Digital discovery最新文献_第8页

Large language models in materials science and the need for open-source approaches 材料科学中的大型语言模型和对开源方法的需求

IF 6.2

Digital discovery Pub Date : 2026-04-13 DOI: 10.1039/D5DD00499C

Fengxu Yang, Weitong Chen and Jack D. Evans

引用次数: 0

Generalization of long-range machine learning potentials in complex chemical spaces 复杂化学空间中远程机器学习势的泛化。

IF 6.2

Digital discovery Pub Date : 2026-04-13 DOI: 10.1039/D5DD00570A

Michał Sanocki and Julija Zavadlav

{"title":"Generalization of long-range machine learning potentials in complex chemical spaces","authors":"Michał Sanocki and Julija Zavadlav","doi":"10.1039/D5DD00570A","DOIUrl":"10.1039/D5DD00570A","url":null,"abstract":"The vastness of chemical space makes generalization a central challenge in the development of machine learning interatomic potentials (MLIPs). While MLIPs could enable large-scale atomistic simulations with near-quantum accuracy, their usefulness is often limited by poor transferability to out-of-distribution samples. Here, we systematically evaluate different MLIP architectures with long-range corrections across diverse chemical spaces and show that such schemes are essential, not only for improving in-distribution performance but, more importantly, for enabling significant gains in transferability to unseen regions of chemical space. To enable a more rigorous benchmarking, we introduce biased train–test splitting strategies, which explicitly test the model performance in significantly different regions of chemical space. Together, our findings highlight the importance of long-range modeling for achieving generalizable MLIPs and provide a framework for diagnosing systematic failures across chemical space. While this study focuses on metal–organic frameworks and related systems, the proposed methodology is not limited to this class of materials and may inform the design of more robust and transferable MLIPs in other systems.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 2195-2208"},"PeriodicalIF":6.2,"publicationDate":"2026-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13093489/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790645","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}

引用次数: 0

The loss landscape of powder X-ray diffraction-based structure optimization is too rough for gradient descent 粉末x射线衍射结构优化的损失图过于粗糙，无法进行梯度下降

IF 6.2

Digital discovery Pub Date : 2026-04-10 DOI: 10.1039/D6DD00017G

Nofit Segal, Akshay Subramanian, Mingda Li, Benjamin Kurt Miller and Rafael Gómez-Bombarelli

{"title":"The loss landscape of powder X-ray diffraction-based structure optimization is too rough for gradient descent","authors":"Nofit Segal, Akshay Subramanian, Mingda Li, Benjamin Kurt Miller and Rafael Gómez-Bombarelli","doi":"10.1039/D6DD00017G","DOIUrl":"https://doi.org/10.1039/D6DD00017G","url":null,"abstract":"Solving crystal structures from powder X-ray diffraction (XRD) is a critical inverse problem in materials characterization. This work studies the mapping from diffractogram to crystal structure using gradient-based optimization of the structure with XRD similarity as the objective, and evaluates the retrieval of ground-truth geometries from moderately distorted structures. We find that commonly used XRD similarity metrics result in an ill-posed, highly non-convex loss landscape where high signal agreement does not necessarily imply structural accuracy, a phenomenon driven by spurious peak overlaps. Constraining the optimization to the ground-truth crystal family significantly improves retrieval, and yields higher correlation between structural similarity and XRD similarity. Nevertheless, the landscape may remain non-convex along certain symmetry axes. Finally, we contrast this with the interatomic potential energy landscape, which exhibits smooth, locally convex behavior for identical structural perturbations.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 4","pages":" 1590-1599"},"PeriodicalIF":6.2,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00017g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733042","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}

引用次数: 0

MolRes-DTA: a molecular-multiview fusion and residue-aware model for drug-target affinity prediction MolRes-DTA：一种用于药物靶点亲和力预测的分子-多视角融合和残留物感知模型

