Digital discovery最新文献

{"title":"BoTier: multi-objective Bayesian optimization with tiered objective structures†","authors":"Mohammad Haddadnia, Leonie Grashoff and Felix Strieth-Kalthoff","doi":"10.1039/D5DD00039D","DOIUrl":"https://doi.org/10.1039/D5DD00039D","url":null,"abstract":"<p >Scientific optimization problems are usually concerned with balancing multiple competing objectives that express preferences over both the outcomes of an experiment (<em>e.g.</em> maximize reaction yield) and the corresponding input parameters (<em>e.g.</em> minimize the use of an expensive reagent). In practice, operational and economic considerations often establish a hierarchy of these objectives, which must be reflected in algorithms for sample-efficient experiment planning. Herein, we introduce <em>BoTier</em>, a software library that can flexibly represent a hierarchy of preferences over experiment outcomes and input parameters. We provide systematic benchmarks on synthetic and real-life surfaces, demonstrating the robust applicability of <em>BoTier</em> across a number of use cases. Importantly, <em>BoTier</em> is implemented in an auto-differentiable fashion, enabling seamless integration with the <em>BoTorch</em> library, thereby facilitating adoption by the scientific community.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1417-1422"},"PeriodicalIF":6.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00039d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of pretrained universal machine-learning interatomic potential for physicochemical simulation of liquid electrolytes in Li-ion batteries†","authors":"Suyeon Ju, Jinmu You, Gijin Kim, Yutack Park, Hyungmin An and Seungwu Han","doi":"10.1039/D5DD00025D","DOIUrl":"https://doi.org/10.1039/D5DD00025D","url":null,"abstract":"<p >Achieving higher operational voltages, faster charging, and broader temperature ranges for Li-ion batteries necessitates advancements in electrolyte engineering. However, the complexity of optimizing combinations of solvents, salts, and additives has limited the effectiveness of both experimental and computational screening methods for liquid electrolytes. Recently, pretrained universal machine-learning interatomic potentials (MLIPs) have emerged as promising tools for computational exploration of complex chemical spaces with high accuracy and efficiency. In this study, we evaluated the performance of the state-of-the-art equivariant pretrained MLIP, SevenNet-0, in predicting key properties of liquid electrolytes, including solvation behavior, density, and ion transport. To assess its suitability for extensive material screening, we considered a dataset comprising 20 solvents. Although SevenNet-0 was predominantly trained on inorganic compounds, its predictions for the properties of liquid electrolytes showed good agreement with experimental and <em>ab initio</em> data. However, systematic errors were identified, particularly in the predicted density of liquid electrolytes. To address this limitation, we fine-tuned SevenNet-0, achieving improved accuracy at a significantly reduced computational cost compared to developing bespoke models. Analysis of the training set suggested that the model achieved its accuracy by generalizing across the chemical space rather than memorizing trained configurations. This work highlights the potential of SevenNet-0 as a powerful tool for future engineering of liquid electrolyte systems.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1544-1559"},"PeriodicalIF":6.2,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00025d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Natural language processing for automated workflow and knowledge graph generation in self-driving labs†","authors":"Bastian Ruehle","doi":"10.1039/D5DD00063G","DOIUrl":"https://doi.org/10.1039/D5DD00063G","url":null,"abstract":"<p >Natural language processing with the help of large language models such as ChatGPT has become ubiquitous in many software applications and allows users to interact even with complex hardware or software in an intuitive way. The recent concepts of Self-Driving Labs and Material Acceleration Platforms stand to benefit greatly from making them more accessible to a broader scientific community through enhanced user-friendliness or even completely automated ways of generating experimental workflows that can be run on the complex hardware of the platform from user input or previously published procedures. Here, two new datasets with over 1.5 million experimental procedures and their (semi)automatic annotations as action graphs, <em>i.e.</em>, structured output, were created and used for training two different transformer-based large language models. These models strike a balance between performance, generality, and fitness for purpose and can be hosted and run on standard consumer-grade hardware. Furthermore, the generation of node graphs from these action graphs as a user-friendly and intuitive way of visualizing and modifying synthesis workflows that can be run on the hardware of a Self-Driving Lab or Material Acceleration Platform is explored. Lastly, it is discussed how knowledge graphs – following an ontology imposed by the underlying node setup and software architecture – can be generated from the node graphs. All resources, including the datasets, the fully trained large language models, the node editor, and scripts for querying and visualizing the knowledge graphs are made publicly available.