Organic Semiconductors with Machine Learning

Crystalline organic semiconductors are known to have improved charge carrier mobility and exciton diffusion length in comparison to their amorphous counterparts. Certain organic molecular thin films can be transitioned from initially prepared amorphous layers to large-scale crystalline films via abrupt thermal annealing. Ideally, these films crystallize as platelets with long-range-ordered domains on the scale of tens to hundreds of microns. However, other organic molecular thin films may instead crystallize as spherulites or resist crystallization entirely. Organic molecules that have the capability of transforming into a platelet morphology feature both high melting point (Tm) and crystallization driving force (ΔGc). In this work, we employed machine learning (ML) to identify candidate organic materials with the potential to crystallize into platelets by estimating the aforementioned thermal properties. Six organic molecules identified by the ML algorithm were experimentally evaluated; three crystallized as platelets, one crystallized as a spherulite, and two resisted thin film crystallization. These results demonstrate a successful application of ML in the scope of predicting thermal properties of organic molecules and reinforce the principles of Tm and ΔGc as metrics that aid in predicting the crystallization behavior of organic thin films.

A Connected Convolutional Neutral Network Protocol for Design of Two-Dimensional Materials Based on Modified Graphdiyne

In materials science, doping plays a crucial role in manipulating the electronic properties of materials. Conventional screening via a trial-and-error strategy is challenging owing to the enormous chemical space. We proposed a connected convolutional neutral network (CCNN) for quick screening of boron nitrogen (B-N) codoped graphdiyne in terms of band gap. A paired-atomic localized matrix (PALM) descriptor was designed to describe the local chemical environment of materials with the matrix form adapted to a neutral network. An attribution analysis was conducted, and a quantitative relationship between structure and band gap is proposed, which reveals more significant influence of B-N doping at sp2 hybridized sites than at sp hybridized sites on broadening of the band gap of GDY. The accuracy and efficiency of the proposed approach implicate its potential in promoting the design of graphdiyne-based optoelectronic devices and catalysts with expected electronic properties, opening a new avenue for rational design of novel materials.

Physical Chemistry Education and Research in an Open-Sourced Future

Proficiency in physical chemistry requires a broad skill set. Successful trainees often receive mentoring from senior colleagues (research advisors, postdocs, etc.). Mentoring introduces trainees to experimental design, instrumental setup, and complex data interpretation. In lab settings, trainees typically learn by customizing experimental setups, and developing new ways of analyzing data. Learning alongside experts strengthens these fundamentals, and places a focus on the clear communication of research problems. However, this level of input is not scalable, nor can it easily be shared with all researchers or students, particularly those that face socioeconomic barriers to accessing mentoring. New approaches to training will therefore progress the field of physical chemistry. Technology is disrupting and democratising scientific education and research. The emergence of free online courses and video resources enables students to learn in a style that suits them. Higher degrees of automation remove cumbersome and sometimes arbitrary technical barriers to learning new techniques, allowing one to collect high quality data quickly. Open sourcing of data and analysis tools has increased transparency, lowered barriers to access, and accelerated scientific dissemination. However, these advances also can lead to "black box" approaches to acquiring and analyzing data, where convenience replaces understanding and errors and misrepresentations become more common. The risk is a breakdown in education: if one does not understand the fundamentals of a technique or analysis, it is difficult to correctly discern the practical limits of an experiment, distinguish signal from noise, troubleshoot problems, or take full advantage of powerful analytical procedures. Our vision of the future of physical chemistry is built around democratized learning, where deep technical and analytical expertise from physical chemists is made freely available. Advancements in technical education through expert-generated educational resources and AI-based tools will enrich physical chemistry education. A holistic approach to education will prepare the physical chemists of 2050 to adapt to rapidly advancing technological tools, which accelerate the pace of research. Technical education will be enhanced by accessible open-source instrumentation and analysis procedures, which will provide instruments and analysis scripts specifically designed for education. High quality, comparable data from standardized open-source instruments will feed into accessible databases and analysis projects, providing others the opportunity to store and analyze both failed and successful experiments. The coupling of open-source education, hardware, and analysis will democratize physical chemistry while addressing risks associated with "black box" approaches.

Stereoisomers Are Not Machine Learning's Best Friends

This study addresses the challenge of accurately identifying stereoisomers in cheminformatics, which originates from our objective to apply machine learning to predict the association constant between cyclodextrin and a guest. Identifying stereoisomers is indeed crucial for machine learning applications. Current tools offer various molecular descriptors, including their textual representation as Isomeric SMILES that can distinguish stereoisomers. However, such representation is text-based and does not have a fixed size, so a conversion is needed to make it usable to machine learning approaches. Word embedding techniques can be used to solve this problem. Mol2vec, a word embedding approach for molecules, offers such a conversion. Unfortunately, it cannot distinguish between stereoisomers due to its inability to capture the spatial configuration of molecular structures. This study proposes several approaches that use word embedding techniques to handle molecular discrimination using stereochemical information on molecules or considering Isomeric SMILES notation as a text in Natural Language Processing. Our aim is to generate a distinct vector for each unique molecule, correctly identifying stereoisomer information in cheminformatics. The proposed approaches are then compared to our original machine learning task: predicting the association constant between cyclodextrin and a guest molecule.

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction

Recent years have seen a surge of machine learning (ML) in chemistry for predicting chemical properties, but a low-cost, general-purpose, and high-performance model, desirable to be accessible on central processing unit (CPU) devices, remains not available. For this purpose, here we introduce an atomic attention mechanism into many-body function corrected neural network (MBNN), namely, MBNN-att ML model, to predict both the extensive and intensive properties of molecules and materials. The MBNN-att uses explicit function descriptors as the inputs for the atom-based feed-forward neural network (NN). The output of the NN is designed to be a vector to implement the multihead self-attention mechanism. This vector is split into two parts: the atomic attention weight part and the many-body-function part. The final property is obtained by summing the products of each atomic attention weight and the corresponding many-body function. We show that MBNN-att performs well on all QM9 properties, i.e., errors on all properties, below chemical accuracy, and, in particular, achieves the top performance for the energy-related extensive properties. By systematically comparing with other explicit-function-type descriptor ML models and the graph representation ML models, we demonstrate that the many-body-function framework and atomic attention mechanism are key ingredients for the high performance and the good transferability of MBNN-att in molecular property prediction.

