Patterns最新文献_第5页

Five views on the foundations of data science. 关于数据科学基础的五种观点。

IF 10.8

Patterns Pub Date : 2026-06-12 DOI: 10.1016/j.patter.2026.101566

Bruce S Kristal, Melissa D McCradden, Jeyan Thiyagalingam, Zijun Zhang, Carole Goble

引用次数: 0

Graphlet- and motif-based link prediction in large networks. 基于Graphlet和motif的大型网络链路预测。

IF 10.8

Patterns Pub Date : 2026-06-11 eCollection Date: 2026-07-10 DOI: 10.1016/j.patter.2026.101586

Wayne B Hayes, Kimia Yazdani, S M A Nahian, Ezra Alemu

引用次数: 0

SelfCheck-Eval: A multi-module framework for zero-resource hallucination detection in large language models. SelfCheck-Eval：一个用于大型语言模型中零资源幻觉检测的多模块框架。

IF 10.8

Patterns Pub Date : 2026-06-05 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101569

Diyana Muhammed, Giusy Giulia Tuccari, Gollam Rabby, Sören Auer, Sahar Vahdati

{"title":"SelfCheck-Eval: A multi-module framework for zero-resource hallucination detection in large language models.","authors":"Diyana Muhammed, Giusy Giulia Tuccari, Gollam Rabby, Sören Auer, Sahar Vahdati","doi":"10.1016/j.patter.2026.101569","DOIUrl":"10.1016/j.patter.2026.101569","url":null,"abstract":"Large language models (LLMs) have achieved considerable progress across diverse applications, yet their tendency to generate incorrect or fabricated content, commonly termed hallucinations, remains a fundamental obstacle to reliable deployment in high-stakes domains. Existing detection benchmarks are confined to general-knowledge settings, leaving specialized fields, where accuracy is important, underexplored. To address this gap, we introduce the American Invitational Mathematics Examination (AIME) Math Hallucination dataset, a benchmark for evaluating mathematical reasoning hallucinations, and propose SelfCheck-Eval, an LLM-agnostic, black-box detection framework compatible with open- and closed-source LLMs. The framework integrates three independent modules, semantic, specialized detection, and contextual consistency, into a suitable architecture. Systematic evaluation reveals a noticeable performance gap: existing methods perform well on biographical content but struggle with mathematical reasoning, a deficit that continues across natural language inference (NLI) fine-tuning, preference learning, and process supervision paradigms. These findings expose fundamental limitations of current approaches and motivate the development of specialized, black-box-compatible methods for trustworthy LLM deployment.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 6","pages":"101569"},"PeriodicalIF":10.8,"publicationDate":"2026-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13280721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148296763","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

Tina: A diffusion neural network for generating personalized AI models from text prompts. 蒂娜：从文本提示生成个性化人工智能模型的扩散神经网络。

IF 10.8

Patterns Pub Date : 2026-05-29 eCollection Date: 2026-07-10 DOI: 10.1016/j.patter.2026.101571

Zexi Li, Lingzhi Gao, Dongqi Cai, Nicholas D Lane, Chao Wu

引用次数: 0

EnzymeHunter: Achieving fine-grained enzyme function prediction with a hierarchically aware contrastive learning framework. 酶猎人：通过层次感知对比学习框架实现细粒度酶功能预测。

IF 10.8

Patterns Pub Date : 2026-05-28 eCollection Date: 2026-07-10 DOI: 10.1016/j.patter.2026.101567

Guoxin Cao, Jian Ouyang, Xiangyi Xiong, Changle Liu, Yi Zhang, Siqi Yang, Tieliu Shi, Jun Wu

{"title":"EnzymeHunter: Achieving fine-grained enzyme function prediction with a hierarchically aware contrastive learning framework.","authors":"Guoxin Cao, Jian Ouyang, Xiangyi Xiong, Changle Liu, Yi Zhang, Siqi Yang, Tieliu Shi, Jun Wu","doi":"10.1016/j.patter.2026.101567","DOIUrl":"10.1016/j.patter.2026.101567","url":null,"abstract":"Accurate enzyme function annotation is a grand challenge due to the vast number of uncharacterized proteins and the difficulty of distinguishing subtle functions. We introduce EnzymeHunter, a deep-learning framework that achieves fine-grained prediction via a hierarchically aware contrastive learning strategy. By integrating sequence and structural information and using the Enzyme Commission (EC) hierarchy to guide its loss function, our model learns a functionally coherent embedding space where distances reflect precise levels of catalytic similarity. EnzymeHunter significantly outperforms state-of-the-art models, particularly in challenging scenarios, achieving fine-grained precision down to the fourth EC level, maintaining robust performance in low-homology cases, and accurately predicting rare enzyme classes. In a proteome-wide application to Thermus thermophilus, EnzymeHunter discovered novel catalytic functions, one of which was subsequently validated by an independent UniProt update. Furthermore, our model is interpretable, with predictions guided by learned attention on mechanistically critical functional sites.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 7","pages":"101567"},"PeriodicalIF":10.8,"publicationDate":"2026-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13366525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148449615","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

