Digital discovery最新文献

{"title":"Assessing data-driven predictions of band gap and electrical conductivity for transparent conducting materials†","authors":"Federico Ottomano, John Y. Goulermas, Vladimir Gusev, Rahul Savani, Michael W. Gaultois, Troy D. Manning, Hai Lin, Teresa Partida Manzanera, Emmeline G. Poole, Matthew S. Dyer, John B. Claridge, Jon Alaria, Luke M. Daniels, Su Varma, David Rimmer, Kevin Sanderson and Matthew J. Rosseinsky","doi":"10.1039/D5DD00010F","DOIUrl":"https://doi.org/10.1039/D5DD00010F","url":null,"abstract":"<p >Machine Learning (ML) has offered innovative perspectives for accelerating the discovery of new functional materials, leveraging the increasing availability of material databases. Despite the promising advances, data-driven methods face constraints imposed by the quantity and quality of available data. Moreover, ML is often employed in tandem with simulated datasets originating from density functional theory (DFT), and assessed through in-sample evaluation schemes. This scenario raises questions about the practical utility of ML in uncovering new and significant material classes for industrial applications. Here, we propose a data-driven framework aimed at accelerating the discovery of new <em>transparent conducting materials</em> (TCMs), an important category of semiconductors with a wide range of applications. To mitigate the shortage of available data, we create and validate unique experimental databases, comprising several examples of existing TCMs. We assess state-of-the-art (SOTA) ML models for property prediction from the stoichiometry alone. We propose a bespoke evaluation scheme to provide empirical evidence on the ability of ML to uncover new, previously unseen materials of interest. We test our approach on a list of 55 compositions containing typical elements of known TCMs. Although our study indicates that ML tends to identify new TCMs compositionally similar to those in the training data, we empirically demonstrate that it can highlight material candidates that may have been previously overlooked, offering a systematic approach to identify materials that are likely to display TCMs characteristics.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1794-1811"},"PeriodicalIF":6.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00010f?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589463","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":"Evaluating the performance and robustness of LLMs in materials science Q&A and property predictions†","authors":"Hongchen Wang, Kangming Li, Scott Ramsay, Yao Fehlis, Edward Kim and Jason Hattrick-Simpers","doi":"10.1039/D5DD00090D","DOIUrl":"https://doi.org/10.1039/D5DD00090D","url":null,"abstract":"<p >Large Language Models (LLMs) have the potential to revolutionize scientific research, yet their robustness and reliability in domain-specific applications remain insufficiently explored. In this study, we evaluate the performance and robustness of LLMs for materials science, focusing on domain-specific question answering and materials property prediction across diverse real-world and adversarial conditions. Three distinct datasets are used in this study: (1) a set of multiple-choice questions from undergraduate-level materials science courses, (2) a dataset including various steel compositions and yield strengths, and (3) a band gap dataset, containing textual descriptions of material crystal structures and band gap values. The performance of LLMs is assessed using various prompting strategies, including zero-shot chain-of-thought, expert prompting, and few-shot in-context learning. The robustness of these models is tested against various forms of “noise”, ranging from realistic disturbances to intentionally adversarial manipulations, to evaluate their resilience and reliability under real-world conditions. Additionally, the study showcases unique phenomena of LLMs during predictive tasks, such as mode collapse behavior when the proximity of prompt examples is altered and performance recovery from train/test mismatch. The findings aim to provide informed skepticism for the broad use of LLMs in materials science and to inspire advancements that enhance their robustness and reliability for practical applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1612-1624"},"PeriodicalIF":6.2,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00090d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264335","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":"Precursor reaction pathway leading to BiFeO3 formation: insights from text-mining and chemical reaction network analyses†","authors":"Viktoriia Baibakova, Kevin Cruse, Michael G. Taylor, Carolin M. Sutter-Fella, Gerbrand Ceder, Anubhav Jain and Samuel M. Blau","doi":"10.1039/D5DD00160A","DOIUrl":"https://doi.org/10.1039/D5DD00160A","url":null,"abstract":"<p >BiFeO<small>₃</small> (BFO) is a next-generation non-toxic multiferroic material with applications in sensors, memory devices, and spintronics, where its crystallinity and crystal structure directly influence its functional properties. Designing sol–gel syntheses that result in phase-pure BFO remains a challenge due to the complex interactions between metal complexes in the precursor solution. Here, we combine text-mined data and chemical reaction network (CRN) analysis to obtain novel insight into BFO sol–gel precursor chemistry. We perform text-mining analysis of 340 synthesis recipes with the emphasis on phase-pure BFO and identify trends in the use of precursor materials, including that nitrates are the preferred metal salts, 2-methoxyethanol (2 ME) is the dominant solvent, and adding citric acid as a chelating agent frequently leads to phase-pure BFO. Our CRN analysis reveals that the thermodynamically favored reaction mechanism between bismuth nitrate and 2ME interaction involves partial solvation followed by dimerization, contradicting assumptions in previous literature. We suggest that further oligomerization, facilitated by nitrite ion bridging, is critical for achieving the pure BFO phase.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1602-1611"},"PeriodicalIF":6.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00160a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264329","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 digital tool for liquid–liquid extraction process design†","authors":"George Karageorgis, Simone Tomasi, Elliot H. E. Farrar, Maxime Tarrago and Tabassum Malik","doi":"10.1039/D5DD00104H","DOIUrl":"https://doi.org/10.1039/D5DD00104H","url":null,"abstract":"<p >Aqueous liquid–liquid extractions are crucial for purifying compounds and removing impurities in the pharmaceutical industry. However, the extensive solvent space involved in such operations highlights the need for an informed approach in solvent selection. We present a digital tool designed to leverage data-driven experimentation to enhance process efficiency and sustainability, aligning with industry trends towards digitalisation. It allows users to input various parameters, retrieve relevant data, and visualise extraction efficiencies, thereby improving process understanding and reducing process development lead times. By providing interactive visualisations and facilitating rapid hypothesis generation, the tool supports informed decision-making and streamlines workflows. The tool's application is demonstrated through representative complex scenarios involving the separation of multiple compounds present in a mixture at the end of a Buchwald coupling reaction. Overall, this digital tool offers a new practical and data-led approach to chemical process design, with the potential to promote experimental efficiency during development and to improve the environmental sustainability of commercial processes.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1763-1771"},"PeriodicalIF":6.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00104h?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589460","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":"Nano Trees: nanopore signal processing and sublevel fitting using decision trees†","authors":"Deekshant Wadhwa, Philipp Mensing, James Harden, Paula Branco, Vincent Tabard-Cossa and Kyle Briggs","doi":"10.1039/D5DD00060B","DOIUrl":"https://doi.org/10.1039/D5DD00060B","url":null,"abstract":"<p >As the complexity of solid-state nanopore experiments increases, analysis of the resulting electrical signals to determine biomolecular details becomes a challenge. State of the art techniques for this task perform poorly when transient signal characteristics approach the bandwidth limitations of the measurement electronics. In this work, we address this challenge through an algorithm, called Nano Trees, for fitting piecewise constant functions. Nano Trees leverages machine learning algorithms to provide fits to the noisy piecewise constant data that is characteristic of nanopore ionic current signals, producing accurate fits on transients as short as twice the rise time of the measurement system. We demonstrate the performance of our algorithm on several real and synthetic datasets. These findings underscore the generalizability and accuracy of this approach in the regime of fast molecular translocations.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1743-1750"},"PeriodicalIF":6.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00060b?