Revolutionizing CAD/CAM-based restorative dental processes and materials with artificial intelligence: a concise narrative review

Artificial intelligence (AI) is increasingly prevalent in biomedical and industrial development, capturing the interest of dental professionals and patients. Its potential to improve the accuracy and speed of dental procedures is set to revolutionize dental care. The use of AI in computer-aided design/computer-aided manufacturing (CAD/CAM) within the restorative dental and material science fields offers numerous benefits, providing a new dimension to these practices. This study aims to provide a concise overview of the implementation of AI-powered technologies in CAD/CAM restorative dental procedures and materials. A comprehensive literature search was conducted using keywords from 2000 to 2023 to obtain pertinent information. This method was implemented to guarantee a thorough investigation of the subject matter. Keywords included; "Artificial Intelligence", "Machine Learning", "Neural Networks", "Virtual Reality", "Digital Dentistry", "CAD/CAM", and "Restorative Dentistry". Artificial intelligence in digital restorative dentistry has proven to be highly beneficial in various dental CAD/CAM applications. It helps in automating and incorporating esthetic factors, occlusal schemes, and previous practitioners' CAD choices in fabricating dental restorations. AI can also predict the debonding risk of CAD/CAM restorations and the compositional effects on the mechanical properties of its materials. Continuous enhancements are being made to overcome its limitations and open new possibilities for future developments in this field.

Application of artificial intelligence in cancer diagnosis and tumor nanomedicine

Cancer is a major health concern due to its high incidence and mortality rates. Advances in cancer research, particularly in artificial intelligence (AI) and deep learning, have shown significant progress. The swift evolution of AI in healthcare, especially in tools like computer-aided diagnosis, has the potential to revolutionize early cancer detection. This technology offers improved speed, accuracy, and sensitivity, bringing a transformative impact on cancer diagnosis, treatment, and management. This paper provides a concise overview of the application of artificial intelligence in the realms of medicine and nanomedicine, with a specific emphasis on the significance and challenges associated with cancer diagnosis. It explores the pivotal role of AI in cancer diagnosis, leveraging structured, unstructured, and multimodal fusion data. Additionally, the article delves into the applications of AI in nanomedicine sensors and nano-oncology drugs. The fundamentals of deep learning and convolutional neural networks are clarified, underscoring their relevance to AI-driven cancer diagnosis. A comparative analysis is presented, highlighting the accuracy and efficiency of traditional methods juxtaposed with AI-based approaches. The discussion not only assesses the current state of AI in cancer diagnosis but also delves into the challenges faced by AI in this context. Furthermore, the article envisions the future development direction and potential application of artificial intelligence in cancer diagnosis, offering a hopeful prospect for enhanced cancer detection and improved patient prognosis.

A Machine-Learning-Assisted Crystalline Structure Prediction Framework To Accelerate Materials Discovery

Modern crystal structure prediction methods based on structure generation algorithms and first-principles calculations play important roles in the design of new materials. However, the cost of these methods is very expensive because their success mostly relies on the efficient sampling of structures and the accurate evaluation of energies for those sampled structures. Herein, we develop a Machine-learning-Assisted CRYStalline Materials sAmpling sysTem (MAXMAT) aiming to accelerate the prediction of new crystal structures. For a given chemical composition, MAXMAT can generate efficient crystal structures with the help of a Python package for crystal structure generation (PyXtal) and can quickly evaluate the energies of these generated structures using a well-developed machine learning interaction potential model (M3GNET). We have used MAXMAT to perform crystal structure searches for three different chemical systems (TiO2, MgAl2O4, and BaBOF3) to test its accuracy and efficiency. Furthermore, we apply MAXMAT to predict new nonlinear optical materials, suggesting several thermodynamically synthesizable structures with high performance in LiZnGaS3 and CaBOF3 systems.

A general graph neural network based implicit solvation model for organic molecules in water

The dynamical behavior of small molecules in their environment can be studied with classical molecular dynamics (MD) simulations to gain deeper insight on an atomic level and thus complement and rationalize the interpretation of experimental findings. Such approaches are of great value in various areas of research, e.g., in the development of new therapeutics. The accurate description of solvation effects in such simulations is thereby key and has in consequence been an active field of research since the introduction of MD. So far, the most accurate approaches involve computationally expensive explicit solvent simulations, while widely applied models using an implicit solvent description suffer from reduced accuracy. Recently, machine learning (ML) approaches that provide a probabilistic representation of solvation effects have been proposed as potential alternatives. However, the associated computational costs and minimal or lack of transferability render them unusable in practice. Here, we report the first example of a transferable ML-based implicit solvent model trained on a diverse set of 3 000 000 molecular structures that can be applied to organic small molecules for simulations in water. Extensive testing against reference calculations demonstrated that the model delivers on par accuracy with explicit solvent simulations while providing an up to 18-fold increase in sampling rate.

Versatile Deep Learning Pipeline for Transferable Chemical Data Extraction

Chemical information disseminated in scientific documents offers an untapped potential for deep learning-assisted insights and breakthroughs. Automated extraction efforts have shifted from resource-intensive manual extraction toward applying machine learning methods to streamline chemical data extraction. While current extraction models and pipelines have ushered in notable efficiency improvements, they often exhibit modest performance, compromising the accuracy of predictive models trained on extracted data. Further, current chemical pipelines lack both transferability─where a model trained on one task can be adapted to another relevant task with limited examples─and extensibility, which enables seamless adaptability for new extraction tasks. Addressing these gaps, we present ChemREL, a versatile chemical data extraction pipeline emphasizing performance, transferability, and extensibility. ChemREL utilizes a custom, diverse data set of chemical documents, labeled through an active learning strategy to extract two properties: normal melting point and lethal dose 50 (LD50). The normal melting point is selected for its prevalence in diverse contexts and wider literature, serving as the foundation for pipeline training. In contrast, LD50 evaluates the pipeline's transferability to an unrelated property, underscoring variance in its biological nature, toxicological context, and units, among other differences. With pretraining and fine-tuning, our pipeline outperforms existing methods and GPT-4, achieving F1-scores of 96.1% for entity identification and 97.0% for relation mapping, culminating in an overall F1-score of 95.4%. More importantly, ChemREL displays high transferability, effectively transitioning from melting point extraction to LD50 extraction with 10 randomly selected training documents. Released as an open-source package, ChemREL aims to broaden access to chemical data extraction, enabling the construction of expansive relational data sets that propel discovery.

