Patterns最新文献_第3页

Uncovering smooth structures in single-cell data with neighbor embeddings guided by predictability-computability-stability. 基于可预测性-可计算性-稳定性的邻域嵌入，揭示单细胞数据中的光滑结构。

IF 10.8

Patterns Pub Date : 2026-07-29 eCollection Date: 2026-08-14 DOI: 10.1016/j.patter.2026.101621

Rong Ma, Xi Li, Jingyuan Hu, Bin Yu

{"title":"Uncovering smooth structures in single-cell data with neighbor embeddings guided by predictability-computability-stability.","authors":"Rong Ma, Xi Li, Jingyuan Hu, Bin Yu","doi":"10.1016/j.patter.2026.101621","DOIUrl":"10.1016/j.patter.2026.101621","url":null,"abstract":"Single-cell sequencing enables detailed study of cell-state transitions, but extracting smooth, low-dimensional structures from noisy, high-dimensional data remains challenging. Neighbor embedding (NE) algorithms, such as t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP), are widely used to embed high-dimensional single-cell data into low dimensions, but they often introduce distortions that can lead to misleading interpretations. To address these challenges, we build on the predictability-computability-stability (PCS) framework for reliable and reproducible data-driven discoveries. First, we systematically evaluate popular NE algorithms through empirical and theoretical analyses, revealing their key limitations such as algorithmic artifacts and instability. We then introduce NESS, a principled and interpretable machine learning approach that improves NE representations by leveraging algorithmic stability, enabling more robust inference of smooth biological structures from single-cell data. Finally, we apply NESS to multiple datasets, including studies of pluripotent stem cell differentiation, organoid development, and diverse tissue-specific lineages. Across these settings, NESS consistently yields biologically meaningful insights.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 8","pages":"101621"},"PeriodicalIF":10.8,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13494638/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799055","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

Revealing hidden material composition via physics-induced deep learning for precision clinical diagnosis. 通过物理诱导的深度学习揭示隐藏的物质成分，用于精确的临床诊断。

IF 10.8

Patterns Pub Date : 2026-07-28 eCollection Date: 2026-08-14 DOI: 10.1016/j.patter.2026.101620

Mengyang Liu, Jiachen Liu, Qingyang Liu, Xiangzhi Bai

{"title":"Revealing hidden material composition via physics-induced deep learning for precision clinical diagnosis.","authors":"Mengyang Liu, Jiachen Liu, Qingyang Liu, Xiangzhi Bai","doi":"10.1016/j.patter.2026.101620","DOIUrl":"10.1016/j.patter.2026.101620","url":null,"abstract":"Material-composition information extracted from spectral computed tomography (CT) images facilitates clinical diagnosis by characterizing pathological tissues. However, the complexity of human anatomy and the diversity of tissue types make precise material quantification from single-energy CT (SECT) highly challenging. Here, we propose an X-ray imaging induced multi-material decomposition (MMDX) framework. By integrating the physical principles of photoelectric effect and Compton scattering into a deep-learning network architecture, MMDX achieves superior performance on both phantom and clinical patient datasets, with a 12.92-dB improvement in peak signal-to-noise ratio (PSNR) and a 3.94% increase in volume fraction accuracy. To evaluate the clinical utility of MMDX, we constructed a large-scale clinical CT dataset with 1,637,738 CT images from 7,629 patients. MMDX demonstrates superior performance across 20 downstream tasks, including three diagnosis tasks, two prognosis tasks, and 15 biomarker prediction tasks, showing promise as an accessible AI tool for precision clinical diagnosis.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 8","pages":"101620"},"PeriodicalIF":10.8,"publicationDate":"2026-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13494639/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799081","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

Sampling bias corrections for discrete and Gaussian partial information decompositions. 离散和高斯部分信息分解的抽样偏差校正。

IF 10.8

Patterns Pub Date : 2026-07-23 eCollection Date: 2026-09-11 DOI: 10.1016/j.patter.2026.101619

Gabriel Matías Lorenz, Nicola Marie Engel, Loren Koçillari, Marco Celotto, Davide Orsenigo, Sebastiano Curreli, Simone Blanco Malerba, Andreas K Engel, Christoph Kayser, Tommaso Fellin, Andrea I Luppi, Stefano Panzeri

