Machine Learning Science and Technology最新文献

{"title":"Correlated clustering and projection for dimensionality reduction.","authors":"Yuta Hozumi, Rui Wang, Guo-Wei Wei","doi":"10.1088/2632-2153/ae72eb","DOIUrl":"10.1088/2632-2153/ae72eb","url":null,"abstract":"<p><p>Most dimensionality reduction methods employ frequency domain representations obtained from matrix diagonalization and may not be efficient for large datasets with relatively high intrinsic dimensions. To address this challenge, correlated clustering and projection (CCP) offers a novel data domain strategy that does not need to solve any matrix. CCP partitions high-dimensional features into correlated clusters and then projects correlated features in each cluster into a one-dimensional representation based on sample correlations. residue-similarity (R-S) scores and indexes, the shape of data in Riemannian manifolds, and algebraic topology-based persistent Laplacian are introduced for visualization and analysis. Proposed methods are validated using benchmark datasets associated with various machine learning algorithms.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"7 3","pages":"035062"},"PeriodicalIF":4.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13292825/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148333275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MDCrow: automating molecular dynamics workflows with large language models.","authors":"Quintina Campbell, Sam Cox, Jorge Medina, Brittany Watterson, Andrew D White","doi":"10.1088/2632-2153/ae4b07","DOIUrl":"10.1088/2632-2153/ae4b07","url":null,"abstract":"<p><p>Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLMs) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows for proteins. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 common tasks of varying complexity, and we evaluate the agent's robustness to difficulty and prompt style. gpt-4o is able to complete increasingly complex tasks with low variance, followed closely by llama3-405b, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"7 2","pages":"025037"},"PeriodicalIF":4.2,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13033927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147595217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative diffusion model surrogates for mechanistic agent-based biological models.","authors":"Tien Comlekoglu, J Quetzalcoatl Toledo-Marín, Douglas W DeSimone, Shayn M Peirce, Geoffrey Fox, James A Glazier","doi":"10.1088/2632-2153/ae11f8","DOIUrl":"10.1088/2632-2153/ae11f8","url":null,"abstract":"<p><p>Mechanistic, multicellular, agent-based models are commonly used to investigate tissue, organ, and organism-scale biology at single-cell resolution. The Cellular-Potts Model (CPM) is a powerful and popular framework for developing and interrogating these models. CPMs become computationally expensive at large space- and time- scales making application and investigation of developed models difficult. Surrogate models may allow for the accelerated evaluation of CPMs of complex biological systems. However, the stochastic nature of these models means each set of parameters may give rise to different model configurations, complicating surrogate model development. In this work, we leverage denoising diffusion probabilistic models (DDPMs) to train a generative AI surrogate of a CPM used to investigate <i>in vitro</i> vasculogenesis. We describe the use of an image classifier to learn the characteristics that define unique areas of a 2-dimensional parameter space. We then apply this classifier to aid in surrogate model selection and verification. Our CPM model surrogate generates model configurations 20,000 timesteps ahead of a reference configuration and demonstrates approximately a 22x reduction in computational time as compared to native code execution. Our work represents a step towards the implementation of DDPMs to develop digital twins of stochastic biological systems.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 4","pages":"045024"},"PeriodicalIF":4.2,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12570967/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145408961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Depthwise-Dilated Convolutional Adapters for Medical Object Tracking and Segmentation Using the Segment Anything Model 2.","authors":"Guoping Xu, Christopher Kabat, You Zhang","doi":"10.1088/2632-2153/ae13d1","DOIUrl":"10.1088/2632-2153/ae13d1","url":null,"abstract":"<p><p>Recent advances in medical image segmentation have been driven by deep learning; however, most existing methods remain limited by modality-specific designs and exhibit poor adaptability to dynamic medical imaging scenarios. The Segment Anything Model 2 (SAM2) and its related variants, which introduce a streaming memory mechanism for real-time video segmentation, present new opportunities for prompt-based, generalizable solutions. Nevertheless, adapting these models to medical video scenarios typically requires large-scale datasets for retraining or transfer learning, leading to high computational costs and the risk of catastrophic forgetting. To address these challenges, we propose DD-SAM2, an efficient adaptation framework for SAM2 that incorporates a Depthwise-Dilated Adapter (DD-Adapter) to enhance multi-scale feature extraction with minimal parameter overhead. This design enables effective fine-tuning of SAM2 on medical videos with limited training data. Unlike existing adapter-based methods focused solely on static images, DD-SAM2 fully exploits SAM2's streaming memory for medical video objects tracking and segmentation. Comprehensive evaluations on TrackRad2025 (tumor segmentation) and EchoNet-Dynamic (left ventricle tracking) datasets demonstrate superior performance, achieving Dice scores of 0.93±0.04 and 0.97±0.01, respectively. To the best of our knowledge, this work provides an initial attempt at systematically exploring adapter-based fine-tuning strategies for SAM2 applied medical video segmentation and tracking. Code, datasets, and models will be made publicly available at https://github.com/apple1986/DD-SAM2.