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589458","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":"Self-driving laboratories in Japan","authors":"Naruki Yoshikawa, Yuki Asano, Don N. Futaba, Kanako Harada, Taro Hitosugi, Genki N. Kanda, Shoichi Matsuda, Yuuya Nagata, Keisuke Nagato, Masanobu Naito, Tohru Natsume, Kazunori Nishio, Kanta Ono, Haruka Ozaki, Woosuck Shin, Junichiro Shiomi, Kunihiko Shizume, Koichi Takahashi, Seiji Takeda, Ichiro Takeuchi, Ryo Tamura, Koji Tsuda and Yoshitaka Ushiku","doi":"10.1039/D4DD00387J","DOIUrl":"https://doi.org/10.1039/D4DD00387J","url":null,"abstract":"<p >Self-driving laboratories (SDLs) are transforming the scientific discovery process worldwide by integrating automated experimentation with data-driven decision-making. Japan, known for its automation industry, is actively contributing to this field. This perspective introduces Japan's efforts in SDL development, including diverse applications across materials science, biology, chemistry, and software. In addition, it covers national funding programs, research communities, and Japanese industries supporting progress in this field. It also highlights the importance of education, standardization, and benchmarking for the future growth of SDL research.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1384-1403"},"PeriodicalIF":6.2,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00387j?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264298","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 noncollinear magnetic energy landscapes with Bayesian optimization","authors":"Jakob Baumsteiger, Lorenzo Celiberti, Patrick Rinke, Milica Todorović and Cesare Franchini","doi":"10.1039/D4DD00402G","DOIUrl":"https://doi.org/10.1039/D4DD00402G","url":null,"abstract":"<p >The investigation of magnetic energy landscapes and the search for ground states of magnetic materials using <em>ab initio</em> methods like density functional theory (DFT) is a challenging task. Complex interactions, such as superexchange and spin–orbit coupling, make these calculations computationally expensive and often lead to non-trivial energy landscapes. Consequently, a comprehensive and systematic investigation of large magnetic configuration spaces is often impractical. We approach this problem by utilizing Bayesian optimization, an active machine learning scheme that has proven to be efficient in modeling unknown functions and finding global minima. Using this approach we can obtain the magnetic contribution to the energy as a function of one or more spin canting angles with relatively small numbers of DFT calculations. To assess the capabilities and the efficiency of the approach we investigate the noncollinear magnetic energy landscapes of selected materials containing 3d, 5d and 5f magnetic ions: Ba<small>₃</small>MnNb<small>₂</small>O<small>₉</small>, LaMn<small>₂</small>Si<small>₂</small>, β-MnO<small>₂</small>, Sr<small>₂</small>IrO<small>₄</small>, UO<small>₂</small>, Ba<small>₂</small>NaOsO<small>₆</small> and kagome RhMn<small>₃</small>. By comparing our results to previous <em>ab initio</em> studies that followed more conventional approaches, we observe significant improvements in efficiency.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1639-1650"},"PeriodicalIF":6.2,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00402g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264337","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":"Reprogramming pretrained language models for protein sequence representation learning†","authors":"Ria Vinod, Pin-Yu Chen and Payel Das","doi":"10.1039/D4DD00195H","DOIUrl":"https://doi.org/10.1039/D4DD00195H","url":null,"abstract":"<p >Machine learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessibility of well-defined and labeled in-domain data. To tackle the low-data constraint, recent adaptions of deep learning models pretrained on millions of protein sequences have shown promise; however, the construction of such domain-specific large-scale models is computationally expensive. Herein, we propose representation reprogramming <em>via</em> dictionary learning (R2DL), an end-to-end representation learning framework in which we reprogram deep models for alternate-domain tasks that can perform well on protein property prediction with significantly fewer training samples. R2DL reprograms a pretrained English language model to learn the embeddings of protein sequences, by learning a sparse linear mapping between English and protein sequence vocabulary embeddings. Our model can attain better accuracy and significantly improve the data efficiency by up to 10<small>⁴</small> times over the baselines set by pretrained and standard supervised methods. To this end, we reprogram several recent state-of-the-art pretrained English language classification models (BERT, TinyBERT, T5, and roBERTa) and benchmark on a set of protein physicochemical prediction tasks (secondary structure, stability, homology, and solubility) as well as on a biomedically relevant set of protein function prediction tasks (antimicrobial, toxicity, antibody affinity, and protein–protein interaction).