Quantum-level machine learning calculations of Levodopa

Many drug molecules contain functional groups, resulting in a torsional barrier corresponding to rotation around the bond linking the fragments. In medicinal chemistry and pharmaceutical sciences, inclusive of drug design studies, the exact calculation of the potential energy surface (PES) of these molecular torsions is extremely important and precious. Machine learning (ML), including deep learning (DL), is currently one of the most rapidly evolving tools in computer-aided drug discovery and molecular simulations. In this work, we used ANI-1x neural network potential as a quantum-level ML to predict the PESs of the L-3,4-dihydroxyphenylalanine (Levodopa) antiparkinsonian drug molecule. The electronic energies and structural parameters calculated by density functional theory (DFT) using the wB97X method and all possible Pople's basis sets indicated the 6-31G(d) basis set, when used with the wB97X functional, exhibits behavior similar to that of the ANI-1x model. The vibrational frequencies investigation showed a linear correlation between DFT and ML data. All ANI-1x calculations were completed quickly in a very short computing time. From this perspective, we expect the ANI-1x dataset applied in this work to be appreciably efficient and effective in computational structure-based drug design studies.

Active learning streamlines development of high performance catalysts for higher alcohol synthesis

Developing efficient catalysts for syngas-based higher alcohol synthesis (HAS) remains a formidable research challenge. The chain growth and CO insertion requirements demand multicomponent materials, whose complex reaction dynamics and extensive chemical space defy catalyst design norms. We present an alternative strategy by integrating active learning into experimental workflows, exemplified via the FeCoCuZr catalyst family. Our data-aided framework streamlines navigation of the extensive composition and reaction condition space in 86 experiments, offering >90% reduction in environmental footprint and costs over traditional programs. It identifies the Fe65Co19Cu5Zr11 catalyst with optimized reaction conditions to attain higher alcohol productivities of 1.1 gHA h-1 gcat-1 under stable operation for 150 h on stream, a 5-fold improvement over typically reported yields. Characterization reveals catalytic properties linked to superior activities despite moderate higher alcohol selectivities. To better reflect catalyst demands, we devise multi-objective optimization to maximize higher alcohol productivity while minimizing undesired CO2 and CH4 selectivities. An intrinsic trade-off between these metrics is uncovered, identifying Pareto-optimal catalysts not readily discernible by human experts. Finally, based on feature-importance analysis, we formulate data-informed guidelines to develop performance-specific FeCoCuZr systems. This approach goes beyond existing HAS catalyst design strategies, is adaptable to broader catalytic transformations, and fosters laboratory sustainability.

Performance Assessment of Universal Machine Learning Interatomic Potentials: Challenges and Directions for Materials' Surfaces

Machine learning interatomic potentials (MLIPs) are one of the main techniques in the materials science toolbox, able to bridge ab initio accuracy with the computational efficiency of classical force fields. This allows simulations ranging from atoms, molecules, and biosystems, to solid and bulk materials, surfaces, nanomaterials, and their interfaces and complex interactions. A recent class of advanced MLIPs, which use equivariant representations and deep graph neural networks, is known as universal models. These models are proposed as foundation models suitable for any system, covering most elements from the periodic table. Current universal MLIPs (UIPs) have been trained with the largest consistent data set available nowadays. However, these are composed mostly of bulk materials' DFT calculations. In this article, we assess the universality of all openly available UIPs, namely MACE, CHGNet, and M3GNet, in a representative task of generalization: calculation of surface energies. We find that the out-of-the-box foundation models have significant shortcomings in this task, with errors correlated to the total energy of surface simulations, having an out-of-domain distance from the training data set. Our results show that while UIPs are an efficient starting point for fine-tuning specialized models, we envision the potential of increasing the coverage of the materials space toward universal training data sets for MLIPs.

Addressing the Accuracy-Cost Trade-off in Material Property Prediction Using a Teacher-Student Strategy

Deep learning has catalyzed a transformative shift in material discovery, offering a key advantage over traditional experimental and theoretical methods by significantly reducing associated costs. Models adept at predicting properties from chemical compositions alone do not require structural information. However, this cost-efficient approach compromises model precision, particularly in Chemical Composition-based Property Prediction Models (CPMs), which are notably less accurate than Structure-based Property Prediction Models (SPMs). Addressing this challenge, our study introduces a novel Teacher-Student (TS) strategy, where a pretrained SPM serves as an instructive 'teacher' to enhance the CPM's precision. This TS strategy successfully harmonizes low-cost exploration with high accuracy, achieving a significant 47.1% reduction in relative error in scenarios involving 100 data entries. We also evaluate the effectiveness of the proposed strategy by employing perovskites as a case study. This method represents a significant advancement in the exploration and identification of valuable materials, leveraging CPM's potential while overcoming its precision limitations.

Biomimetic Mechanical Robust Cement-Resin Composites with Machine Learning-Assisted Gradient Hierarchical Structures

Biological materials relying on hierarchically ordered architectures inspire the emergence of advanced composites with mutually exclusive mechanical properties, but the efficient topology optimization and large-scale manufacturing remain challenging. Herein, this work proposes a scalable bottom-up approach to fabricate a novel nacre-like cement-resin composite with gradient brick-and-mortar (BM) structure, and demonstrates a machine learning-assisted method to optimize the gradient structure. The fabricated gradient composite exhibits an extraordinary combination of high flexural strength, toughness, and impact resistance. Particularly, the toughness and impact resistance of such composite attractively surpass the cement counterparts by factors of approximately 700 and 600 times, and even outperform natural rocks, fiber-reinforced cement-based materials and even some alloys. The strengthening and toughening mechanisms are clarified as the regional-matrix densifying and crack-tip shielding effects caused by the gradient BM structure. The developed gradient composite not only endows a promising structural material for protective applications in harsh scenarios, but also paves a new way for biomimetic metamaterials designing.

AI-assisted chemistry research: a comprehensive analysis of evolutionary paths and hotspots through knowledge graphs

Artificial intelligence (AI) offers transformative potential for chemical research through its ability to optimize reactions and processes, enhance energy efficiency, and reduce waste. AI-assisted chemical research (AI + chem) has become a global hotspot. To better understand the current research status of "AI + chem", this study conducted a scientific bibliometric investigation using CiteSpace. The web of science core collection was utilized to retrieve original articles related to "AI + chem" published from 2000 to 2024. The obtained data allowed for the visualization of the knowledge background, current research status, and latest knowledge structure of "AI + chem". The "AI + chem" has entered a stage of explosive growth, and the number of papers will maintain long-term high-speed growth. This article systematically analyzes the latest progress in "AI + chem" and objectively predicts future trends, including molecular design, reaction prediction, materials design, drug design, and quantum chemistry. The outcomes of this study will provide readers with a comprehensive understanding of the overall landscape of "AI + chem".

