Digital discovery最新文献

{"title":"Operator-free HPLC automated method development guided by Bayesian optimization†","authors":"Thomas M. Dixon, Jeanine Williams, Maximilian Besenhard, Roger M. Howard, James MacGregor, Philip Peach, Adam D. Clayton, Nicholas J. Warren and Richard A. Bourne","doi":"10.1039/D4DD00062E","DOIUrl":"10.1039/D4DD00062E","url":null,"abstract":"<p >The need to efficiently develop high performance liquid chromatography (HPLC) methods, whilst adhering to quality by design principles is of paramount importance when it comes to impurity detection in the synthesis of active pharmaceutical ingredients. This study highlights a novel approach that fully automates HPLC method development using black-box single and multi-objective Bayesian optimization algorithms. Three continuous variables including the initial isocratic hold time, initial organic modifier concentration and the gradient time were adjusted to simultaneously optimize the number of peaks detected, the resolution between peaks and the method length. Two mixtures of analytes, one with seven compounds and one with eleven compounds, were investigated. The system explored the design space to find a global optimum in chromatogram quality without human assistance, and methods that gave baseline resolution were identified. Optimal operating conditions were typically reached within just 13 experiments. The single and multi-objective Bayesian optimization algorithms were compared to show that multi-objective optimization was more suitable for HPLC method development. This allowed for multiple chromatogram acceptance criteria to be selected without having to repeat the entire optimization, making it a useful tool for robustness testing. Work in this paper presents a fully “operator-free” and closed loop HPLC method optimization process that can find optimal methods quickly when compared to other modern HPLC optimization techniques such as design of experiments, linear solvent strength models or quantitative structure retention relationships.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1591-1601"},"PeriodicalIF":6.2,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00062e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141524882","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":"High throughput methodology for investigating green hydrogen generating processes using colorimetric detection films and machine vision†","authors":"Savannah Talledo, Andrew Kubaney, Mitchell A. Baumer, Keegan Pietrak and Stefan Bernhard","doi":"10.1039/D4DD00070F","DOIUrl":"10.1039/D4DD00070F","url":null,"abstract":"<p >The generation of hydrogen from abundant and renewable precursors driven by sunlight will be a cornerstone of a future, sustainable hydrogen infrastructure. Current methods to monitor the evolution of hydrogen in such photocatalytic systems such as gas chromatography, mass spectrometry, manometry or Raman spectroscopy are either expensive and low throughput or lack sensitivity and selectivity over other gasses. These impediments hinder the generation of photo-driven hydrogen evolution data necessary for machine learning and artificial intelligence-based protocols. This work presents an open-source approach for studying solar-driven hydrogen evolution reactions (HERs) in parallel that uses colorimetric hydrogen detection films in tandem with an image analysis software capable of providing metrics such as hydrogen amount, hydrogen evolution rates, incubation times, and plateau times. The sensing medium is composed of 0.05% (w/w) Pt impregnated molybdenum(<small>VI</small>) oxide or tungsten(<small>VI</small>) oxide which was incorporated into poly(vinyl alcohol) films placed under clear, gas impermeable septa. To conduct experiments, users require only blue reaction-driving high intensity LEDs (light emitting diodes), a camera, and uniform lighting to take pictures as the septa darken. This work introduces a sample configuration in which nine samples in hydrogen sensitive septa-capped vials were illuminated and the gas evolution is monitored using a RaspberryPi for image capture and storage. Two calibration methods are presented, one uses a gravimetric hydrogen evolution with Zn/HCl that is compared to a direct hydrogen injection. Both methods allow the accurate correlation of normalized intensity values of film photographs to mole fractions of H<small>₂</small> ranging from 0 to 50%. Four light-driven HERs are described that highlight the capabilities of the detection method, two of which were conducted using the novel septa-based instrumentation while the other two experiments used the films on a 108 multiwell plate using a previously described photoreactor.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1430-1440"},"PeriodicalIF":6.2,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00070f?