ArXiv最新文献

{"title":"Frugal inference for control.","authors":"Itzel Olivos-Castillo, Paul Schrater, Xaq Pitkow","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>A key challenge in advancing artificial intelligence is achieving the right balance between utility maximization and resource use by both external movement and internal computation. While this trade-off has been studied in fully observable settings, our understanding of resource efficiency in partially observable environments remains limited. Motivated by this challenge, we develop a version of the POMDP framework where the information gained through inference is treated as a resource that must be optimized alongside task performance and motion effort. By solving this problem in environments described by linear-Gaussian dynamics, we uncover fundamental principles of resource efficiency. Our study reveals a phase transition in the inference, switching from a Bayes-optimal approach to one that strategically leaves some uncertainty unresolved. This frugal behavior gives rise to a structured family of equally effective strategies, facilitating adaptation to later objectives and constraints overlooked during the original optimization. We illustrate the applicability of our framework and the generality of the principles we derived using two nonlinear tasks. Overall, this work provides a foundation for a new type of rational computation that both brains and machines could use for effective but resource-efficient control under uncertainty.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11581108/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142689935","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":"Full-Head Segmentation of MRI with Abnormal Brain Anatomy: Model and Data Release.","authors":"Andrew M Birnbaum, Adam Buchwald, Peter Turkeltaub, Adam Jacks, George Carr, Shreya Kannan, Yu Huang, Abhisheck Datta, Lucas C Parra, Lukas A Hirsch","doi":"","DOIUrl":"","url":null,"abstract":"<p><strong>Purpose: </strong>The goal of this work was to develop a deep network for whole-head segmentation including clinical MRIs with abnormal anatomy, and compile the first public benchmark dataset for this purpose. We collected 98 MRIs with volumetric segmentation labels for a diverse set of human subjects including normal, as well as abnormal anatomy in clinical cases of stroke and disorders of consciousness.</p><p><strong>Approach: </strong>Training labels were generated by manually correcting initial automated segmentations for skin/scalp, skull, CSF, gray matter, white matter, air cavity and extracephalic air. We developed a \"MultiAxial\" network consisting of three 2D U-Net that operate independently in sagittal, axial and coronal planes and are then combined to produce a single 3D segmentation.</p><p><strong>Results: </strong>The MultiAxial network achieved a test-set Dice scores of 0.88±0.04 (median ± interquartile range) on whole head segmentation including gray and white matter. This compared to 0.86 ± 0.04 for Multipriors and 0.79 ± 0.10 for SPM12, two standard tools currently available for this task. The MultiAxial network gains in robustness by avoiding the need for coregistration with an atlas. It performed well in regions with abnormal anatomy and on images that have been de-identified. It enables more accurate and robust current flow modeling when incorporated into ROAST, a widely-used modeling toolbox for transcranial electric stimulation.</p><p><strong>Conclusions: </strong>We are releasing a new state-of-the-art tool for whole-head MRI segmentation in abnormal anatomy, along with the largest volume of labeled clinical head MRIs including labels for non-brain structures. Together the model and data may serve as a benchmark for future efforts.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066710","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":"Learning residue level protein dynamics with multiscale Gaussians.","authors":"Mihir Bafna, Bowen Jing, Bonnie Berger","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Many methods have been developed to predict static protein structures, however understanding the <i>dynamics</i> of protein structure is essential for elucidating biological function. While molecular dynamics (MD) simulations remain the <i>in silico</i> gold standard, its high computational cost limits scalability. We present DynaProt, a lightweight, SE(3)-invariant framework that predicts rich descriptors of protein dynamics directly from static structures. By casting the problem through the lens of multivariate Gaussians, DynaProt estimates dynamics at two complementary scales: (1) per-residue marginal anisotropy as 3 × 3 covariance matrices capturing local flexibility, and (2) joint scalar covariances encoding pairwise dynamic coupling across residues. From these dynamics outputs, DynaProt achieves high accuracy in predicting residue-level flexibility (RMSF) and, remarkably, enables reasonable reconstruction of the full covariance matrix for fast ensemble generation. Notably, it does so using orders of magnitude fewer parameters than prior methods. Our results highlight the potential of direct protein dynamics prediction as a scalable alternative to existing methods.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066695","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":"OTMol: Robust Molecular Structure Comparison via Optimal Transport.","authors":"Xiaoqi Wei, Xuhang Dai, Yaqi Wu, Yanxiang Zhao, Yingkai Zhang, Zixuan Cang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Root-mean-square deviation (RMSD) is widely used to assess structural similarity in systems ranging from flexible ligand conformers to complex molecular cluster configurations. Despite its wide utility, RMSD calculation is often challenged by inconsistent atom ordering, indistinguishable configurations in molecular clusters, and potential chirality inversion during alignment. These issues highlight the necessity of accurate atom-to-atom correspondence as a prerequisite for meaningful alignment. Traditional approaches often rely on heuristic cost matrices combined with the Hungarian algorithm, yet these methods underutilize the rich intra-molecular structural information and may fail to generalize across chemically diverse systems. In this work, we introduce OTMol, a method that formulates the molecular alignment task as a fused supervised Gromov-Wasserstein (fsGW) optimal transport problem. By leveraging the intrinsic geometric and topological relationships within each molecule, OTMol eliminates the need for manually defined cost functions and enables a principled, data-driven matching strategy. Importantly, OTMol preserves key chemical features such as molecular chirality and bond connectivity consistency. We evaluate OTMol across a wide range of molecular systems, including Adenosine triphosphate, Imatinib, lipids, small peptides, and water clusters, and demonstrate that it consistently achieves low RMSD values while preserving computational efficiency. Importantly, OTMol maintains molecular integrity by enforcing one-to-one mappings between entire molecules, thereby avoiding erroneous many-to-one alignments that often arise in comparing molecular clusters. Our results underscore the utility of optimal transport theory for molecular alignment and offer a generalizable framework applicable to structural comparison tasks in cheminformatics, molecular modeling, and related disciplines.