Subtraction Descriptors in Machine Learning for Optimizing the Cocatalyst Effect of Cobalt Phosphate on Hematite Photoanodes

In the quest for sustainable energy solutions, the optimization of the photoelectrochemical (PEC) performance of hematite photoanodes through cocatalysts represents a promising avenue. This study introduces a novel machine learning approach, leveraging subtraction descriptors, to isolate and quantify the specific effects of cobalt phosphate (Co-Pi) as a cocatalyst on hematite's PEC performance. By integrating data from various analytical techniques, including photoelectrochemical impedance spectroscopy and ultraviolet-visible spectroscopy, with advanced machine learning models, we successfully predicted the PEC performance enhancement attributed to Co-Pi. The Gaussian process regression (GPR) model emerged as the most effective, revealing the critical influence of the interfacial resistance, bulk resistance, and interfacial capacitance on the PEC performance. These findings underscore the potential of cocatalysts in improving charge separation and extending charge carrier lifetimes, thereby boosting the efficiency of photocatalytic reactions. This study not only advances our understanding of the cocatalyst effect in photocatalytic systems but also demonstrates the power of machine learning in modifying complex materials and guiding the development of optimized photocatalytic materials. The implications of this research extend beyond hematite photoanodes, offering a generalizable framework for enhancing the photoelectrochemical properties of a wide range of material modifications such as cocatalyst deposition, doping, and passivation.

Evaluating the Physicochemical Properties-Activity Relationship and Discovering New 1,2-Dihydropyridine Derivatives as Promising Inhibitors for PIM1-Kinase: Evidence from Principal Component Analysis, Molecular Docking, and Molecular Dynamics Studies

In this study, we evaluated the physicochemical properties related to the previously reported anticancer activity of a dataset comprising thirty 1,2-dihydropyridine derivatives. We utilized Principal Component Analysis (PCA) to identify the most significant influencing factors. The PCA analysis showed that the first two principal components accounted for 59.91% of the total variance, indicating a strong correlation between the molecules and specific descriptors. Among the 239 descriptors analyzed, 18 were positively correlated with anticancer activity, clustering with the 12 most active compounds based on their IC50 values. Six of these variables-LogP, Csp3, b_1rotN, LogS, TPSA, and lip_don-are related to drug-likeness potential. Thus, we then ranked the 12 compounds according to these six variables and excluded those violating the drug-likeness criteria, resulting in a shortlist of nine compounds. Next, we investigated the binding affinity of these nine shortlisted compounds with the use of molecular docking towards the PIM-1 Kinase enzyme (PDB: 2OBJ), which is overexpressed in various cancer cells. Compound 6 exhibited the best docking score among the docked compounds, with a docking score of -11.77 kcal/mol, compared to -12.08 kcal/mol for the reference PIM-1 kinase inhibitor, 6-(5-bromo-2-hydroxyphenyl)-2-oxo-4-phenyl-1,2-dihydropyridine-3-carbonitrile. To discover new PIM-1 kinase inhibitors, we designed nine novel compounds featuring hybrid structures of compound 6 and the reference inhibitor. Among these, compound 31 displayed the best binding affinity, with a docking score of -13.11 kcal/mol. Additionally, we performed PubChem database mining using the structure of compound 6 and the similarity search tool, identifying 16 structurally related compounds with various reported biological properties. Among these, compound 52 exhibited the best binding affinity, with a docking score of -13.03 kcal/mol. Finally, molecular dynamics (MD) studies were conducted to confirm the stability of the protein-ligand complexes obtained from docking the studied compounds to PIM-1 kinase, validating the potential of these compounds as PIM-1 kinase inhibitors.

Accelerating Formulation Design via Machine Learning: Generating a High-throughput Shampoo Formulations Dataset

Liquid formulations are ubiquitous yet have lengthy product development cycles owing to the complex physical interactions between ingredients making it difficult to tune formulations to customer-defined property targets. Interpolative ML models can accelerate liquid formulations design but are typically trained on limited sets of ingredients and without any structural information, which limits their out-of-training predictive capacity. To address this challenge, we selected eighteen formulation ingredients covering a diverse chemical space to prepare an open experimental dataset for training ML models for rinse-off formulations development. The resulting design space has an over 50-fold increase in dimensionality compared to our previous work. Here, we present a dataset of 812 formulations, including 294 stable samples, which cover the entire design space, with phase stability, turbidity, and high-fidelity rheology measurements generated on our semi-automated, ML-driven liquid formulations workflow. Our dataset has the unique attribute of sample-specific uncertainty measurements to train predictive surrogate models.

Metal-insulator-semiconductor photoelectrodes for enhanced photoelectrochemical water splitting

Photoelectrochemical (PEC) water splitting provides a scalable and integrated platform to harness renewable solar energy for green hydrogen production. The practical implementation of PEC systems hinges on addressing three critical challenges: enhancing energy conversion efficiency, ensuring long-term stability, and achieving economic viability. Metal-insulator-semiconductor (MIS) heterojunction photoelectrodes have gained significant attention over the last decade for their ability to efficiently segregate photogenerated carriers and mitigate corrosion-induced semiconductor degradation. This review discusses the structural composition and interfacial intricacies of MIS photoelectrodes tailored for PEC water splitting. The application of MIS heterostructures across various semiconductor light-absorbing layers, including traditional photovoltaic-grade semiconductors, metal oxides, and emerging materials, is presented first. Subsequently, this review elucidates the reaction mechanisms and respective merits of vacuum and non-vacuum deposition techniques in the fabrication of the insulator layers. In the context of the metal layers, this review extends beyond the conventional scope, not only by introducing metal-based cocatalysts, but also by exploring the latest advancements in molecular and single-atom catalysts integrated within MIS photoelectrodes. Furthermore, a systematic summary of carrier transfer mechanisms and interface design principles of MIS photoelectrodes is presented, which are pivotal for optimizing energy band alignment and enhancing solar-to-chemical conversion efficiency within the PEC system. Finally, this review explores innovative derivative configurations of MIS photoelectrodes, including back-illuminated MIS photoelectrodes, inverted MIS photoelectrodes, tandem MIS photoelectrodes, and monolithically integrated wireless MIS photoelectrodes. These novel architectures address the limitations of traditional MIS structures by effectively coupling different functional modules, minimizing optical and ohmic losses, and mitigating recombination losses.