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141524883","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":"Expanding the chemical space using a chemical reaction knowledge graph†","authors":"Emma Rydholm, Tomas Bastys, Emma Svensson, Christos Kannas, Ola Engkvist and Thierry Kogej","doi":"10.1039/D3DD00230F","DOIUrl":"10.1039/D3DD00230F","url":null,"abstract":"<p >In this work, we present a new molecular <em>de novo</em> design approach which utilizes a knowledge graph encoding chemical reactions, extracted from the publicly available USPTO (United States Patent and Trademark Office) dataset. Our proposed method can be used to expand the chemical space by performing forward synthesis prediction by finding new combinations of reactants in the knowledge graph and can in this way generate libraries of <em>de novo</em> compounds along with a valid synthetic route. The forward synthesis prediction of novel compounds involves two steps. In the first step, a graph neural network-based link prediction model is used to suggest pairs of existing reactant nodes in the graph that are likely to react. In the second step, product prediction is performed using a molecular transformer model to obtain the potential products for the suggested reactant pairs. We achieve a ROC–AUC score of 0.861 for link prediction in the knowledge graph and for the product prediction, a top-1 accuracy of 0.924. The method's utility is demonstrated by generating a set of <em>de novo</em> compounds by predicting high probability reactions in the USPTO. The generated compounds are diverse in nature and many exhibit drug-like properties. A brief comparison with a template-based library design is provided. Furthermore, evaluation of the potential activity using a quantitative structure–activity relationship (QSAR) model suggested the presence of potential dopamine receptor D2 (DRD2) modulators among the proposed compounds. In summary, our results suggest that the proposed method can expand the easily accessible chemical space, by combining known compounds, and identify novel drug-like compounds for a specific target.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1378-1388"},"PeriodicalIF":6.2,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d3dd00230f?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501271","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":"Deep learning-based recommendation system for metal–organic frameworks (MOFs)†","authors":"Xiaoqi Zhang, Kevin Maik Jablonka and Berend Smit","doi":"10.1039/D4DD00116H","DOIUrl":"10.1039/D4DD00116H","url":null,"abstract":"<p >This work presents a recommendation system for metal–organic frameworks (MOFs) inspired by online content platforms. By leveraging the unsupervised Doc2Vec model trained on document-structured intrinsic MOF characteristics, the model embeds MOFs into a high-dimensional chemical space and suggests a pool of promising materials for specific applications based on user-endorsed MOFs with similarity analysis. This proposed approach significantly reduces the need for exhaustive labeling of every material in the database, focusing instead on a select fraction for in-depth investigation. Ranging from methane storage and carbon capture to quantum properties, this study illustrates the system's adaptability to various applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1410-1420"},"PeriodicalIF":6.2,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00116h?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141501245","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":"Materials science in the era of large language models: a perspective†","authors":"Ge Lei, Ronan Docherty and Samuel J. Cooper","doi":"10.1039/D4DD00074A","DOIUrl":"10.1039/D4DD00074A","url":null,"abstract":"<p >Large Language Models (LLMs) have garnered considerable interest due to their impressive natural language capabilities, which in conjunction with various emergent properties make them versatile tools in workflows ranging from complex code generation to heuristic finding for combinatorial problems. In this paper we offer a perspective on their applicability to materials science research, arguing their ability to handle ambiguous requirements across a range of tasks and disciplines means they could be a powerful tool to aid researchers. We qualitatively examine basic LLM theory, connecting it to relevant properties and techniques in the literature before providing two case studies that demonstrate their use in task automation and knowledge extraction at-scale. At their current stage of development, we argue LLMs should be viewed less as oracles of novel insight, and more as tireless workers that can accelerate and unify exploration across domains. It is our hope that this paper can familiarise materials science researchers with the concepts needed to leverage these tools in their own research.