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1534-1543"},"PeriodicalIF":6.2,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00063g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feature vectorization of microphase-separated structures in polymeric materials using dissipative particle dynamics and persistent homology for machine learning applications†","authors":"Yukito Higashi, Koji Okuwaki, Yuji Mochizuki, Tsuyohiko Fujigaya and Koichiro Kato","doi":"10.1039/D4DD00376D","DOIUrl":"https://doi.org/10.1039/D4DD00376D","url":null,"abstract":"<p >Recently, materials informatics (MI) has gained attention as an efficient approach for materials development. However, its application to polymers has been limited owing to the complexity and significance of the higher-order structures unique to these materials. This study focuses on microphase-separated structures, among the higher-order structures, as they influence many functional polymeric materials that support modern society. To implement MI that accounts for specific higher-order structures, such as microphase-separated structures, these structures must be quantified and converted into features. This approach addresses a gap in current materials informatics, in which traditional methods do not adequately account for the complex structures of polymers. Persistent homology (PH), a topological data analysis method, was used to extract features from the microphase-separated structures of polymeric materials. A coarse-grained simulation method known as dissipative particle dynamics (DPD) was used to generate the microphase-separated structures for PH analysis. The method was validated using electrolyte membranes for fuel cells, where microphase-separated structures are critical. Topological feature extraction was successfully performed on Nafion™ and its analogs, Aquivion® and Flemion™. Additionally, the correlation between the extracted features and proton conductivity was analyzed using unsupervised machine learning, which indicated that these features can be used to predict proton conductivity. The combination of DPD and PH can effectively convert microphase-separated structures into features. This method may be applicable to a wide range of polymeric materials influenced by microphase-separated structures, as it is not limited to proton exchange membranes or proton conductivity. This research marks a significant step toward advancing polymer informatics by incorporating the microphase-separated structures of polymers.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 1339-1351"},"PeriodicalIF":6.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00376d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143944075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing predictive models for solubility in multicomponent solvent systems using semi-supervised graph neural networks†","authors":"Hojin Jung, Christopher D. Stubbs, Sabari Kumar, Raúl Pérez-Soto, Su-min Song, Yeonjoon Kim and Seonah Kim","doi":"10.1039/D5DD00015G","DOIUrl":"https://doi.org/10.1039/D5DD00015G","url":null,"abstract":"<p >Solubility plays a critical role in guiding molecular design, reaction optimization, and product formulation across diverse chemical applications. Despite its importance, current approaches for measuring solubility face significant challenges, including time- and resource-intensive experiments and limited applicability to novel compounds. Computational prediction strategies, ranging from theoretical models to machine learning (ML) based methods, offer promising pathways to address these challenges. However, such methodologies need further improvement to achieve accurate predictions of solubilities in multicomponent solvent systems, as expanding the modeling approaches to multicomponent mixtures enables broader practical applications in chemistry. This study focuses on modeling solubility in multicomponent solvent systems, where data scarcity and model generalizability remain key hurdles. We curated a comprehensive experimental solubility dataset (MixSolDB) and examined two graph neural network (GNN) architectures – concatenation and subgraph – for improved predictive performance. By further integrating computationally derived COSMO-RS data <em>via</em> a teacher–student semi-supervised distillation (SSD) framework, we significantly expanded the chemical space and corrected previously high error margins. These results illustrate the feasibility of unifying experimental and computational data in a robust, flexible GNN-SSD pipeline, enabling greater coverage, improved accuracy, and enhanced applicability of solubility models for complex multicomponent solvent systems.