Patterns最新文献_第2页

TweetyBERT: Automated parsing of birdsong through self-supervised machine learning. TweetyBERT：通过自我监督的机器学习自动解析鸟鸣。

IF 7.4

Patterns Pub Date : 2026-03-03 eCollection Date: 2026-04-10 DOI: 10.1016/j.patter.2025.101491

George Vengrovski, Miranda R Hulsey-Vincent, Melissa A Bemrose, Timothy J Gardner

引用次数: 0

Promoting sustainable human mobility for income segregation mitigation. 促进可持续的人员流动，以缓解收入隔离。

IF 7.4

Patterns Pub Date : 2026-03-02 eCollection Date: 2026-03-13 DOI: 10.1016/j.patter.2025.101477

Yong Chen, Chenlei Liao, Zeen Cai, Wanru Wang, Yingji Xia, Xiqun Michael Chen, Jianjun Wu, Ziyou Gao

{"title":"Promoting sustainable human mobility for income segregation mitigation.","authors":"Yong Chen, Chenlei Liao, Zeen Cai, Wanru Wang, Yingji Xia, Xiqun Michael Chen, Jianjun Wu, Ziyou Gao","doi":"10.1016/j.patter.2025.101477","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101477","url":null,"abstract":"Unraveling urban income segregation fosters social cohesion, urban sustainability, and equitable access to public resources and opportunities for all socioeconomic groups. Here, we show that locations with different segregation levels exhibit biased collective mobility patterns, tending to visit locations with lower segregation levels, which escalate with city size and infrastructure accessibility, and cannot be explained solely by distance and population. Using 1.4 million data points on human mobility, socioeconomic factors, and environmental pollution from 16,093 census tracts in 10 large US cities, we introduce the segregation visitation index to quantify this tendency and develop a human mobility model incorporating segregation constraints and a transfer ensemble optimization component, providing a structural interpretation for the discovered biased mobility. Our results reveal the intricate interplays among urban income segregation, mobility, and environmental exposure, emphasizing the importance of accounting for location-specific mobility differences in developing sustainable income segregation mitigation strategies.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 3","pages":"101477"},"PeriodicalIF":7.4,"publicationDate":"2026-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13100684/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147783418","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

DestinyNet: A deep-learning framework for cell-fate analysis from lineage-tracing single-cell RNA sequencing data. DestinyNet：一个从谱系追踪单细胞RNA测序数据进行细胞命运分析的深度学习框架。

IF 7.4

Patterns Pub Date : 2026-02-20 eCollection Date: 2026-04-10 DOI: 10.1016/j.patter.2025.101471

Zuozhu Liu, Songtao Jiang, Tianxiang Hu, Ziwei Xue, Yuhui Chen, Dengfeng Ruan, Haoxiang Xia, Yang Feng, Jin Hao, Wei Li, Joey Tianyi Zhou, Bing Fang, Jian Wu, Wanlu Liu

{"title":"DestinyNet: A deep-learning framework for cell-fate analysis from lineage-tracing single-cell RNA sequencing data.","authors":"Zuozhu Liu, Songtao Jiang, Tianxiang Hu, Ziwei Xue, Yuhui Chen, Dengfeng Ruan, Haoxiang Xia, Yang Feng, Jin Hao, Wei Li, Joey Tianyi Zhou, Bing Fang, Jian Wu, Wanlu Liu","doi":"10.1016/j.patter.2025.101471","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101471","url":null,"abstract":"Unraveling cell-development dynamics, including lineage commitment, differentiation, and disease progression, is fundamental to biology. Despite advances in single-cell omics and barcoding technologies, comprehensive frameworks for accurate, robust, and scalable cell-fate analysis using lineage-tracing single-cell RNA sequencing (LT-scSeq) data remain limited. We introduce DestinyNet, a multi-task deep-learning framework addressing three key challenges: (1) fate clustering, integrating fate and cell-type information; (2) fate flow, depicting dynamic pseudotime trajectories with fate information; and (3) fate prediction, identifying early-stage cell-fate biases. DestinyNet enables end-to-end cell representation learning through cell-relation triplets and is robust across various LT-scSeq data types, including static, cumulative, and dynamic barcoding with single or multiple time points. Experiments on diverse datasets, including hematopoiesis differentiation and fibroblast reprogramming (in vitro and in vivo), demonstrate DestinyNet's effectiveness in multiple fate-analysis tasks.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 4","pages":"101471"},"PeriodicalIF":7.4,"publicationDate":"2026-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083642/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147724042","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