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1257-1272"},"PeriodicalIF":6.2,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00074a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254151","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":"Modelling kinetic isotope effects for Swern oxidation using DFT-based transition state theory†","authors":"D. Christopher Braddock, Siwoo Lee and Henry S. Rzepa","doi":"10.1039/D3DD00246B","DOIUrl":"10.1039/D3DD00246B","url":null,"abstract":"<p >We investigate the model reported by Giagou and Meyer in 2010 for comparing deuterium kinetic isotope effects (KIEs) computed using density functional theory (DFT) for the intramolecular hydrogen transfer step in the mechanism of the Swern oxidation of alcohols to aldehydes, with those measured by experiment. Whereas the replication of the original computed values for the gas-phase reaction proved entirely successful, several issues were discovered when a continuum solvent model was used. These included uncertainty regarding the parameters and methods used for the calculations and also the coordinates for the original reactant and transition structures, <em>via</em> their provision as data in the ESI. The original conclusions, in which a numerical mis-match between the magnitude of the computed and experimentally measured KIE was attributed to significant deviations from transition structure theory, are here instead rationalised as a manifestation of basis-set effects in the computation. Transition state theory appears to be operating successfully. We now recommend the use of basis sets of triple- or quadruple-ζ quality, rather than the split-valence level previously employed, that dispersion energy corrections be included and that a continuum solvent model using smoothed reaction cavities is essential for effective geometry optimisation and hence accurate normal coordinate analysis. An outlying experimental KIE obtained for chloroform as solvent is attributed to a small level of an explicit hydrogen bonded interaction with the substrate. A temperature outlier for the measured KIE at 195 K is suggested for further experimental investigation, although it may also be an indication of an unusually abrupt incursion of hydrogen tunnelling which would need non-Born–Oppenheimer methods in which nuclear quantum effects are included to be more accurately modelled. We predict KIEs for new substituents, of which those for R = NMe<small>₂</small> are significantly larger than those for R = H. This approach could be useful in designing variations of the Swern reagent that could lead to synthesis of aldehydes incorporating much higher levels of deuterium. The use of FAIR data rather than the traditional model of its inclusion in the ESI is discussed, and two data discovery tools exploiting these FAIR attributes are suggested.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 8","pages":" 1496-1508"},"PeriodicalIF":6.2,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d3dd00246b?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254141","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-guided high throughput nanoparticle design†","authors":"Ana Ortiz-Perez, Derek van Tilborg, Roy van der Meel, Francesca Grisoni and Lorenzo Albertazzi","doi":"10.1039/D4DD00104D","DOIUrl":"10.1039/D4DD00104D","url":null,"abstract":"<p >Designing nanoparticles with desired properties is a challenging endeavor, due to the large combinatorial space and complex structure–function relationships. High throughput methodologies and machine learning approaches are attractive and emergent strategies to accelerate nanoparticle composition design. To date, how to combine nanoparticle formulation, screening, and computational decision-making into a single effective workflow is underexplored. In this study, we showcase the integration of three key technologies, namely microfluidic-based formulation, high content imaging, and active machine learning. As a case study, we apply our approach for designing PLGA-PEG nanoparticles with high uptake in human breast cancer cells. Starting from a small set of nanoparticles for model training, our approach led to an increase in uptake from ∼5-fold to ∼15-fold in only two machine learning guided iterations, taking one week each. To the best of our knowledge, this is the first time that these three technologies have been successfully integrated to optimize a biological response through nanoparticle composition. Our results underscore the potential of the proposed platform for rapid and unbiased nanoparticle optimization.