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1492-1504"},"PeriodicalIF":6.2,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00015g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Classification of (dis)ordered structures as superionic lithium conductors with an experimental structure–conductivity database†","authors":"Daniel B. McHaffie, Zachery W. B. Iton, Jadon M. Bienz, Forrest A. L. Laskowski and Kimberly A. See","doi":"10.1039/D5DD00052A","DOIUrl":"https://doi.org/10.1039/D5DD00052A","url":null,"abstract":"<p >Solid-state electrolytes (SSEs) are critical for the development of high-performance all-solid-state batteries. Data-driven efforts to discover novel SSEs have been constrained by the absence of databases linking ionic conductivity with structure, as well as by challenges in encoding structural information for the disorder that is often found in superionic conductors. Here, we construct the largest database to date of experimentally measured ionic conductivity values paired with corresponding crystal structures, comprising 548 Li-containing compounds. Graph-based features, derived using a transfer learning framework, enable learning directly from disordered crystals, and AtomSets models leveraging these features outperform domain-specific features in a classification task. These models are employed to screen the Inorganic Crystal Structure Database (ICSD) and Materials Project for superionic Li-containing compounds. We identify 241 compounds with predicted superionic conductivity and band gaps greater than 1 eV. Experimental validation confirming superionic conductivity in one of these candidates, Li<small>₉</small>B<small>₁₉</small>S<small>₃₃</small>, demonstrates the utility of this approach for the discovery and development of advanced SSEs for all-solid-state batteries.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1518-1533"},"PeriodicalIF":6.2,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00052a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated structural analysis of small angle scattering data from common nanoparticles via machine learning","authors":"Graham Roberts, Mu-Ping Nieh, Anson W. K. Ma and Qian Yang","doi":"10.1039/D5DD00059A","DOIUrl":"https://doi.org/10.1039/D5DD00059A","url":null,"abstract":"<p >Billions of dollars have been invested in recent years to build up national scattering facilities around the world with more advanced configurations and faster data collection for small angle scattering (SAS), a technique that enables <em>in situ</em> structural analysis of nanoparticles (NP) under stringent sample environments. However, the interpretation of experimental SAS data is typically a slow process that requires significant domain expertise, leading to high-throughput scattering facilities such as synchrotron scattering centers collecting large quantities of data that may potentially be left unanalyzed. Here, we present a fast and data-efficient machine learning (ML) framework for identifying basic NP morphologies (spherical, cylindrical and discoidal geometries) and their corresponding structural parameters. The trained models take as input scattering curves with minimal pre-processing, and are able to identify morphology and structural dimensions from experimental curves with comparable accuracy to human experts. Critically, design choices that facilitate the practical application of ML models in scattering facilities are discussed, including ease of training, extrapolability outside of the parameter range of training data, and verifiability of predictions. The enhanced data analysis efficiency enabled by applying ML models to real-time <em>in situ</em> analysis of SAS data has the potential to revolutionize the utilization of synchrotron and neutron scattering facilities for probing nanostructures.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1467-1477"},"PeriodicalIF":6.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00059a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the transferability of machine-learning models for analyzing XRD data of shocked microstructures: from single crystal to polycrystals†","authors":"Daniel Vizoso, Phillip Tsurkan, Ke Ma, Avinash M. Dongare and Rémi Dingreville","doi":"10.1039/D4DD00400K","DOIUrl":"https://doi.org/10.1039/D4DD00400K","url":null,"abstract":"<p >This study explores the transferability of machine-learning models to analyze X-ray diffraction (XRD) profiles of shock-loaded single-crystal and polycrystalline data. Transferability in this context refers to the ability of these models to accurately predict microstructural descriptors for crystal orientations and structures not included in its training data. Supervised machine-learning models were trained on XRD profiles and microstructural descriptors from atomistic simulations to extract properties like pressure, temperature, phase fractions, and dislocation density. We assessed two aspects of transferability: (1) the ability of models trained on specific single crystal orientations to predict microstructural descriptors for other orientations, and (2) the capacity of models trained on single crystal data to analyze polycrystalline structures. Results show promising accuracy in predicting certain descriptors within the same orientation and improved transferability to new orientations and polycrystalline systems when trained on multiple orientations. However, the accuracy of these predictions depends on the microstructural descriptor being targeted and the specific crystal orientations included in the training dataset. This work highlights the potential and limitations of machine learning for analyzing XRD data of shock-loaded materials and emphasizes the need for diverse training data to enhance model transferability and robustness.