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425015/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066687","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":"Clinical Metadata Guided Limited-Angle CT Image Reconstruction.","authors":"Yu Shi, Shuyi Fan, Changsheng Fang, Shuo Han, Haodong Li, Li Zhou, Bahareh Morovati, Dayang Wang, Hengyong Yu","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Limited-angle computed tomography (LACT) offers improved temporal resolution and reduced radiation dose for cardiac imaging, but suffers from severe artifacts due to truncated projections. To address the ill-posedness of LACT reconstruction, we propose a two-stage diffusion framework guided by structured clinical metadata. In the first stage, a transformer-based diffusion model conditioned exclusively on metadata, including acquisition parameters, patient demographics, and diagnostic impressions, generates coarse anatomical priors from noise. The second stage further refines the images by integrating both the coarse prior and metadata to produce high-fidelity results. Physics-based data consistency is enforced at each sampling step in both stages using an Alternating Direction Method of Multipliers module, ensuring alignment with the measured projections. Extensive experiments on both synthetic and real cardiac CT datasets demonstrate that incorporating metadata significantly improves reconstruction fidelity, particularly under severe angular truncation. Compared to existing metadata-free baselines, our method achieves superior performance in SSIM, PSNR, nMI, and PCC. Ablation studies confirm that different types of metadata contribute complementary benefits, particularly diagnostic and demographic priors under limited-angle conditions. These findings highlight the dual role of clinical metadata in improving both reconstruction quality and efficiency, supporting their integration into future metadata-guided medical imaging frameworks.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12425017/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145066627","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":"Beyond Scalar Metrics: Functional Data Analysis of Postprandial Continuous Glucose Monitoring in the AEGIS Study.","authors":"Marcos Matabuena, Joseph Sartini, Francisco Gude","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Postprandial glucose collected through continuous glucose monitoring (CGM) provides critical information for assessing metabolic capacity and guiding dietary recommendations. Traditional approaches summarize these data into scalar measures, such as 2-hour AUC or peak glucose, potentially overlooking temporal dynamics. We propose analyzing entire CGM trajectories using multilevel functional data analysis (FDA), which accounts for the smooth, hierarchical nature of glucose responses. Applying these methods to AEGIS study participants without diabetes, we illustrate how FDA characterizes variability in postprandial responses and links dietary/patient characteristics to glucose dynamics. We further extend the R² metric to hierarchical functional models to quantify explanatory power. Our results show that dietary effects vary across the 6-hour postprandial window-for example, fiber blunts responses after 90 minutes, while fats reduce early rises within 50 minutes. Moreover, metabolic responses differ between normoglycemic and prediabetic individuals. These findings demonstrate that functional approaches reveal temporal and stratified insights into postprandial glucose regulation that scalar methods cannot capture.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11142320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141201632","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":"Many Will Enter, Few Will Win: Cost and Sensitivity of Exploratory Dynamics.","authors":"Elena F Koslover, Milo M Lin, Rob Phillips","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>A variety of biomolecular systems rely on exploratory dynamics to reach target locations or states within a cell. Without a mechanism to remotely sense and move directly towards a target, the system must sample over many paths, often including resetting transitions back to the origin. We investigate how exploratory dynamics can confer an important functional benefit: the ability to respond to small changes in parameters with large shifts in the steady-state behavior. However, such enhanced sensitivity comes at a cost: resetting cycles require energy dissipation in order to push the system out of its equilibrium steady state. We focus on minimalist models for two concrete examples: translational proofreading in the ribosome and microtubule length control via dynamic instability to illustrate the trade-offs between energetic cost and sensitivity. In the former, a driven hydrolysis step enhances the ability to distinguish between substrates and decoys with small binding energy differences. In the latter, resetting cycles enable catalytic control, with the steady-state length distribution modulated by sub-stoichiometric concentrations of a reusable catalyst. Synthesizing past models of these well-studied systems, we show how path-counting and circuit mapping approaches can be used to address fundamental questions such as the number of futile cycles inherent in translation and the steady-state length distribution of a dynamically unstable polymer. In both cases, a limited amount of thermodynamic driving is sufficient to yield a qualitative transition to a system with enhanced sensitivity, enabling accurate discrimination and catalytic control at a modest energetic cost.