Precise Capture and Dynamic Release of Circulating Liver Cancer Cells with Dual-Histidine-Based Cell Imprinted Hydrogels

Circulating tumor cells (CTCs) detection presents significant advantages in diagnosing liver cancer due to its noninvasiveness, real-time monitoring, and dynamic tracking. However, the clinical application of CTCs-based diagnosis is largely limited by the challenges of capturing low-abundance CTCs within a complex blood environment while ensuring them alive. Here, an ultrastrong ligand, l-histidine-l-histidine (HH), specifically targeting sialylated glycans on the surface of CTCs, is designed. Furthermore, HH is integrated into a cell-imprinted polymer, constructing a hydrogel with precise CTCs imprinting, high elasticity, satisfactory blood compatibility, and robust anti-interference capacities. These features endow the hydrogel with excellent capture efficiency (>95%) for CTCs in peripheral blood, as well as the ability to release CTCs controllably and alive. Clinical tests substantiate the accurate differentiation between liver cancer, cirrhosis, and healthy groups using this method. The remarkable diagnostic accuracy (94%), lossless release of CTCs, material reversibility, and cost-effectiveness ($6.68 per sample) make the HH-based hydrogel a potentially revolutionary technology for liver cancer diagnosis and single-cell analysis.

Data-driven, explainable machine learning model for predicting volatile organic compounds' standard vaporization enthalpy

The accurate prediction of standard vaporization enthalpy (ΔvapHm°) for volatile organic compounds (VOCs) is of paramount importance in environmental chemistry, industrial applications and regulatory compliance. To overcome traditional experimental methods for predicting ΔvapHm° of VOCs, machine learning (ML) models enable a high-throughput, cost-effective property estimation. But despite a rising momentum, existing ML algorithms still present limitations in prediction accuracy and broad chemical applications. In this work, we present a data driven, explainable supervised ML model to predict ΔvapHm° of VOCs. The model was built on an established experimental database of 2410 unique molecules and 223 VOCs categorized by chemical groups. Using supervised ML regression algorithms, the Random Forest successfully predicted VOCs' ΔvapHm° with a mean absolute error of 3.02 kJ mol-1 and a 95% test score. The model was successfully validated through the prediction of ΔvapHm° for a known database of VOCs and through molecular group hold-out tests. Through chemical feature importance analysis, this explainable model revealed that VOC polarizability, connectivity indexes and electrotopological state are key for the model's prediction accuracy. We thus present a replicable and explainable model, which can be further expanded towards the prediction of other thermodynamic properties of VOCs.

Response surface methodology and machine learning optimisations comparisons of recycled AA6061-B4C-ZrO2 hybrid metal matrix composites via hot forging forming process

The optimal conditions of applied factors to reuse Aluminium AA6061 scraps are (450, 500, and 550) ⁰C preheating temperature, (1-15) % Boron Carbide (B4C), and Zirconium (ZrO2) hybrid reinforced particles at 120 min forging time via Hot Forging (HF) process. The response surface methodology (RSM) and machine learning (ML) were established for the optimisations and comparisons towards materials strength structure. The Ultimate Tensile Strength (UTS) strength and Microhardness (MH) were significantly increased by increasing the processed temperature and reinforced particles because of the material dispersion strengthening. The high melting point of particles caused impedance movements of aluminium ceramics dislocations which need higher plastic deformation force and hence increased the material's mechanical and physical properties. But, beyond Al/10 % B4C + 10 % ZrO2 the strength and hardness were decreased due to more particle agglomeration distribution. The optimisation tools of both RSM and ML show high agreement between the reported results of applied parameters towards the materials' strength characterisation. The microstructure analysis of Field Emission Scanning Electron Microscopy (FE-SEM) and Atomic Force Microscope (AFM) provides insights mapping behavioural characterisation supports related to strength and hardness properties. The distribution of different volumes of ceramic particle proportion was highlighted. The environmental impacts were also analysed by employing a life cycle assessment (LCA) to identify energy savings because of its fewer processing steps and produce excellent hybrid materials properties.

Application of machine learning in the study of development, behavior, nerve, and genotoxicity of zebrafish

Machine learning (ML) as a novel model-based approach has been used in studying aquatic toxicology in the environmental field. Zebrafish, as an ideal model organism in aquatic toxicology research, has been widely used to study the toxic effects of various pollutants. However, toxicity testing on organisms may cause significant harm, consume considerable time and resources, and raise ethical concerns. Therefore, ML is used in related research to reduce animal experiments and assist researchers in conducting toxicological research. Although ML techniques have matured in various fields, research on ML-based aquatic toxicology is still in its infancy due to the lack of comprehensive large-scale toxicity databases for environmental pollutants and model organisms. Therefore, to better understand the recent research progress of ML in studying the development, behavior, nerve, and genotoxicity of zebrafish, this review mainly focuses on using ML modeling to assess and predict the toxic effects of zebrafish exposure to different toxic chemicals. Meanwhile, the opportunities and challenges faced by ML in the field of toxicology were analyzed. Finally, suggestions and perspectives were proposed for the toxicity studies of ML on zebrafish in future applications.

From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

Data scarcity is one of the critical bottlenecks to utilizing machine learning in material discovery. Transfer learning can use existing big data to assist property prediction on small data sets, but the premise is that there must be a strong correlation between large and small data sets. To extend its applicability in scenarios with different properties and materials, here we develop a hybrid framework combining adversarial transfer learning and expert knowledge, which enables the direct prediction of carrier mobility of two-dimensional (2D) materials using the knowledge learned from bulk effective mass. Specifically, adversarial training ensures that only common knowledge between bulk and 2D materials is extracted while expert knowledge is incorporated to further improve the prediction accuracy and generalizability. Successfully, 2D carrier mobilities are predicted with the accuracy over 90% from only crystal structure, and 21 2D semiconductors with carrier mobilities far exceeding silicon and suitable bandgap are successfully screened out. This work enables transfer learning in simultaneous cross-property and cross-material scenarios, providing an effective tool to predict intricate material properties with limited data.

