Digital discovery最新文献

{"title":"Text-to-flowsheet: an LLM-assisted pipeline for expert-level digitization and automated simulation of chemical processes.","authors":"Jan-Frederic Laub, Luca Bosetti, André Bardow","doi":"10.1039/d6dd00060f","DOIUrl":"10.1039/d6dd00060f","url":null,"abstract":"<p><p>Converting unstructured natural language descriptions into structured process flowsheets is a fundamental bottleneck in chemical engineering, traditionally requiring years of expert training. While large language models (LLMs) show promise in text comprehension, their ability to match human expertise in modeling complex chemical process flowsheets remains unproven. Here, we present a rigorous benchmark comparing a fully automated LLM-powered digitization pipeline against the collective performance of 50 chemical engineering experts. Our pipeline leverages LLMs to extract process structures from text and formalize them as flowsheet graphs. To handle the inherent ambiguities of natural language, we utilize constrained, step-by-step prompting augmented with thermodynamic property calculations. Subsequently, the digitized flowsheet graphs are automatically translated into the flowsheeting software Aspen Plus to compute rigorous mass and energy balances. Black-box optimization on subprocess structures is used to estimate unknown parameters and ensure simulation convergence, completing the pipeline from text to converged process simulation. For the first time, we demonstrate that an automated pipeline can achieve expert-level accuracy in process topology digitization. Using a unique, newly-generated dataset of 101 expert-drawn flowsheets, we show that our LLM-assisted approach faithfully captures process topology and operating conditions even in the face of incomplete information. This work provides a robust, validated framework for the large-scale digitization of chemical production literature, contributing a transformative tool and dataset for the community to accelerate automated process design and assessment.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" ","pages":"2937-2951"},"PeriodicalIF":7.1,"publicationDate":"2026-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13251679/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148229320","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":"RobInHood: a robotic chemist in a fume hood","authors":"Louis Longley, Francisco Munguia-Galeano, Yushu Han, Rob Clowes, Sriram Vijayakrishnan, Adam Edwards, Gabriella Pizzuto, Hatem Fakhruldeen and Andrew Cooper","doi":"10.1039/D6DD00007J","DOIUrl":"10.1039/D6DD00007J","url":null,"abstract":"<p >Fume hoods protect chemists and the environment from hazardous vapours and airborne substances produced during experiments. They are standard in chemistry laboratories worldwide. However, fume hoods were designed for manual chemistry, and there are still relatively few robotic systems designed to operate within these inherently confined spaces. It is challenging to design robotic systems that can perform the same variety of operations within fume hoods that can be performed by a dexterous human chemist. Here, we present an automated platform comprising a robotic arm that can perform liquid handling, solid handling, capping/decapping, heating and stirring, filtration, and sample imaging within a standard laboratory fume hood (50 cm × 120 cm × 170 cm). The broad applicability of this system was demonstrated in two materials research problems (a dye-based porosity screening workflow and the synthesis of a porous organic cage) and in a phthalimide synthesis. The success of the synthesis workflows was validated offline by NMR, X-ray diffraction, mass spectrometry and FTIR.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2438-2447"},"PeriodicalIF":7.1,"publicationDate":"2026-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13202499/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148044657","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":"PRISM: protocol refinement through intelligent simulation modeling","authors":"Brian Hsu, Priyanka V. Setty, Rory M. Butler, Ryan Lewis, Casey Stone, Rebecca Weinberg, Thomas Brettin, Rick Stevens, Ian Foster and Arvind Ramanathan","doi":"10.1039/D6DD00004E","DOIUrl":"https://doi.org/10.1039/D6DD00004E","url":null,"abstract":"<p >Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates the design, validation, and execution of experimental protocols on a laboratory platform composed of off-the-shelf robotic instruments. PRISM uses a set of language-model-based agents that work together to generate and refine experimental steps. The process begins with automatically gathering relevant procedures from web-based sources describing experimental workflows. These are converted into structured experimental steps (<em>e.g.