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12407632/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002112","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":"Improving Biomedical Knowledge Graph Quality: A Community Approach.","authors":"Katherina G Cortes, Shilpa Sundar, Sarah Gehrke, Keenan Manpearl, Junxia Lin, Daniel Robert Korn, Harry Caufield, Kevin Schaper, Justin Reese, Kushal Koirala, Lawrence E Hunter, E Kathleen Carter, Marcello DeLuca, Arjun Krishnan, Chris Mungall, Melissa Haendel","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Biomedical knowledge graphs (KGs) are widely used across research and translational settings, yet their design decisions and implementation are often opaque. Unlike ontologies that more frequently adhere to established creation principles, biomedical KGs lack consistent practices for construction, documentation, and dissemination. To address this gap, we introduce a set of evaluation criteria grounded in widely accepted data standards and principles from related fields. We apply these criteria to 16 biomedical KGs, revealing that even those that appear to align with best practices often obscure essential information required for external reuse. Moreover, biomedical KGs, despite pursuing similar goals and ingesting the same sources in some cases, display substantial variation in models, source integration, and terminology for node types. Reaping the potential benefits of knowledge graphs for biomedical research while reducing duplicated effort requires community-wide adoption of shared criteria and maturation of standards such as Biolink and KGX. Such improvements in transparency and standardization are essential for creating long-term reusability, improving comparability across resources, providing a rigorous foundation for artificial intelligence models, and enhancing the overall utility of KGs within biomedicine.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12407614/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002185","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":"Practical indistinguishability in a gene regulatory network inference problem, a case study.","authors":"Cody E FitzGerald, Shelley Reich, Victor Agaba, Arjun Mathur, Michael S Werner, Niall M Mangan","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Computationally inferring mechanistic insights and underlying control structures from typical biological data is a challenging pursuit. The technical reasons for this are multifaceted-and we delve into them in depth here, but they are easy to understand and involve both the data and model development. Even the highest-quality experimental data come with challenges. There are always sources of noise, a limit to how often we can measure the system, and we can rarely measure all the relevant states that participate in the full underlying complexity. There are usually sources of uncertainty in model development, which give rise to multiple competing model structures. To underscore the need for further analysis of structural uncertainty in modeling, we use a meta-analysis across six journals covering mathematical biology and show that a huge number of mathematical models for biological systems are developed each year, but model selection and comparison across model structures appear to be less common. We walk through a case study involving inference of regulatory network structure involved in a developmental decision in the nematode, <i>Pristonchus pacificus</i>. We first examine the <i>practical indistinguishability</i> of a model structure, or the ability to uniquely infer the structure given the data, across a wide range of synthetic data regimes by refitting both the true model structure and several misspecified models. We then use real biological data and compare across 13,824 models-each corresponding to a different regulatory network structure, to determine which regulatory features are supported by the data across three experimental conditions. We find that the best-fitting models for each experimental condition share a combination of features and identify a regulatory network that is common across the model sets for each condition. This model is capable of describing the data across the experimental conditions we considered and exhibits a high degree of positive regulation and interconnectivity between the key regulators, <math><mi>eud-1</mi></math> , <math><mi>sult-1</mi></math> , and <math><mi>nhr-40</mi></math> . While the biological results are specific to the molecular biology of development in <i>Pristonchus pacificus</i>, the general modeling framework and underlying challenges we faced doing this analysis are widespread across biology, chemistry, physics, and many other scientific disciplines.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12407701/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145002093","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":"Ultrasound Autofocusing: Common Midpoint Phase Error Optimization via Differentiable Beamforming.","authors":"Walter Simson, Louise Zhuang, Benjamin N Frey, Sergio J Sanabria, Jeremy J Dahl, Dongwoon Hyun","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>In ultrasound imaging, propagation of an acoustic wavefront through heterogeneous media causes phase aberrations that degrade the coherence of the reflected wavefront, leading to reduced image resolution and contrast. Adaptive imaging techniques attempt to correct this phase aberration and restore coherence, leading to improved focusing of the image. We propose an autofocusing paradigm for aberration correction in ultrasound imaging by fitting an acoustic velocity field to pressure measurements, via optimization of the common midpoint phase error (CMPE), using a straight-ray wave propagation model for beamforming in diffusely scattering media. We show that CMPE induced by heterogeneous acoustic velocity is a robust measure of phase aberration that can be used for acoustic autofocusing. CMPE is optimized iteratively using a differentiable beamforming approach to simultaneously improve the image focus while estimating the acoustic velocity field of the interrogated medium. The approach relies solely on wavefield measurements using a straight-ray integral solution of the two-way time-of-flight without explicit numerical time-stepping models of wave propagation. We demonstrate method performance through in silico simulations, in vitro phantom measurements, and in vivo mammalian models, showing practical applications in distributed aberration quantification, correction, and velocity estimation for medical ultrasound autofocusing.</p>","PeriodicalId":93888,"journal":{"name":"ArXiv","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12265487/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144651455","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}