Making neural networks more neural. 让神经网络更神经化。

IF 7.4

Patterns Pub Date : 2026-02-13 DOI: 10.1016/j.patter.2026.101494

Alan W Freeman

引用次数: 0

Creating strong predictive models in oncology. 在肿瘤学领域建立强大的预测模型。

IF 7.4

Patterns Pub Date : 2026-02-13 DOI: 10.1016/j.patter.2026.101492

Michael F Gensheimer

引用次数: 0

BDI-Kit: An AI-powered toolkit for biomedical data harmonization. BDI-Kit：用于生物医学数据协调的人工智能工具包。

IF 7.4

Patterns Pub Date : 2026-02-12 eCollection Date: 2026-04-10 DOI: 10.1016/j.patter.2025.101470

Roque Lopez, Aécio Santos, Christos Koutras, Juliana Freire

{"title":"BDI-Kit: An AI-powered toolkit for biomedical data harmonization.","authors":"Roque Lopez, Aécio Santos, Christos Koutras, Juliana Freire","doi":"10.1016/j.patter.2025.101470","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101470","url":null,"abstract":"The wide availability of biomedical data, coupled with advanced analytics, holds unprecedented promise for scientific discovery and improved patient care; yet, heterogeneity across datasets remains a major barrier. Given the inherent diversity of biomedical domains, one-size-fits-all solutions are impractical. Despite decades of active research and numerous methods for automating data integration, there is a scarcity of open-source tools capable of handling this complexity. To address these challenges, we introduce Biomedical Data Integration and Harmonization Toolkit (BDI-Kit), an extensible toolkit designed for human-AI collaboration that provides a diverse suite of harmonization methods. It offers two complementary interfaces: a Python API that supports the creation of computational pipelines for harmonization and an AI-assisted chat interface that enables domain experts to perform harmonization using natural language. In this paper, we describe BDI-Kit and demonstrate its capabilities through real-world use cases. By simplifying data harmonization, BDI-Kit empowers researchers and practitioners, facilitating effective exploration and accelerating scientific discovery and clinical research.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 4","pages":"101470"},"PeriodicalIF":7.4,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083632/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147723946","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

Evolving reservoir computers reveal bidirectional coupling between predictive power and emergent dynamics. 不断发展的油藏计算机揭示了预测能力和涌现动力之间的双向耦合。

IF 7.4

Patterns Pub Date : 2026-02-06 eCollection Date: 2026-03-13 DOI: 10.1016/j.patter.2025.101457

Hanna M Tolle, Andrea I Luppi, Anil K Seth, Pedro A M Mediano

{"title":"Evolving reservoir computers reveal bidirectional coupling between predictive power and emergent dynamics.","authors":"Hanna M Tolle, Andrea I Luppi, Anil K Seth, Pedro A M Mediano","doi":"10.1016/j.patter.2025.101457","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101457","url":null,"abstract":"Biological neural networks perform complex computations to predict their environment, far exceeding the capabilities of individual neurons. Here, we argue that understanding these computations requires considering emergent dynamics-dynamics that make the whole system \"more than the sum of its parts.\" We examine the relationship between prediction performance and emergence by leveraging quantitative metrics of emergence and modeling environmental time-series prediction within a bio-inspired computational framework called reservoir computing. Notably, three key results reveal a robust bidirectional coupling between prediction performance and emergence: (1) optimizing hyperparameters for performance enhances emergent dynamics, and vice versa; (2) emergent dynamics serve as a highly sufficient and often also necessary condition for prediction success in most environments; and (3) training with larger datasets results in stronger emergent dynamics, encoding task-relevant information. These findings emphasize the importance of emergence-based approaches for studying neural networks-biological or artificial-as they enable network-level insights, complementing traditional single-neuron-based analyses.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 3","pages":"101457"},"PeriodicalIF":7.4,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13100675/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147783913","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

Experimental and machine learning-based exploration of repurposed drugs reveals chemical features underlying phospholipidosis. 基于实验和机器学习的药物再利用探索揭示了磷脂病的化学特征。