</em>, liquid handling steps, deck layout and other related operations) through a planning, critique, and validation loop. The finalized steps are translated into the Argonne MADSci protocol format, which provides a unified interface for coordinating multiple robotic instruments (Opentrons OT-2 liquid handler, PF400 arm, Azenta plate sealer and peeler) without requiring human intervention between steps. To evaluate protocol-generation performance, we benchmarked both single reasoning models and multi-agent workflow across constrained and open-ended prompting paradigms. The resulting protocols were validated in a digital-twin environment built in NVIDIA Omniverse to detect physical or sequencing errors before execution. Using Luna qPCR amplification and Cell Painting as case studies, we demonstrate PRISM as a practical end-to-end workflow that bridges language-based protocol generation, simulation-based validation, and automated robotic execution.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2613-2628"},"PeriodicalIF":7.1,"publicationDate":"2026-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00004e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261442","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":"Gradient-enhanced neural networks for model parameter estimation applied to flow chemistry automated platforms","authors":"Francisco Bolaños-García, Jean-Marc Commenge and Laurent Falk","doi":"10.1039/D5DD00526D","DOIUrl":"https://doi.org/10.1039/D5DD00526D","url":null,"abstract":"<p >The acceleration of chemical process development through flow chemistry depends on obtaining reliable kinetic models. Model-based design of experiments (MBDoE) has been successfully applied with flow chemistry platforms for estimating reaction rate parameters for low-complexity models. However, its use with dynamic experiments involving computationally expensive models remains challenging, particularly when experimental conditions must be suggested in real time. Surrogate models can approximate complex models, but often lack the ability to reproduce the derivatives of the original model, which are essential for MBDoE as a gradient-based approach. This work investigates the use of gradient-enhanced neural networks as surrogate models for parameter estimation within an MBDoE framework. By incorporating gradient information, the surrogate model is able to reproduce the local sensitivity structure of the original first-principles model, ensuring predictive accuracy for both output values and gradients needed for parameter estimation. A case study on competitive–consecutive reactions demonstrates that artificial neural networks (ANNs) that were trained with gradient information can be used for parameter estimation, while substantially reducing computational cost by a factor of approximately 200 000. This enables sequential MBDoE suitable for real-time applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2728-2742"},"PeriodicalIF":7.1,"publicationDate":"2026-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00526d?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261398","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":"Navigating the landscape of modular reconfigurable laboratory automation in chemistry","authors":"Rodrigo Moreno, Jonas Jensen, Andres Faina and Kasper Stoy","doi":"10.1039/D5DD00330J","DOIUrl":"https://doi.org/10.1039/D5DD00330J","url":null,"abstract":"<p >Easily reusable lab automation is the next frontier in automating experiments. Equipment must be repurposed often for experiments, making the current generation of lab automation too costly and too complicated to apply. However, with the rise of platforms in which modules encapsulate operations, connections and equipment can be swapped around quickly and, in some cases, automatically to perform different experiments. This article reviews the current state of the art of reconfigurable modular laboratory automation systems in chemistry. We discuss the key barriers of adoption of these systems and the importance of standardized benchmarks to compare capabilities of different platforms. We provide an outlook on the most promising research paths, including the possibility that AI systems can help guide the layout of processes and operations, leading to improved efficiency and possibly new process layouts. We conclude that the field of laboratory automation should continue to advance, benefiting chemists and the broader scientific community.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2383-2399"},"PeriodicalIF":7.1,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00330j?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261460","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":"ConforFormer: representation for molecules through understanding of conformers","authors":"Mas Pieter Klein, Irina Rudenko, Evgeny A. Pidko and Ivan Bushmarinov","doi":"10.1039/D6DD00096G","DOIUrl":"https://doi.org/10.1039/D6DD00096G","url":null,"abstract":"<p >Molecular properties of chemical compounds are governed not by a single unique arrangement of atoms (2D molecular graph) but by ensembles of three-dimensional conformers, yet most molecular representations for machine learning approaches either ignore conformational diversity or use it implicitly to augment molecular graphs. Here we introduce ConforFormer, a geometry-first foundation model capable of learning conformation-robust molecular