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 4","pages":""},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12806169/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145999235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Attention-based Spatio-Temporal Neural Operator for Evolving Physics.","authors":"Vispi Karkaria, Doksoo Lee, Yi-Ping Chen, Yue Yu, Wei Chen","doi":"10.1088/2632-2153/ae1277","DOIUrl":"10.1088/2632-2153/ae1277","url":null,"abstract":"<p><p>In scientific machine learning (SciML), a key challenge is learning unknown, evolving physical processes and making predictions across spatio-temporal scales. For example, in real-world manufacturing problems like additive manufacturing, users adjust known machine settings while unknown environmental parameters simultaneously fluctuate. To make reliable predictions, it is desired for a model to not only capture long-range spatio-temporal interactions from data but also adapt to new and unknown environments; traditional machine learning models excel at the first task but often lack physical interpretability and struggle to generalize under varying environmental conditions. To tackle these challenges, we propose the Attention-based Spatio-Temporal Neural Operator (ASNO), a novel architecture that combines separable attention mechanisms for spatial and temporal interactions and adapts to unseen physical parameters. Inspired by the backward differentiation formula (BDF), ASNO learns a transformer for temporal prediction and extrapolation and an attention-based neural operator for handling varying external loads, enhancing interpretability by isolating historical state contributions and external forces, enabling the discovery of underlying physical laws and generalizability to unseen physical environments. Empirical results on SciML benchmarks demonstrate that ASNO outperforms over existing models, establishing its potential for engineering applications, physics discovery, and interpretable machine learning.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 4","pages":""},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13289668/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148319582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Topological machine learning for protein-nucleic acid binding affinity changes upon mutation.","authors":"Xiang Liu, Junjie Wee, Guo-Wei Wei","doi":"10.1088/2632-2153/ae1714","DOIUrl":"10.1088/2632-2153/ae1714","url":null,"abstract":"<p><p>Understanding how protein mutations affect protein-nucleic acid binding is critical for unraveling disease mechanisms and advancing therapies. Current experimental approaches are laborious, and computational methods remain limited in accuracy. To address this challenge, we propose a novel topological machine learning model (TopoML) combining persistent Laplacian (from topological data analysis) with multi-perspective features: physicochemical properties, topological structures, and protein Transformer-derived sequence embeddings. This integrative framework captures robust representations of protein-nucleic acid binding interactions. To validate the proposed method, we employ two datasets, a protein-DNA dataset with 596 single-point amino acid mutations, and a protein-RNA dataset with 710 single-point amino acid mutations. We show that the proposed TopoML model outperforms state-of-the-art methods in predicting mutation-induced binding affinity changes for protein-DNA and protein-RNA complexes.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 4","pages":""},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13523844/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148851608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CAP: Commutative algebra prediction of protein-nucleic acid binding affinities.","authors":"Mushal Zia, Faisal Suwayyid, Yuta Hozumi, JunJie Wee, Hongsong Feng, Guo-Wei Wei","doi":"10.1088/2632-2153/ae29bc","DOIUrl":"10.1088/2632-2153/ae29bc","url":null,"abstract":"<p><p>An accurate prediction of protein-nucleic acid binding affinity is vital for deciphering genomic processes, yet existing approaches often struggle in reconciling high accuracy with interpretability and computational efficiency. In this study, we introduce commutative algebra prediction (CAP) framework, which couples persistent Stanley-Reisner theory with advanced sequence embedding for predicting protein-nucleic acid binding affinities. CAP encodes proteins through transformer-learned embeddings that retain long-range evolutionary context, and represents DNA and RNA with <i>k</i>-mer algebra embeddings derived from persistent facet ideals, which capture fine-scale nucleotide geometry. We demonstrate that CAP surpasses the SVSBI protein-nucleic acid benchmark and, in a further test, maintains reasonable performance on newly curated protein-RNA and protein-nucleic acid datasets. Leveraging only primary sequences, CAP generalizes to any protein-nucleic acid pair with minimal preprocessing, enabling genome-scale analyses without 3D structural data and promising faster virtual screening for drug discovery and protein engineering.