IF 6.2

Digital discovery Pub Date : 2026-04-10 DOI: 10.1039/D5DD00365B

Hongli Hou, Qi Wei, Dian Huang, Minglu Zhao, Hongliang Duan and Shengzhong Feng

{"title":"MolRes-DTA: a molecular-multiview fusion and residue-aware model for drug-target affinity prediction","authors":"Hongli Hou, Qi Wei, Dian Huang, Minglu Zhao, Hongliang Duan and Shengzhong Feng","doi":"10.1039/D5DD00365B","DOIUrl":"https://doi.org/10.1039/D5DD00365B","url":null,"abstract":"Accurate prediction of drug-target affinity (DTA) is crucial for drug screening and reducing drug development costs. Despite the significant progress made by deep learning methods in DTA prediction, most existing approaches neglect two critical factors: the influence of drug molecular size and the different contribution of amino acid residues to DTA. Here, we propose an affinity prediction model, MolRes-DTA, which introduces multiview drug characterization and a dynamic residue-aware network to capture the influence of molecular size on affinity prediction and weigh the contributions of different residues. Experiments on the Davis and KIBA datasets demonstrate that MolRes-DTA outperforms baseline models by 15.58% and 20.11%, respectively. Further analysis shows that our multiview drug representation improves prediction accuracy across different types of molecular sizes, with particularly notable gains for larger compounds. To our knowledge, this is the first study to explore the impact of molecular size on DTA prediction, providing a novel perspective for enhancing the accuracy of DTA prediction.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 2184-2194"},"PeriodicalIF":6.2,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00365b?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147968366","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}

引用次数: 0

AiiDA-TrainsPot: towards automated training of neural-network interatomic potentials AiiDA-TrainsPot：神经网络原子间势的自动训练

IF 6.2

Digital discovery Pub Date : 2026-04-09 DOI: 10.1039/D6DD00005C

Davide Bidoggia, Nataliia Manko, Maria Peressi and Antimo Marrazzo

{"title":"AiiDA-TrainsPot: towards automated training of neural-network interatomic potentials","authors":"Davide Bidoggia, Nataliia Manko, Maria Peressi and Antimo Marrazzo","doi":"10.1039/D6DD00005C","DOIUrl":"https://doi.org/10.1039/D6DD00005C","url":null,"abstract":"Crafting neural-network interatomic potentials (NNIPs) remains a complex task, demanding specialized expertise in both machine learning and electronic-structure calculations. Here, we introduce AiiDA-TrainsPot, an automated, open-source, and user-friendly workflow that streamlines the creation of accurate NNIPs by orchestrating density-functional-theory calculations, data augmentation strategies, and classical molecular dynamics. Our active-learning strategy leverages on-the-fly calibration of committee disagreement against ab initio reference errors to ensure reliable uncertainty estimates. We use electronic-structure descriptors and dimensionality reduction to analyze the efficiency of this calibrated criterion, and show that it minimizes both false positives and false negatives when deciding what to compute from first principles. AiiDA-TrainsPot has a modular design that supports multiple NNIP backends, enabling both the training of NNIPs from scratch and the fine-tuning of foundation models. We demonstrate its capabilities through automated training campaigns targeting pristine and defective carbon allotropes, including amorphous carbon, as well as structural phase stability in monolayer WxMo1−xTe2 alloys.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 2292-2309"},"PeriodicalIF":6.2,"publicationDate":"2026-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00005c?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147968333","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}

引用次数: 0

Multi-stage Bayesian optimisation for dynamic decision-making in self-driving labs 自动驾驶实验室动态决策的多阶段贝叶斯优化

IF 6.2

Digital discovery Pub Date : 2026-04-07 DOI: 10.1039/D5DD00572H

Luca Torresi and Pascal Friederich

{"title":"Multi-stage Bayesian optimisation for dynamic decision-making in self-driving labs","authors":"Luca Torresi and Pascal Friederich","doi":"10.1039/D5DD00572H","DOIUrl":"https://doi.org/10.1039/D5DD00572H","url":null,"abstract":"Currently, Bayesian optimisation is the most widely used algorithm for identifying informative experiments in self-driving labs (SDLs). While versatile, standard Bayesian optimisation relies on fixed experimental workflows with predefined parameters and objective functions. This prevents on-the-fly adjustments to operation sequences or the inclusion of intermediate results in the decision-making process. Therefore, many real-world experiments need to be adapted and simplified to fit standard SDL settings. In this paper, we introduce multi-stage Bayesian optimisation (MSBO), an extension to Bayesian optimisation that allows flexible sampling of multi-stage workflows and makes data-efficient decisions based on intermediate observables, which we call proxy measurements. MSBO is designed to address common SDL challenges, such as high downstream characterisation costs, sequential dependencies, and the effective use of proxy measurements. To evaluate this approach, we validate our method using computational simulations and retrospective datasets of chemical discovery, demonstrating its potential to accelerate future SDLs. We systematically compare the advantage of taking into account proxy measurements over conventional Bayesian optimisation, in which only the final measurement is observed. We find that across a wide range of scenarios, proxy measurements substantially improve both the time to find solutions and their overall optimality. This not only paves the way to use more complex and thus more realistic experimental workflows in autonomous labs but also to smoothly combine simulations and experiments in the next generation of SDLs.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 4","pages":" 1900-1912"},"PeriodicalIF":6.2,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00572h?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147732965","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}