</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1591-1601"},"PeriodicalIF":6.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00195h?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264334","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":"Democratizing self-driving labs: advances in low-cost 3D printing for laboratory automation","authors":"Sayan Doloi, Maloy Das, Yujia Li, Zen Han Cho, Xingchi Xiao, John V. Hanna, Matthew Osvaldo and Leonard Ng Wei Tat","doi":"10.1039/D4DD00411F","DOIUrl":"https://doi.org/10.1039/D4DD00411F","url":null,"abstract":"<p >Laboratory automation through self-driving labs represents a transformative approach to accelerating scientific discovery, particularly in chemical sciences, biological sciences, materials science, and high-throughput experimentation. However, widespread adoption of these technologies faces a significant barrier: the prohibitive costs of commercial automation systems, which can range from tens to hundreds of thousands of dollars. This financial hurdle has created a technological divide, limiting access primarily to well-funded institutions and leaving many research facilities unable to leverage the benefits of automated experimentation. 3D printing technology emerges as a democratizing force in this landscape, offering a revolutionary solution to the accessibility challenge. By enabling the production of customizable laboratory equipment at a fraction of the cost of commercial alternatives, 3D printing is transforming how researchers approach laboratory automation. This approach not only reduces financial barriers but also promotes innovation through open-source designs, allowing researchers to share, modify, and improve upon existing solutions. This review addresses a critical gap in the current literature by exploring both the transformation of low-cost Fused Deposition Modelling (FDM) 3D printers into sophisticated automation platforms and the use of FDM 3D-printed components to develop a broad range of affordable laboratory automation systems. Furthermore, we explore how strategic modifications enable these systems to serve as automatic liquid handlers, robotic arms, automated sample preparation and detection systems, chemical reactionware, automated imaging systems and bioprinting units. The integration of these modified 3D-printed components with machine learning and artificial intelligence algorithms creates unprecedented opportunities for developing accessible, highly flexible self-driving laboratories.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1685-1721"},"PeriodicalIF":6.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00411f?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589451","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":"Machine learning-assisted profiling of a kinked ladder polymer structure using scattering†","authors":"Lijie Ding, Chi-Huan Tung, Zhiqiang Cao, Zekun Ye, Xiaodan Gu, Yan Xia, Wei-Ren Chen and Changwoo Do","doi":"10.1039/D5DD00051C","DOIUrl":"https://doi.org/10.1039/D5DD00051C","url":null,"abstract":"<p >Ladder polymers consisting of fused rings in the backbone have very limited conformational freedom, which results in very different properties from traditional linear polymers. However, accurately determining their size and chain conformations from solution scattering remains a challenge. Their chain conformations of kinked ladder polymers are largely governed by the structures and relative orientations or configurations of the repeat units, unlike conventional polymer chains whose bending angles between repeat units follow a unimodal Gaussian distribution. Meanwhile, traditional scattering models for polymer chains do not account for these unique structural features. This work introduces a novel approach that integrates machine learning with Monte Carlo simulations to construct a model that can describe the geometry of a type of kinked CANAL ladder polymers. We first develop a Monte Carlo simulation model for sampling the configuration space of CANAL ladder polymers, where each repeat unit is modeled as a biaxial segment. Then, we establish a machine learning-assisted scattering analysis framework based on Gaussian Process Regression. Finally, we conduct small-angle neutron scattering experiments on a CANAL ladder polymer solution to apply our approach. Our method uncovers structural features of such ladder polymers that conventional methods fail to capture.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1570-1577"},"PeriodicalIF":6.2,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00051c?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264328","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}