{"title":"Sampling bias corrections for discrete and Gaussian partial information decompositions.","authors":"Gabriel Matías Lorenz, Nicola Marie Engel, Loren Koçillari, Marco Celotto, Davide Orsenigo, Sebastiano Curreli, Simone Blanco Malerba, Andreas K Engel, Christoph Kayser, Tommaso Fellin, Andrea I Luppi, Stefano Panzeri","doi":"10.1016/j.patter.2026.101619","DOIUrl":"10.1016/j.patter.2026.101619","url":null,"abstract":"Partial information decomposition (PID) has emerged as a principled way to decompose the information carried by neural activity into components identifying whether interactions among neurons or brain areas generate synergistic or redundant information. Here, we demonstrate that empirical measures of synergy and redundancy based on either Gaussian or discrete probability estimators suffer from a substantial limited-sampling estimation bias. This bias is much larger for synergy than for redundancy. The gap between them increases with the number of parameters specifying the probability distributions. We develop procedures that effectively correct for the bias and provide rules of thumb for the sample sizes required to obtain unbiased estimates. We show that, when used on empirical brain datasets, they successfully remove large synergy biases across species, recording modalities, and experimental designs. Our bias corrections extend the range of neuroscience questions and experimental designs addressable with PID and allow accurate comparisons between synergy and redundancy.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 9","pages":"101619"},"PeriodicalIF":10.8,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13576656/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978275","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

Interpretable machine learning reveals hemispheric asymmetry of state switching in the suprachiasmatic nucleus. 可解释的机器学习揭示了视交叉上核状态切换的半球不对称。

IF 10.8

Patterns Pub Date : 2026-07-22 eCollection Date: 2026-09-11 DOI: 10.1016/j.patter.2026.101617

Zongpeng Zhang, Zichen Wang, Jing Yu, Mingqing Xiao, Haoxuan Li, Zongkun Zhang, Xiheng Fang, Ying Xu, Lei Ma, Zhouchen Lin, Heping Cheng, Xiao-Hua Zhou

{"title":"Interpretable machine learning reveals hemispheric asymmetry of state switching in the suprachiasmatic nucleus.","authors":"Zongpeng Zhang, Zichen Wang, Jing Yu, Mingqing Xiao, Haoxuan Li, Zongkun Zhang, Xiheng Fang, Ying Xu, Lei Ma, Zhouchen Lin, Heping Cheng, Xiao-Hua Zhou","doi":"10.1016/j.patter.2026.101617","DOIUrl":"10.1016/j.patter.2026.101617","url":null,"abstract":"The suprachiasmatic nucleus (SCN) is the master circadian clock in mammals, comprising ∼20,000 neurons organized into a bilaterally symmetric oval structure. System-level time computations in the SCN depend on coordinated spatiotemporal patterns of neuronal activity, yet most prevailing methods perform time-series analyses while disregarding neural spatiotemporal organization. Here, we developed an interpretable machine learning framework for the integrative analysis of large-scale spatiotemporal calcium signals from SCN neurons, with built-in validation and biological interpretability. Applying this framework, we identified distinct neural spatiotemporal states and subtypes whose spatial mapping across hemispheres revealed hemispheric asymmetry, particularly during the subjective day. Circadian timekeeping ability also displayed side specificity, with each hemisphere encoding a full yet unique time feature representation. Attribution analysis further indicated spectral features of calcium signals as the primary discriminative elements underlying this asymmetry. Overall, we demonstrate that hemispheric asymmetry of state switching is a fundamental property of the brain's circadian clock.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 9","pages":"101617"},"PeriodicalIF":10.8,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13576658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148978248","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

mlr3mbo: Bayesian optimization in R. mlr3mbo: R中的贝叶斯优化。

IF 10.8

Patterns Pub Date : 2026-07-21 eCollection Date: 2026-10-09 DOI: 10.1016/j.patter.2026.101614

Marc Becker, Lennart Schneider, Martin Binder, Lars Kotthoff, Bernd Bischl

引用次数: 0

From matching to facilitation: Reframing AI's role in clinical trial enrollment. 从匹配到促进：重塑人工智能在临床试验招募中的作用。

IF 10.8

Patterns Pub Date : 2026-07-10 DOI: 10.1016/j.patter.2026.101591

Adar Yaacov, Einat Levi, Nir Peled

引用次数: 0

A tropical geometry for bounded biochemical state spaces. 有界生化状态空间的热带几何。

IF 10.8

Patterns Pub Date : 2026-07-09 eCollection Date: 2026-10-09 DOI: 10.1016/j.patter.2026.101613

James N Cobley

{"title":"A tropical geometry for bounded biochemical state spaces.","authors":"James N Cobley","doi":"10.1016/j.patter.2026.101613","DOIUrl":"10.1016/j.patter.2026.101613","url":null,"abstract":"Many biochemical measurements define state spaces that are bounded, absorbing, and generically noninvertible yet they are routinely analyzed using categorically mismatched linear and Euclidean frameworks. This categorical mismatch can irretrievably obscure biological structure. This work formalizes the minimal algebraic properties imposed by bounded biochemical state spaces, demonstrating that a bounded tropical semiring provides a natural category match by replacing additive linear structure with order-based, piecewise-linear operations that encode dominance, saturation, and path-dependence without contradiction. To instantiate this framework, measurement-native tropical geometric analysis was applied to cysteine redox proteomic data (Oxi-Shapes). Oxi-Shapes represents cysteine oxidation occupancies as a bounded scalar field over a discrete lattice of invariant residue identities, enabling analysis of both ensemble-level organization and site-wise admissible transitions. As demonstrated on empirical cysteine redox proteomic data, categorically correct algebraic structures exposed geometric features that remained inaccessible under unbounded linear representations.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 10","pages":"101613"},"PeriodicalIF":10.8,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13674305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149216921","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