引用次数: 0

On-the-fly fine-tuning of foundational neural network potentials: a Bayesian neural network approach 基础神经网络电位的动态微调：贝叶斯神经网络方法

IF 6.2

Digital discovery Pub Date : 2026-04-07 DOI: 10.1039/D5DD00392J

Tim Rensmeyer, Denis Kramer and Oliver Niggemann

{"title":"On-the-fly fine-tuning of foundational neural network potentials: a Bayesian neural network approach","authors":"Tim Rensmeyer, Denis Kramer and Oliver Niggemann","doi":"10.1039/D5DD00392J","DOIUrl":"https://doi.org/10.1039/D5DD00392J","url":null,"abstract":"Due to the computational complexity of evaluating interatomic forces from first principles, the creation of interatomic machine learning force fields has become a highly active field of research. However, the generation of training datasets of sufficient size and sample diversity itself comes with a computational burden that can make this approach impractical for modeling rare events or systems with a large configuration space. Fine-tuning foundation models that have been pre-trained on large-scale material or molecular databases offers a promising opportunity to reduce the amount of training data necessary to reach a desired level of accuracy. However, even if this approach requires less training data overall, creating a suitable training dataset can still be a very challenging problem, especially for systems with rare events and for end-users who don't have an extensive background in machine learning. In on-the-fly learning, the creation of a training dataset can be largely automated by using model uncertainty during the simulation to decide if the model is accurate enough or if a structure should be recalculated with quantum-chemical methods and used to update the model. A key challenge for applying this form of active learning to the fine-tuning of foundation models is how to assess the uncertainty of those models during the fine-tuning process, even though most foundation models lack any form of uncertainty quantification. In this paper, we overcome this challenge by introducing a fine-tuning approach based on Bayesian neural network methods and a subsequent on-the-fly workflow that automatically fine-tunes the model while maintaining a pre-specified accuracy and can detect rare events such as transition states and sample them at an increased rate relative to their occurrence.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 4","pages":" 1845-1867"},"PeriodicalIF":6.2,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00392j?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147732961","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}

引用次数: 0

FlowMol3: flow matching for 3D de novo small-molecule generation FlowMol3: 3D从头生成小分子的流动匹配。

IF 6.2

Digital discovery Pub Date : 2026-04-07 DOI: 10.1039/D5DD00363F

Ian Dunn and David R. Koes

{"title":"FlowMol3: flow matching for 3D de novo small-molecule generation","authors":"Ian Dunn and David R. Koes","doi":"10.1039/D5DD00363F","DOIUrl":"10.1039/D5DD00363F","url":null,"abstract":"A generative model capable of sampling realistic molecules with desired properties could accelerate chemical discovery across a wide range of applications. Toward this goal, significant effort has focused on developing models that jointly sample molecular topology and 3D structure. We present FlowMol3, an open-source, multi-modal flow matching model that advances the state of the art for all-atom, small-molecule generation. Its substantial performance gains over previous FlowMol versions are achieved without changes to the graph neural network architecture or the underlying flow matching formulation. Instead, FlowMol3's improvements arise from three architecture-agnostic techniques that incur negligible computational cost: self-conditioning, fake atoms, and train-time geometry distortion. FlowMol3 achieves nearly 100% molecular validity for drug-like molecules with explicit hydrogens, more accurately reproduces the functional group composition and geometry of its training data, and does so with an order of magnitude fewer learnable parameters than comparable methods. We hypothesize that these techniques mitigate a general pathology affecting transport-based generative models, enabling detection and correction of distribution drift during inference. Our results highlight simple, transferable strategies for improving the stability and quality of diffusion- and flow-based molecular generative models.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 2052-2066"},"PeriodicalIF":6.2,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13104864/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790575","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}