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1280-1291"},"PeriodicalIF":6.2,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00104d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254047","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":"Autonomous laboratories for accelerated materials discovery: a community survey and practical insights†","authors":"Linda Hung, Joyce A. Yager, Danielle Monteverde, Dave Baiocchi, Ha-Kyung Kwon, Shijing Sun and Santosh Suram","doi":"10.1039/D4DD00059E","DOIUrl":"10.1039/D4DD00059E","url":null,"abstract":"<p >What are researchers' motivations and challenges related to automation and autonomy in materials science laboratories? Our survey on this topic received 102 responses from researchers across a variety of institutions and in a variety of roles. Accelerated discovery was a clear theme in the responses, and another theme was concern about the role of human researchers. Survey respondents shared a variety of use cases targeting accelerated materials discovery, including examples where partial automation is preferred over full self-driving laboratories. Building on the observed patterns of researcher priorities and needs, we propose a framework for levels of laboratory autonomy from non-automated (L0) to fully autonomous (L5).</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1273-1279"},"PeriodicalIF":6.2,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00059e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196314","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":"Apples to apples: shift from mass ratio to additive molecules per electrode area to optimize Li-ion batteries","authors":"Bojing Zhang, Leon Merker, Monika Vogler, Fuzhan Rahmanian and Helge S. Stein","doi":"10.1039/D4DD00002A","DOIUrl":"10.1039/D4DD00002A","url":null,"abstract":"<p >Electrolyte additives in liquid electrolyte batteries can trigger the formation of a protective solid electrolyte interphase (SEI) at the electrodes <em>e.g.</em> to suppress side reactions at the electrodes. Studies of varying amounts of additives have been done over the last few years, providing a comprehensive understanding of the impact of the electrolyte formulation on the lifetime of the cells. However, these studies mostly focused on the variation of the mass fraction of additive in the electrolyte while disregarding the ratio (<em>r</em><small>_add</small>) of the additive's amount of substance (<em>n</em><small>_add</small>) to the electrode area (<em>A</em><small>_electrode</small>). Herein we utilize our accurate automatic battery assembly system (AUTOBASS) to vary electrode area and amount of substance of the additive. Our data provides evidence that reporting the mass ratios of electrolyte components is insufficient and the amount of substance of additive relative to the electrodes' area should be reported. Herein, the two most utilized additives, namely fluoroethylene carbonate (FEC) and vinylene carbonate (VC) were studied. Each additive was varied from 0.1 wt-%–3.0 wt-% for VC, and 5 wt-%–15 wt-% for FEC for two electrode loadings of 1 mA h cm<small>⁻²</small> and 3 mA h cm<small>⁻²</small>. To help the community to find better descriptors, such as the proposed <em>r</em><small>_add</small>, we publish the dataset alongside this manuscript. The active electrode placement correction reduces the failure rate of our automatically assembled cells to 3%.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1342-1349"},"PeriodicalIF":6.2,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd00002a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196322","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":"Perspective on AI for accelerated materials design at the AI4Mat-2023 workshop at NeurIPS 2023","authors":"Santiago Miret, N. M. Anoop Krishnan, Benjamin Sanchez-Lengeling, Marta Skreta, Vineeth Venugopal and Jennifer N. Wei","doi":"10.1039/D4DD90010C","DOIUrl":"10.1039/D4DD90010C","url":null,"abstract":"<p >Applications of advanced artificial intelligence (AI) methods in the materials science domain has grown significantly in recent years resulting in numerous research efforts spanning diverse aspects of materials design, materials synthesis, and materials characterization. The AI for Accelerated Materials Design (AI4Mat) workshop at NeurIPS 2023 featured many of the ongoing major research themes by bringing together an international interdisciplinary community of researchers and enthusiasts across academia, industry, and national labs. The goal of these discussions was to highlight cutting-edge work from active researchers in these fields and uncover major impactful research problems that the community can jointly address. In this article, the AI4Mat-2023 organizing committee showcases the major developments in the field as well as ongoing research challenges where innovative solutions can bring transformative changes to the state-of-the-art in applying AI for accelerated materials design. The editors of <em>Digital Discovery</em> are pleased to feature this overview, and a selection of these manuscripts, in a new themed collection.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1081-1085"},"PeriodicalIF":0.0,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2024/dd/d4dd90010c?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196509","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}