Stretchable MXene/Carbon Nanotube Bilayer Strain Sensors with Tunable Sensitivity and Working Ranges

Stretchable strain sensors have gained increasing popularity as wearable devices to convert mechanical deformation of the human body into electrical signals. Two-dimensional transition metal carbides (Ti3C2Tx MXene) are promising candidates to achieve excellent sensitivity. However, MXene films have been limited in operating strain ranges due to rapid crack propagation during stretching. In this regard, this study reports MXene/carbon nanotube bilayer films with tunable sensitivity and working ranges. The device is fabricated using a scalable process involving spray deposition of well-dispersed nanomaterial inks. The bilayer sensor's high sensitivity is attributed to the cracks that form in the MXene film, while the compliant carbon nanotube layer extends the working range by maintaining conductive pathways. Moreover, the response of the sensor is easily controlled by tuning the MXene loading, achieving a gauge factor of 9039 within 15% strain at 1.92 mg/cm2 and a gauge factor of 1443 within 108% strain at 0.55 mg/cm2. These tailored properties can precisely match the operation requirements during the wearable application, providing accurate monitoring of various body movements and physiological activities. Additionally, a smart glove with multiple integrated strain sensors is demonstrated as a human-machine interface for the real-time recognition of hand gestures based on a machine-learning algorithm. The design strategy presented here provides a convenient avenue to modulate strain sensors for targeted applications.

t-SMILES: a fragment-based molecular representation framework for de novo ligand design

Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models. This study introduces a flexible, fragment-based, multiscale molecular representation framework called t-SMILES (tree-based SMILES) with three code algorithms: TSSA (t-SMILES with shared atom), TSDY (t-SMILES with dummy atom but without ID) and TSID (t-SMILES with ID and dummy atom). It describes molecules using SMILES-type strings obtained by performing a breadth-first search on a full binary tree formed from a fragmented molecular graph. Systematic evaluations using JTVAE, BRICS, MMPA, and Scaffold show the feasibility of constructing a multi-code molecular description system, where various descriptions complement each other, enhancing the overall performance. In addition, it can avoid overfitting and achieve higher novelty scores while maintaining reasonable similarity on labeled low-resource datasets, regardless of whether the model is original, data-augmented, or pre-trained then fine-tuned. Furthermore, it significantly outperforms classical SMILES, DeepSMILES, SELFIES and baseline models in goal-directed tasks. And it surpasses state-of-the-art fragment, graph and SMILES based approaches on ChEMBL, Zinc, and QM9.

Advancing precision rheumatology: applications of machine learning for rheumatoid arthritis management

Rheumatoid arthritis (RA) is an autoimmune disease causing progressive joint damage. Early diagnosis and treatment is critical, but remains challenging due to RA complexity and heterogeneity. Machine learning (ML) techniques may enhance RA management by identifying patterns within multidimensional biomedical data to improve classification, diagnosis, and treatment predictions. In this review, we summarize the applications of ML for RA management. Emerging studies or applications have developed diagnostic and predictive models for RA that utilize a variety of data modalities, including electronic health records, imaging, and multi-omics data. High-performance supervised learning models have demonstrated an Area Under the Curve (AUC) exceeding 0.85, which is used for identifying RA patients and predicting treatment responses. Unsupervised learning has revealed potential RA subtypes. Ongoing research is integrating multimodal data with deep learning to further improve performance. However, key challenges remain regarding model overfitting, generalizability, validation in clinical settings, and interpretability. Small sample sizes and lack of diverse population testing risks overestimating model performance. Prospective studies evaluating real-world clinical utility are lacking. Enhancing model interpretability is critical for clinician acceptance. In summary, while ML shows promise for transforming RA management through earlier diagnosis and optimized treatment, larger scale multisite data, prospective clinical validation of interpretable models, and testing across diverse populations is still needed. As these gaps are addressed, ML may pave the way towards precision medicine in RA.

Application of machine learning techniques in population pharmacokinetics/pharmacodynamics modeling

Population pharmacokinetics/pharmacodynamics (pop-PK/PD) consolidates pharmacokinetic and pharmacodynamic data from many subjects to understand inter- and intra-individual variability due to patient backgrounds, including disease state and genetics. The typical workflow in pop-PK/PD analysis involves the determination of the structure model, selection of the error model, analysis based on the base model, covariate modeling, and validation of the final model. Machine learning is gaining considerable attention in the medical and various fields because, in contrast to traditional modeling, which often assumes linear or predefined relationships, machine learning modeling learns directly from data and accommodates complex patterns. Machine learning has demonstrated excellent capabilities for prescreening covariates and developing predictive models. This review introduces various applications of machine learning techniques in pop-PK/PD research.

Machine intelligence accelerated design of conductive MXene aerogels with programmable properties

Designing ultralight conductive aerogels with tailored electrical and mechanical properties is critical for various applications. Conventional approaches rely on iterative, time-consuming experiments across a vast parameter space. Herein, an integrated workflow is developed to combine collaborative robotics with machine learning to accelerate the design of conductive aerogels with programmable properties. An automated pipetting robot is operated to prepare 264 mixtures of Ti3C2Tx MXene, cellulose, gelatin, and glutaraldehyde at different ratios/loadings. After freeze-drying, the aerogels' structural integrity is evaluated to train a support vector machine classifier. Through 8 active learning cycles with data augmentation, 162 unique conductive aerogels are fabricated/characterized via robotics-automated platforms, enabling the construction of an artificial neural network prediction model. The prediction model conducts two-way design tasks: (1) predicting the aerogels' physicochemical properties from fabrication parameters and (2) automating the inverse design of aerogels for specific property requirements. The combined use of model interpretation and finite element simulations validates a pronounced correlation between aerogel density and compressive strength. The model-suggested aerogels with high conductivity, customized strength, and pressure insensitivity allow for compression-stable Joule heating for wearable thermal management.

Advances of LiCoO2 in Cathode of Aqueous Lithium-Ion Batteries

Aqueous lithium-ion batteries offer promising advantages such as low cost, enhanced safety, high rate capability, and the ability to deliver considerable capacity at 1.8 V, making them ideal candidates for large-scale reserve power sources for renewable energy. However, the practical application of aqueous lithium-ion batteries has been hindered by the poor cycle stability of layered cathode materials, including LiCoO2, in neutral aqueous electrolytes. This review examines the working principles, material limitations, and research progress of aqueous lithium-ion batteries. The types and characteristics of materials used in the cathode of aqueous lithium-ion batteries are summarized, with a primary focus on the attenuation mechanisms of LiCoO2 when used as the cathode material in aqueous electrolytes. Furthermore, this review explores the advancements in utilizing LiCoO2 in the cathode of aqueous lithium-ion batteries, as well as the combination with machine learning. By addressing these critical aspects, this review aims to provide a comprehensive understanding of aqueous lithium-ion batteries and shed light on future development and application prospects.