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 4","pages":""},"PeriodicalIF":4.2,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13001652/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147500037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mamba time series forecasting with uncertainty quantification.","authors":"Pedro Pessoa, Paul Campitelli, Douglas P Shepherd, S Banu Ozkan, Steve Pressé","doi":"10.1088/2632-2153/adec3b","DOIUrl":"10.1088/2632-2153/adec3b","url":null,"abstract":"<p><p>State space models, such as Mamba, have recently garnered attention in time series forecasting (TSF) due to their ability to capture sequence patterns. However, in electricity consumption benchmarks, Mamba forecasts exhibit a mean error of approximately 8%. Similarly, in traffic occupancy benchmarks, the mean error reaches 18%. This discrepancy leaves us to wonder whether the prediction is simply inaccurate or falls within error given spread in historical data. To address this limitation, we propose a method to quantify the predictive uncertainty of Mamba forecasts. To achieve this, we propose a dual-network framework based on the Mamba architecture for probabilistic forecasting, where one network generates point forecasts while the other estimates predictive uncertainty by modeling variance. We abbreviate our tool, Mamba with probabilistic TSF, as Mamba-ProbTSF and the code for its implementation is available on GitHub https://github.com/PessoaP/Mamba-ProbTSF. Evaluating this approach on synthetic and real-world benchmark datasets, we find Kullback-Leibler divergence between the learned distributions and the data-which, in the limit of infinite data, should converge to zero if the model correctly captures the underlying probability distribution-reduced to the order of 10^-3 for synthetic data and 10^-1 for real-world benchmark. We find that in both the electricity consumption and traffic occupancy benchmark, the true trajectory stays within the predicted uncertainty interval at the two-sigma level about 95% of the time. We further compare Mamba-ProbTSF against leading probabilistic forecast methods, DeepAR and ARIMA, and show that our method consistently achieves lower forecast errors while offering more reliable uncertainty quantification. We end with a consideration of potential limitations, adjustments to improve performance, and considerations for applying this framework to processes for purely or largely stochastic dynamics where the stochastic changes accumulate as observed, for example, in pure Brownian motion or molecular dynamics trajectories.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 3","pages":"035012"},"PeriodicalIF":4.2,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12281171/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144699735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery.","authors":"Yoel Zimmermann, Adib Bazgir, Alexander Al-Feghali, Mehrad Ansari, Joshua Bocarsly, L Catherine Brinson, Yuan Chiang, Defne Circi, Min-Hsueh Chiu, Nathan Daelman, Matthew L Evans, Abhijeet S Gangan, Janine George, Hassan Harb, Ghazal Khalighinejad, Sartaaj Takrim Khan, Sascha Klawohn, Magdalena Lederbauer, Soroush Mahjoubi, Bernadette Mohr, Seyed Mohamad Moosavi, Aakash Naik, Aleyna Beste Ozhan, Dieter Plessers, Aritra Roy, Fabian Schöppach, Philippe Schwaller, Carla Terboven, Katharina Ueltzen, Yue Wu, Shang Zhu, Jan Janssen, Calvin Li, Ian Foster, Ben Blaiszik","doi":"10.1088/2632-2153/ae011a","DOIUrl":"10.1088/2632-2153/ae011a","url":null,"abstract":"<p><p>Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 3","pages":"030701"},"PeriodicalIF":4.2,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12492978/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145233532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond Euclid: an illustrated guide to modern machine learning with geometric, topological, and algebraic structures.","authors":"Mathilde Papillon, Sophia Sanborn, Johan Mathe, Louisa Cornelis, Abby Bertics, Domas Buracas, Hansen J Lillemark, Christian Shewmake, Fatih Dinc, Xavier Pennec, Nina Miolane","doi":"10.1088/2632-2153/adf375","DOIUrl":"10.1088/2632-2153/adf375","url":null,"abstract":"<p><p>The enduring legacy of Euclidean geometry underpins classical machine learning, which, for decades, has been primarily developed for data lying in Euclidean space. Yet, modern machine learning increasingly encounters richly structured data that is inherently non-Euclidean. This data can exhibit intricate geometric, topological and algebraic structure: from the geometry of the curvature of space-time, to topologically complex interactions between neurons in the brain, to the algebraic transformations describing symmetries of physical systems. Extracting knowledge from such non-Euclidean data necessitates a broader mathematical perspective. Echoing the 19th-century revolutions that gave rise to non-Euclidean geometry, an emerging line of research is redefining modern machine learning with non-Euclidean structures. Its goal: generalizing classical methods to unconventional data types with geometry, topology, and algebra. In this review, we provide an accessible gateway to this fast-growing field and propose a graphical taxonomy that integrates recent advances into an intuitive unified framework. We subsequently extract insights into current challenges and highlight exciting opportunities for future development in this field.</p>","PeriodicalId":33757,"journal":{"name":"Machine Learning Science and Technology","volume":"6 3","pages":"031002"},"PeriodicalIF":4.6,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12315666/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144776367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}