embeddings directly from the 3D atomic coordinates. By aligning representations across multiple conformers of the same molecules through a novel contrastive objective, ConforFormer produces compact, task-agnostic embeddings that can be generated once and directly applied to downstream tasks, including property prediction and structural similarity, without extensive fine-tuning. Across a range of quantum-chemical and bioactivity benchmarks, these frozen embeddings achieve competitive performance without task-specific fine-tuning, while offering improved stability on small datasets. Beyond property prediction, the learned embedding space allows to discriminate with high-precision molecular conformers and isomers, substantially outperforming classical fingerprint-based similarity measures. This implies that explicit exposure to conformational relationships induces representations that generalize beyond the conformer recognition task itself, capturing chemically meaningful structural constraints directly from 3D geometries. More broadly, our results suggest that incorporating conformation-awareness as a foundational learning task provides a fundamental route towards transferable, geometry-centered molecular representations particularly relevant for complex chemical systems, where conventional graph-based representations are ambiguous or ill-defined.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2639-2649"},"PeriodicalIF":7.1,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00096g?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261444","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":"Lightweight privacy-preserving human activity recognition from CSI data using a CNN-temporal attention network","authors":"Khondakar Ashik Shahriar, Maruf Ahmed and Hafiz Imtiaz","doi":"10.1039/D6DD00077K","DOIUrl":"https://doi.org/10.1039/D6DD00077K","url":null,"abstract":"<p >WiFi Channel State Information (CSI) has emerged as a powerful sensing modality for device-free Human Activity Recognition (HAR), enabling fine-grained motion understanding without requiring wearable sensors or cameras. However, any type of HAR – either CSI signal-based or device-based, inherently encodes sensitive behavioral patterns, raising significant privacy concerns. In this work, we propose an end-to-end privacy-preserving CSI-based HAR framework that integrates a Convolutional Neural Network (CNN) with a temporal attention mechanism. We perform extensive evaluations on multiple benchmark datasets consisting of varying distance and height factors, as well as different environmental conditions. Our baseline non-privacy-preserving CNN–temporal attention model achieves state-of-the-art performance. Additionally, we incorporate differential privacy (DP) into the training pipeline – enabling rigorous privacy guarantees through controlled noise injection and gradient clipping. We evaluate the proposed framework's privacy–utility trade-off and demonstrate that even strong privacy protection can maintain excellent recognition accuracy. Our framework can progressively approach the non-privacy-preserving performance for some parameter regimes. As such, our experimental results clearly demonstrate that the proposed architecture remains robust under privacy constraints and generalizes effectively across heterogeneous sensing conditions. We argue that our work provides practical insights into deploying secure and privacy-aware WiFi sensing systems for real-world HAR applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2701-2715"},"PeriodicalIF":7.1,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00077k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261448","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 user-tunable machine learning framework for step-wise synthesis planning","authors":"Shivesh Prakash, Nandan Patel, Hans-Arno Jacobsen and Viki Kumar Prasad","doi":"10.1039/D5DD00562K","DOIUrl":"https://doi.org/10.1039/D5DD00562K","url":null,"abstract":"<p >We introduce MHNpath, a machine learning-driven retrosynthetic tool designed for computer-aided synthesis planning. Leveraging modern Hopfield networks and novel comparative metrics, MHNpath efficiently prioritizes reaction templates, improving the scalability and accuracy of retrosynthetic predictions. The tool incorporates a tunable scoring system that allows users to prioritize pathways based on cost, reaction temperature, and toxicity, thereby facilitating the design of greener and cost-effective reaction routes. We demonstrate its effectiveness through case studies involving complex molecules from ChemByDesign, showcasing its ability to predict novel synthetic and enzymatic pathways. Furthermore, we benchmark MHNpath against existing frameworks using the PaRoutes dataset, achieving a solution rate of 85.4% and replicating 69.2% of experimentally validated “gold-standard” pathways. Our case studies show that the tool can generate shorter, cheaper, moderate-temperature routes employing green solvents, as exemplified by molecules such as dronabinol, arformoterol, and lupinine.