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1457-1466"},"PeriodicalIF":6.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00400k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A self-driving fluidic lab for data-driven synthesis of lead-free perovskite nanocrystals†","authors":"Sina Sadeghi, Karl Mattsson, Joshua Glasheen, Victoria Lee, Christine Stark, Pragyan Jha, Nikolai Mukhin, Junbin Li, Arup Ghorai, Negin Orouji, Christopher H. J. Moran, Alireza Velayati, Jeffrey A. Bennett, Richard B. Canty, Kristofer G. Reyes and Milad Abolhasani","doi":"10.1039/D5DD00062A","DOIUrl":"https://doi.org/10.1039/D5DD00062A","url":null,"abstract":"<p >Copper (Cu)-based metal halide perovskite (MHP) nanocrystals (NCs) have recently gained attention as promising Pb-free and environmentally sustainable alternatives to traditional Pb-based MHPs, offering wide bandgaps, large Stokes shifts, and high emission stability. Despite these advantages, achieving high photoluminescence quantum yields (PLQYs) in Cu-based MHP NCs remains challenging, which impedes their widespread deployment in advanced optoelectronic and energy-related devices. Introducing a metal halide additive in the precursor chemistry can enhance the optical performance of Cu-based MHP NCs, but this approach substantially expands the experimental parameter space, rendering conventional batch-based, trial-and-error methods both time- and resource-intensive. Here, we present a self-driving fluidic lab (SDFL) that combines a modular microfluidic reactor, real-time <em>in situ</em> characterization, and machine-learning-guided decision-making to autonomously explore and optimize high-dimensional Cu-based MHP NC syntheses in the presence of a metal halide additive. Leveraging droplet-based flow chemistry and ensemble neural network-enabled Bayesian optimization, our SDFL rapidly navigates complex precursor formulations and reaction conditions of Cu-based MHP NCs, thus minimizing waste and accelerating discovery. We utilize the SDFL with three distinct precursor chemistries to synthesize Cs<small>₃</small>Cu<small>₂</small>I<small>₅</small> NCs, with zinc iodide (ZnI<small>₂</small>) serving as the metal halide additive. The high-fidelity data generated <em>in situ</em> allow for the creation of predictive digital twin models that yield mechanistic insights into additive-assisted NC formation. By iteratively refining synthesis parameters within the SDFL, we achieve Cs<small>₃</small>Cu<small>₂</small>I<small>₅</small> NCs with post-purification PLQYs of approximately 61%, marking a significant improvement over conventional Cu-based MHP NCs. The resulting high-performance, Pb-free NCs underscore the potential of sustainable materials acceleration platforms to speed-up the development of next-generation photonic and energy technologies.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1722-1733"},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00062a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large chemical language models for property prediction and high-throughput screening of ionic liquids†","authors":"Yuxin Qiu, Zhen Song, Guzhong Chen, Wenyao Chen, Long Chen, Kake Zhu, Zhiwen Qi, Xuezhi Duan and De Chen","doi":"10.1039/D5DD00035A","DOIUrl":"https://doi.org/10.1039/D5DD00035A","url":null,"abstract":"<p >Ionic liquids (ILs) possess unique physicochemical properties and exceptional tunability, making them versatile materials for a wide range of applications. However, their immense design flexibility also poses significant challenges in efficiently identifying outstanding ILs for specific tasks within the vast chemical space. In this study, we introduce ILBERT, a large-scale chemical language model designed to predict twelve key physicochemical and thermodynamic properties of ILs. By leveraging pre-training on over 31 million unlabeled IL-like molecules and employing data augmentation techniques, ILBERT achieves superior performance compared to existing machine learning methods across all twelve benchmark datasets. As a case study, we highlight ILBERT's ability to screen ILs as potential electrolytes from a database of 8 333 096 synthetically feasible ILs, demonstrating its reliability and computational efficiency. With its robust performance, ILBERT serves as a powerful tool for guiding the rational discovery of ILs, driving innovation in their practical applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1505-1517"},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00035a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}