Perspectives Toward Damage-Tolerant Nanostructure Ceramics

Advanced ceramic materials and devices call for better reliability and damage tolerance. In addition to their strong bonding nature, there are examples demonstrating superior mechanical properties of nanostructure ceramics, such as damage-tolerant ceramic aerogels that can withstand high deformation without cracking and local plasticity in dense nanocrystalline ceramics. The recent progresses shall be reviewed in this perspective article. Three topics including highly elastic nano-fibrous ceramic aerogels, load-bearing nanoceramics with improved mechanical properties, and implementing machine learning-assisted simulations toolbox in understanding the relationship among structure, deformation mechanisms, and microstructure-properties shall be discussed. It is hoped that the perspectives present here can help the discovery, synthesis, and processing of future structural ceramic materials that are insensitive to processing flaws and local damages in service.

Selective recognition between aromatics and aliphatics by cage-shaped borates supported by a machine learning approach

Selective recognition between hydrocarbon moieties is a longstanding issue. Although we developed a π-pocket Lewis acid catalyst with high selectivity for aromatic aldehydes over aliphatic ones, a general strategy for catalyst design remains elusive. As an approach that transfers the molecular recognition based on multiple cooperative non-covalent interactions within the π-pocket to a rational catalyst design, herein, we demonstrate Lewis acid catalysts showing improved selectivity through the support of an ensemble algorithm with random forest, Ada Boost, and XG Boost as a machine learning (ML) approach. Using 7963 explanatory variables extracted from model hetero-Diels-Alder reactions, the ensemble algorithm predicted the chemoselectivity of unlearned catalysts. Experiments confirmed the prediction. The proposed catalyst shows the highest selective recognition, reminiscing enzymatic catalytic activity. Additionally, a SHapley Additive exPlanations (SHAP) method suggested that the selectivity originates from the polarizability and three-dimensional size of the catalyst. This insight leads to rational design guidelines for Lewis acid catalysts with dispersion forces.

Experiment-Driven Atomistic Materials Modeling: A Case Study Combining X-Ray Photoelectron Spectroscopy and Machine Learning Potentials to Infer the Structure of Oxygen-Rich Amorphous Carbon

An important yet challenging aspect of atomistic materials modeling is reconciling experimental and computational results. Conventional approaches involve generating numerous configurations through molecular dynamics or Monte Carlo structure optimization and selecting the one with the closest match to experiment. However, this inefficient process is not guaranteed to succeed. We introduce a general method to combine atomistic machine learning (ML) with experimental observables that produces atomistic structures compatible with experiment by design. We use this approach in combination with grand-canonical Monte Carlo within a modified Hamiltonian formalism, to generate configurations that agree with experimental data and are chemically sound (low in energy). We apply our approach to understand the atomistic structure of oxygenated amorphous carbon (a-COx), an intriguing carbon-based material, to answer the question of how much oxygen can be added to carbon before it fully decomposes into CO and CO2. Utilizing an ML-based X-ray photoelectron spectroscopy (XPS) model trained from GW and density functional theory (DFT) data, in conjunction with an ML interatomic potential, we identify a-COx structures compliant with experimental XPS predictions that are also energetically favorable with respect to DFT. Employing a network analysis, we accurately deconvolve the XPS spectrum into motif contributions, both revealing the inaccuracies inherent to experimental XPS interpretation and granting us atomistic insight into the structure of a-COx. This method generalizes to multiple experimental observables and allows for the elucidation of the atomistic structure of materials directly from experimental data, thereby enabling experiment-driven materials modeling with a degree of realism previously out of reach.

Providing a Photovoltaic Performance Enhancement Relationship from Binary to Ternary Polymer Solar Cells via Machine Learning

Ternary polymer solar cells (PSCs) are currently the simplest and most efficient way to further improve the device performance in PSCs. To find high-performance organic photovoltaic materials, the established connection between the material structure and device performance before fabrication is of great significance. Herein, firstly, a database of the photovoltaic performance in 874 experimental PSCs reported in the literature is established, and three different fingerprint expressions of a molecular structure are explored as input features; the results show that long fingerprints of 2D atom pairs can contain more effective information and improve the accuracy of the models. Through supervised learning, five machine learning (ML) models were trained to build a mapping of the photovoltaic performance improvement relationship from binary to ternary PSCs. The GBDT model had the best predictive ability and generalization. Eighteen key structural features from a non-fullerene acceptor and the third components that affect the device's PCE were screened based on this model, including a nitrile group with lone-pair electron, a halogen atom, an oxygen atom, etc. Interestingly, the structural features for the enhanced device's PCE were essentially increased by the Jsc or FF. More importantly, the reliability of the ML model was further verified by preparing the highly efficient PSCs. Taking the PM6:BTP-eC9:PY-IT ternary PSC as an example, the PCE prediction (18.03%) by the model was in good agreement with the experimental results (17.78%), the relative prediction error was 1.41%, and the relative error between all experimental results and predicted results was less than 5%. These results indicate that ML is a useful tool for exploring the photovoltaic performance improvement of PSCs and accelerating the design and application with highly efficient non-fullerene materials.

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.

Hydrogen Embrittlement as a Conspicuous Material Challenge─Comprehensive Review and Future Directions

Hydrogen is considered a clean and efficient energy carrier crucial for shaping the net-zero future. Large-scale production, transportation, storage, and use of green hydrogen are expected to be undertaken in the coming decades. As the smallest element in the universe, however, hydrogen can adsorb on, diffuse into, and interact with many metallic materials, degrading their mechanical properties. This multifaceted phenomenon is generically categorized as hydrogen embrittlement (HE). HE is one of the most complex material problems that arises as an outcome of the intricate interplay across specific spatial and temporal scales between the mechanical driving force and the material resistance fingerprinted by the microstructures and subsequently weakened by the presence of hydrogen. Based on recent developments in the field as well as our collective understanding, this Review is devoted to treating HE as a whole and providing a constructive and systematic discussion on hydrogen entry, diffusion, trapping, hydrogen-microstructure interaction mechanisms, and consequences of HE in steels, nickel alloys, and aluminum alloys used for energy transport and storage. HE in emerging material systems, such as high entropy alloys and additively manufactured materials, is also discussed. Priority has been particularly given to these less understood aspects. Combining perspectives of materials chemistry, materials science, mechanics, and artificial intelligence, this Review aspires to present a comprehensive and impartial viewpoint on the existing knowledge and conclude with our forecasts of various paths forward meant to fuel the exploration of future research regarding hydrogen-induced material challenges.