IF 7.4

Patterns Pub Date : 2026-02-06 eCollection Date: 2026-04-10 DOI: 10.1016/j.patter.2025.101453

Maria Kuzikov, Adelinn Kalman, Reagon Karki, Jeanette Reinshagen, Johanna Huchting, Kun Qian, Hanna Axelsson, Marianna Tampere, Päivi Östling, Brinton Seashore-Ludlow, Yojana Gadiya, Philip Gribbon, Andrea Zaliani

{"title":"Experimental and machine learning-based exploration of repurposed drugs reveals chemical features underlying phospholipidosis.","authors":"Maria Kuzikov, Adelinn Kalman, Reagon Karki, Jeanette Reinshagen, Johanna Huchting, Kun Qian, Hanna Axelsson, Marianna Tampere, Päivi Östling, Brinton Seashore-Ludlow, Yojana Gadiya, Philip Gribbon, Andrea Zaliani","doi":"10.1016/j.patter.2025.101453","DOIUrl":"10.1016/j.patter.2025.101453","url":null,"abstract":"Phospholipidosis (PLD) is a cellular adverse effect caused by, among other things, cationic amphiphilic drugs. There is interest within pharma discovery to predict this phenomenon, as it can impact the outcome of phenotypic cellular screens and significantly delay drug development processes. The development of accurate and validated machine learning models for predicting drug-induced PLD across different cell lines and research centers could provide a valuable early application tool for the pharmaceutical industry, potentially accelerating drug discovery and reducing the risk of late-stage failures. We report here the assembly, curation, testing, and modeling of one of the largest datasets of repurposed drugs (5,000+) tested for PLD induction on different cell lines. A machine learning classification method was developed and validated to predict whether molecules are prone to induce PLD effects when applied in cell-based screens.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 4","pages":"101453"},"PeriodicalIF":7.4,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147723993","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

UbiQTree: Uncertainty quantification in XAI with tree ensembles. UbiQTree：基于树集成的XAI不确定度量化。

IF 7.4

Patterns Pub Date : 2026-02-04 eCollection Date: 2026-04-10 DOI: 10.1016/j.patter.2025.101454

Akshat Dubey, Aleksandar Anžel, Bahar İlgen, Georges Hattab

引用次数: 0

Variable rate neural compression for sparse detector data. 稀疏检测器数据的可变速率神经压缩。

IF 7.4

Patterns Pub Date : 2026-02-02 eCollection Date: 2026-03-13 DOI: 10.1016/j.patter.2025.101452

Yi Huang, Yeonju Go, Jin Huang, Shuhang Li, Xihaier Luo, Thomas Marshall, Joseph D Osborn, Christopher Pinkenburg, Yihui Ren, Evgeny Shulga, Shinjae Yoo, Byung-Jun Yoon

{"title":"Variable rate neural compression for sparse detector data.","authors":"Yi Huang, Yeonju Go, Jin Huang, Shuhang Li, Xihaier Luo, Thomas Marshall, Joseph D Osborn, Christopher Pinkenburg, Yihui Ren, Evgeny Shulga, Shinjae Yoo, Byung-Jun Yoon","doi":"10.1016/j.patter.2025.101452","DOIUrl":"https://doi.org/10.1016/j.patter.2025.101452","url":null,"abstract":"Particle colliders produce data at extraordinary rates, posing major challenges for transmission and storage. High-throughput compression algorithms are therefore essential. In the sPHENIX experiment taking data at the Relativistic Heavy Ion Collider, a time projection chamber records three-dimensional (3D) particle trajectories that are highly sparse, making conventional learning-free lossy compression ineffective. Convolutional neural networks have surpassed traditional methods in compression ratio and accuracy. However, they fail to exploit sparsity for efficiency. To address these gaps, we present BCAE-VS, a bicephalous convolutional autoencoder with variable compression ratio for sparse data, which adapts compression to input complexity through key-point identification and sparse convolution. BCAE-VS achieves higher accuracy and compression ratios than prior neural approaches while being orders of magnitude smaller. Moreover, its throughput increases with sparsity-a property not observed in other methods. Although it was developed for collider experiments, BCAE-VS readily extends to other sparse data domains, such as light detection and ranging (LiDAR) sensing and 3D microscopy.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 3","pages":"101452"},"PeriodicalIF":7.4,"publicationDate":"2026-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13100687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147783386","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