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2669-2683"},"PeriodicalIF":7.1,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d5dd00562k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261446","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":"Spectroscopy-assisted Bayesian optimization for efficient refolding of inclusion body proteins","authors":"Florian Gisperg, Robert Klausser, Matthias Kierein, Eva Prada Brichtova, Mohamed Elshazly, Julian Kopp and Oliver Spadiut","doi":"10.1039/D6DD00035E","DOIUrl":"https://doi.org/10.1039/D6DD00035E","url":null,"abstract":"<p >The production of recombinant proteins in <em>Escherichia coli</em> often yields insoluble inclusion bodies, which require denaturation and refolding to obtain the native product. The protein refolding step usually represents a major bottleneck. Conventional development and optimization typically rely on sequential design of experiments with high-performance liquid chromatography readouts. This approach is slow, labor-intensive, and requires an established chromatographic method as well as purified protein standards. At the beginning of process development, these prerequisites may not be met—especially for proteins that can only be expressed as inclusion bodies. We introduce a more efficient, data-driven workflow that pairs Bayesian optimization with a rapid, in-line readout from intrinsic tryptophan fluorescence. Using a disulfide-bonded single-chain variable fragment, we explored a five-dimensional design space of refolding buffer composition (dithiothreitol, oxidized glutathione, dilution factor, pH, and final urea concentration) guided by two spectroscopy-derived objectives. We showed that the spectral shift correlates with chromatographic yields, supporting its use as a fit-for-purpose sensor to guide process development with 25 experiments. Bayesian optimization identified conditions that delivered a refolded protein concentration of 1.29 ± 0.06 g L<small>⁻¹</small> at 58.7 ± 1.3% refolding yield with a dilution factor of 3.14, whereas a three-stage design of experiments with more than 60 experiments concluded at 0.37 ± 0.02 g L<small>⁻¹</small> and 61.4 ± 3.1% with a dilution factor of 11.39. Thus, the presented workflow achieved roughly 3.5-fold higher product concentration at comparable yield, while operating at substantially higher protein concentrations. Therefore, spectroscopy-assisted Bayesian optimization was found to be a practical, sample-efficient tool for refolding optimization that is especially valuable in early development stages.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2716-2727"},"PeriodicalIF":7.1,"publicationDate":"2026-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2026/dd/d6dd00035e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148261449","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":"optimade-maker: automated generation of interoperable materials APIs from static datasets","authors":"Kristjan Eimre, Matthew L. Evans, Bud Macaulay, Xing Wang, Jusong Yu, Nicola Marzari, Gian-Marco Rignanese and Giovanni Pizzi","doi":"10.1039/D6DD00125D","DOIUrl":"10.1039/D6DD00125D","url":null,"abstract":"<p >Atomistic structural data are central to materials science, condensed matter physics, and chemistry, and are increasingly digitised across diverse repositories and databases. Interoperable access to these heterogeneous data sources enables reusable clients and tools, and is essential for cross-database analyses and data-driven materials discovery. Toward this aim, the OPTIMADE (Open Databases Integration for Materials Design) specification defines a standard REST API for atomistic structures and related properties. However, deploying and maintaining compliant services remains technically demanding and poses a significant barrier for many data providers. Here, we present <em>optimade-maker</em>, a lightweight toolkit for the automated generation of OPTIMADE-compliant APIs directly from raw atomistic structure and property data. The toolkit supports a wide range of raw datasets, enables conversion to a standardised OPTIMADE data representation, and allows for rapid deployment of APIs in both local and production environments. We further demonstrate it through an automated service on the Materials Cloud Archive, which automatically creates and publishes OPTIMADE APIs for contributed datasets, enabling immediate discoverability and interoperability. In addition, we implement data transformation pipelines for the Cambridge Structural Database (CSD) and the Inorganic Crystal Structure Database (ICSD), enabling unified access to these curated resources through the OPTIMADE framework. By lowering the technical barriers to interoperable data publication, <em>optimade-maker</em> represents an important step toward a scalable, FAIR materials data ecosystem integrating both community-contributed and curated databases.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 2469-2477"},"PeriodicalIF":7.1,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13229571/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148159242","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}