Multivariate Bayesian Optimization of CoO Nanoparticles for CO2 Hydrogenation Catalysis

The hydrogenation of CO2 holds promise for transforming the production of renewable fuels and chemicals. However, the challenge lies in developing robust and selective catalysts for this process. Transition metal oxide catalysts, particularly cobalt oxide, have shown potential for CO2 hydrogenation, with performance heavily reliant on crystal phase and morphology. Achieving precise control over these catalyst attributes through colloidal nanoparticle synthesis could pave the way for catalyst and process advancement. Yet, navigating the complexities of colloidal nanoparticle syntheses, governed by numerous input variables, poses a significant challenge in systematically controlling resultant catalyst features. We present a multivariate Bayesian optimization, coupled with a data-driven classifier, to map the synthetic design space for colloidal CoO nanoparticles and simultaneously optimize them for multiple catalytically relevant features within a target crystalline phase. The optimized experimental conditions yielded small, phase-pure rock salt CoO nanoparticles of uniform size and shape. These optimized nanoparticles were then supported on SiO2 and assessed for thermocatalytic CO2 hydrogenation against larger, polydisperse CoO nanoparticles on SiO2 and a conventionally prepared catalyst. The optimized CoO/SiO2 catalyst consistently exhibited higher activity and CH4 selectivity (ca. 98%) across various pretreatment reduction temperatures as compared to the other catalysts. This remarkable performance was attributed to particle stability and consistent H* surface coverage, even after undergoing the highest temperature reduction, achieving a more stable catalytic species that resists sintering and carbon occlusion.

Experimentally validated inverse design of multi-property Fe-Co-Ni alloys

This study presents a machine learning (ML) framework aimed at accelerating the discovery of multi-property optimized Fe-Ni-Co alloys, addressing the time-consuming, expensive, and inefficient nature of traditional methods of material discovery, development, and deployment. We compiled a detailed heterogeneous database of the magnetic, electrical, and mechanical properties of Fe-Co-Ni alloys, employing a novel ML-based imputation strategy to address gaps in property data. Leveraging this comprehensive database, we developed predictive ML models using tree-based and neural network approaches for optimizing multiple properties simultaneously. An inverse design strategy, utilizing multi-objective Bayesian optimization (MOBO), enabled the identification of promising alloy compositions. This approach was experimentally validated using high-throughput methodology, highlighting alloys such as Fe66.8Co28Ni5.2 and Fe61.9Co22.8Ni15.3, which demonstrated superior properties. The predicted properties data closely matched experimental data within 14% accuracy. Our approach can be extended to a broad range of materials systems to predict novel materials with an optimized set of properties.

Accelerating reliable multiscale quantum refinement of protein-drug systems enabled by machine learning

Biomacromolecule structures are essential for drug development and biocatalysis. Quantum refinement (QR) methods, which employ reliable quantum mechanics (QM) methods in crystallographic refinement, showed promise in improving the structural quality or even correcting the structure of biomacromolecules. However, vast computational costs and complex quantum mechanics/molecular mechanics (QM/MM) setups limit QR applications. Here we incorporate robust machine learning potentials (MLPs) in multiscale ONIOM(QM:MM) schemes to describe the core parts (e.g., drugs/inhibitors), replacing the expensive QM method. Additionally, two levels of MLPs are combined for the first time to overcome MLP limitations. Our unique MLPs+ONIOM-based QR methods achieve QM-level accuracy with significantly higher efficiency. Furthermore, our refinements provide computational evidence for the existence of bonded and nonbonded forms of the Food and Drug Administration (FDA)-approved drug nirmatrelvir in one SARS-CoV-2 main protease structure. This study highlights that powerful MLPs accelerate QRs for reliable protein-drug complexes, promote broader QR applications and provide more atomistic insights into drug development.

Rapid quantitative analysis of petroleum coke properties by laser-induced breakdown spectroscopy combined with random forest based on a variable selection strategy

Driven by the "double carbon" strategy, petroleum coke short-term demand is growing rapidly as a negative electrode material for artificial graphite. The analysis of petroleum coke physicochemical properties has always been an important part of its research, encompassing significant indicators such as ash content, volatile matter and calorific value. A strategy based on laser-induced breakdown spectroscopy (LIBS) in combination with chemometrics is proposed to realize the rapid and accurate quantification of the above properties. LIBS spectra of 46 petroleum coke samples were collected, and an original random forest (RF) calibration model was constructed by optimizing the pretreatment parameters. The RF calibration model was further optimized based on variable importance measures (VIM) and variable importance in projection (VIP) methods. After variable selection, the elemental spectral lines related to ash content, volatile matter and calorific value modeling were screened out, thus initially exploring the correlation between these properties and elements. Under the optimized spectral pretreatment method, VI threshold and model parameters, the mean relative error (MREP) of the prediction set of ash content, volatile matter and calorific value were 0.0881, 0.0527 and 0.006, the root mean square error (RMSEP) of the prediction set of ash content, volatile matter and calorific value were 0.0471%, 0.6178% and 0.2697 MJ kg-1, respectively, and the determination coefficient (RP2) of the prediction set was 0.9187, 0.9820 and 0.9510, respectively. The combination of LIBS technology and chemometric methods can provide powerful technical means for the analysis and evaluation of the physicochemical properties of petroleum coke.

Deep learning and big data mining for Metal-Organic frameworks with high performance for simultaneous desulfurization and carbon capture

Carbon capture and desulfurization of flue gases are crucial for the achievement of carbon neutrality and sustainable development. In this work, the "one-step" adsorption technology with high-performance metal-organic frameworks (MOFs) was proposed to simultaneously capture the SO2 and CO2. Four machine learning algorithms were used to predict the performance indicators (NCO2+SO2, SCO2+SO2/N2, and TSN) of MOFs, with Multi-Layer Perceptron Regression (MLPR) showing better performance (R2 = 0.93). To address sparse data of MOF chemical descriptors, we introduced the Deep Factorization Machines (DeepFM) model, outperforming MLPR with a higher R2 of 0.95. Then, sensitivity analysis was employed to find that the adsorption heat and porosity were the key factors for SO2 and CO2 capture performance of MOF, while the influence of open alkali metal sites also stood out. Furthermore, we established a kinetic model to batch simulate the breakthrough curves of TOP 1000 MOFs to investigate their dynamic adsorption separation performance for SO2/CO2/N2. The TOP 20 MOFs screened by the dynamic performance highly overlap with those screened by the static performance, with 76 % containing open alkali metal sites. This integrated approach of computational screening, machine learning, and dynamic analysis significantly advances the development of efficient MOF adsorbents for flue gas treatment.