引用次数: 0

Large language models for porous materials: from text mining to autonomous laboratory 多孔材料的大型语言模型：从文本挖掘到自主实验室

IF 6.2

Digital discovery Pub Date : 2026-04-07 DOI: 10.1039/D5DD00578G

Seunghee Han, Taeun Bae, Junho Kim, Younghun Kim and Jihan Kim

{"title":"Large language models for porous materials: from text mining to autonomous laboratory","authors":"Seunghee Han, Taeun Bae, Junho Kim, Younghun Kim and Jihan Kim","doi":"10.1039/D5DD00578G","DOIUrl":"https://doi.org/10.1039/D5DD00578G","url":null,"abstract":"Porous materials such as metal–organic frameworks (MOFs), covalent organic frameworks (COFs), zeolites, and porous carbons play central roles in gas storage, separation, catalysis, and environmental technologies. However, their design and discovery remain resource-intensive, relying heavily on expert intuition and fragmented knowledge distributed across the literature. Recent advances in large language models (LLMs) present new opportunities to accelerate these workflows by integrating scientific text mining, domain reasoning, and experimental planning. In this review, we outline the emerging role of LLMs across the porous materials research ecosystem. We first introduce the foundations of LLMs, followed by a discussion of NLP-based text mining for literature analysis. We then examine LLM adaptation including prompt engineering and fine-tuning, and autonomous research systems from human-in-the-loop to self-driving laboratories. For each domain, we summarize how LLM architectures are integrated with research systems, highlighting their applications, advantages, and limitations. Additionally, we discuss the current challenges of applying LLMs to porous materials, trade-offs between prompt engineering and fine-tuning, the influence of generation parameters such as temperature, and safety considerations in autonomous laboratory systems. Finally, we expect LLMs to advance toward multimodal reasoning, tighter integration with structured knowledge bases, and safer autonomous experimental workflows. Together, these developments suggest emerging LLM-driven paradigms that could transform the conceptualization, design, and synthesis of porous materials.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 4","pages":" 1470-1500"},"PeriodicalIF":6.2,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00578g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733018","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}

引用次数: 0

Distilling and exploiting quantitative insights from large language models for enhanced Bayesian optimization of chemical reactions 从大型语言模型中提取和开发定量见解，以增强化学反应的贝叶斯优化

IF 6.2

Digital discovery Pub Date : 2026-04-06 DOI: 10.1039/D6DD00052E

Roshan A. Patel, Mingxuan Li, Chin-Fei Chang, Louis De Lescure, Paul Chauvin, Alan Cherney, Saeed Moayedpour, Sven Jager and Yasser Jangjou

{"title":"Distilling and exploiting quantitative insights from large language models for enhanced Bayesian optimization of chemical reactions","authors":"Roshan A. Patel, Mingxuan Li, Chin-Fei Chang, Louis De Lescure, Paul Chauvin, Alan Cherney, Saeed Moayedpour, Sven Jager and Yasser Jangjou","doi":"10.1039/D6DD00052E","DOIUrl":"https://doi.org/10.1039/D6DD00052E","url":null,"abstract":"Machine learning and Bayesian optimization (BO) algorithms can significantly accelerate the optimization of chemical reactions. Transfer learning can bolster the effectiveness of BO algorithms in low-data regimes by leveraging pre-existing chemical information or data outside the direct optimization task (i.e., source data). Large Language Models (LLMs) have demonstrated that chemical information present in foundation training data can give them utility for processing chemical data. Furthermore, they can be augmented with and help synthesize potentially multiple modalities of source chemical data germane to the optimization task. In this work, we examine how chemical information from LLMs can be elicited and used for transfer learning to accelerate the BO of reaction conditions to maximize yield. Specifically, we show that a survey-like prompting scheme and preference learning can be used to infer a utility function which models prior chemical information embedded in LLMs over a chemical parameter space; we find that the utility function shows modest correlation to true experimental measurements (yield) over the parameter space despite operating in a zero-shot setting. Furthermore, we show that the utility function can be leveraged to focus BO efforts in promising regions of the parameter space, improving the yield of the initial BO query and enhancing optimization in a majority of the datasets studied. Overall, we view this work as a step towards bridging the gap between the chemistry knowledge embedded in LLMs and the capabilities of principled BO methods to accelerate reaction optimization.","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 2042-2051"},"PeriodicalIF":6.2,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00052e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147968355","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}

引用次数: 0