MedicalAgentsBench for complex medical reasoning: Comparing internalized reasoning models versus externalized agent-based frameworks. 用于复杂医学推理的MedicalAgentsBench：比较内部化推理模型与基于外部化代理的框架。

IF 10.8

Patterns Pub Date : 2026-07-08 eCollection Date: 2026-10-09 DOI: 10.1016/j.patter.2026.101610

Yanjun Shao, Xiangru Tang, Jiwoong Sohn, Jiapeng Chen, Yuxuan Liao, Jiayi Zhang, Jinyu Xiang, Fang Wu, Yilun Zhao, Chenglin Wu, Wenqi Shi, Arman Cohan, Mark Gerstein

{"title":"MedicalAgentsBench for complex medical reasoning: Comparing internalized reasoning models versus externalized agent-based frameworks.","authors":"Yanjun Shao, Xiangru Tang, Jiwoong Sohn, Jiapeng Chen, Yuxuan Liao, Jiayi Zhang, Jinyu Xiang, Fang Wu, Yilun Zhao, Chenglin Wu, Wenqi Shi, Arman Cohan, Mark Gerstein","doi":"10.1016/j.patter.2026.101610","DOIUrl":"10.1016/j.patter.2026.101610","url":null,"abstract":"Complex medical reasoning requires integrating heterogeneous clinical evidence across multiple inference steps. Large language models (LLMs) now approach this through two routes: internalized reasoning and externalized agent scaffolding (frameworks that decompose problems collaboratively among multiple LLMs). To determine whether these routes are exclusive or complementary, we introduce MedicalAgentsBench, a filtered benchmark of 862 complex clinical questions drawn from the union of eight medical datasets via difficulty-aware curation and contamination screening. Evaluating three internalized reasoning models (DeepSeek-R1, o1-mini, and o3-mini), seven base models, and nine externalized agent-based methods, we find that internalized and externalized approaches each independently improve performance and that their benefits compound: the highest accuracy is achieved by layering agent workflows onto an internalized reasoning model (i.e., o3-mini + MDAgents with 35.1%). Pareto analysis shows this combination dominates the cost-performance frontier; moreover, lightweight optimization on inexpensive models offers an entry point for resource-constrained settings.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 10","pages":"101610"},"PeriodicalIF":10.8,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13674309/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149217022","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

OscillomeR infers ultradian oscillations and targets of the Hes family. OscillomeR推断出he族的超振荡和靶标。

IF 10.8

Patterns Pub Date : 2026-07-08 eCollection Date: 2026-09-11 DOI: 10.1016/j.patter.2026.101612

Xiaochan Xu, Palle Serup

引用次数: 0

BioMaster: Multi-agent system for automated bioinformatics analysis workflow. BioMaster：用于自动化生物信息学分析工作流程的多代理系统。

IF 10.8

Patterns Pub Date : 2026-07-07 eCollection Date: 2026-08-14 DOI: 10.1016/j.patter.2026.101611

Houcheng Su, Junning Feng, Yawen Lu, Yucheng Xu, Jinming Yang, Haojie Lu, Jixin Yang, Xu Yang, Sirui Xie, Weicai Long, Chengrui Wang, Yusen Hou, Tingyu Zhu, Yanlin Zhang

{"title":"BioMaster: Multi-agent system for automated bioinformatics analysis workflow.","authors":"Houcheng Su, Junning Feng, Yawen Lu, Yucheng Xu, Jinming Yang, Haojie Lu, Jixin Yang, Xu Yang, Sirui Xie, Weicai Long, Chengrui Wang, Yusen Hou, Tingyu Zhu, Yanlin Zhang","doi":"10.1016/j.patter.2026.101611","DOIUrl":"10.1016/j.patter.2026.101611","url":null,"abstract":"The growing volume and complexity of biological data have made bioinformatics workflows increasingly labor-intensive, error-prone, and difficult to scale. Large language model-based agents offer potential for automation but often fail in complex, multi-step analyses because of limited robustness. We present BioMaster, a multi-agent framework that integrates workflow planning, execution, error recovery, and output validation. BioMaster incorporates a dual retrieval-augmented design to leverage domain knowledge for tool selection, parameterization, and adaptation across tasks. A dedicated debug agent supports real-time error detection and correction, while memory optimization enables long, multi-stage workflows. In benchmarking across 49 bioinformatics tasks spanning 102 tools, BioMaster completed substantially more workflows than did existing automated systems, particularly in complex, interdependent pipelines. BioMaster supports both proprietary and open-source language models, enabling flexible deployment across different computational settings.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 8","pages":"101611"},"PeriodicalIF":10.8,"publicationDate":"2026-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13494596/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148799023","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