DuoMod-Net: Logarithmic balancing and geometric refinement for imbalanced semi-supervised medical image segmentation. DuoMod-Net：不平衡半监督医学图像分割的对数平衡和几何细化。

IF 10.8

Patterns Pub Date : 2026-05-27 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101570

Wang Bo, Along He, Ting Xue, Yue Zhang, Yi Xiao, Shiyuan Liu, Shaohua Kevin Zhou

{"title":"DuoMod-Net: Logarithmic balancing and geometric refinement for imbalanced semi-supervised medical image segmentation.","authors":"Wang Bo, Along He, Ting Xue, Yue Zhang, Yi Xiao, Shiyuan Liu, Shaohua Kevin Zhou","doi":"10.1016/j.patter.2026.101570","DOIUrl":"10.1016/j.patter.2026.101570","url":null,"abstract":"Class imbalance in semi-supervised medical image segmentation poses a dual challenge: it not only compromises feature learning for tail classes but also introduces significant bias in loss gradients toward the predominant background class. To address these challenges, we introduce duo-component modulation network (DuoMod-Net), a synergistic learning framework integrating two specialized components. The first component, relative logarithmic modulation (RLM), addresses the dominant gradient bias by decoupling the background magnitude from foreground balancing. It establishes the background as a neutral pivot and then applies a relative, logarithmic scaling anchored by robust percentiles to preserve the dynamic range among the foreground organs. Concurrently, the second component, disagreement-driven adaptive feature refinement (DAFR), functions as a geometric regularization mechanism. It leverages intrinsic inter-model disagreement to selectively expand the feature space during training, forcing the decision boundary to recede. This expansion is removed at inference, establishing a safety margin that enhances detection reliability. Extensive validation across varying data regimes (5%, 10%, and 20%) demonstrates that DuoMod-Net yields substantial improvements on tail classes, increases detection reliability by minimizing catastrophic failures, and maintains robust zero-shot generalization on unseen datasets.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 6","pages":"101570"},"PeriodicalIF":10.8,"publicationDate":"2026-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13280726/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148296658","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

SHIELD: A weakly supervised graph attention neural network for decoding disease-relevant cell-cell interactions. 用于解码疾病相关细胞-细胞相互作用的弱监督图注意神经网络。

IF 10.8

Patterns Pub Date : 2026-05-22 eCollection Date: 2026-07-10 DOI: 10.1016/j.patter.2026.101562

Vivek Sehra, Benjamin Ruf, Gabriel Duval, Sepideh Babaei, Manfred Claassen

{"title":"SHIELD: A weakly supervised graph attention neural network for decoding disease-relevant cell-cell interactions.","authors":"Vivek Sehra, Benjamin Ruf, Gabriel Duval, Sepideh Babaei, Manfred Claassen","doi":"10.1016/j.patter.2026.101562","DOIUrl":"10.1016/j.patter.2026.101562","url":null,"abstract":"Multiplexed tissue imaging enables detailed study of cell-cell interactions in disease, yet systematic, interpretable, and supervised computational methods for inferring such interactions remain scarce. We present SHIELD (spatially enhanced immune landscape decoding), a graph attention network framework that quantifies disease-relevant cell-cell interactions through learned attention scores, without relying on prior biological assumptions such as ligand-receptor databases. Validated across three multiplexed tissue imaging datasets-hepatocellular carcinoma (HCC), colorectal cancer (CRC), and type 1 diabetes (T1D)-SHIELD identifies rare mucosal-associated invariant T (MAIT) cell-macrophage interactions in HCC, suppressive CD8+ T cell-macrophage interactions enriched in CRC non-responders, and β cell interactions with cytotoxic and helper T cells across T1D disease stages. In all contexts, SHIELD reconstructs known and biologically meaningful interactions, offering a robust, interpretable tool for spatial tissue analysis and data-driven mechanistic discovery.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 7","pages":"101562"},"PeriodicalIF":10.8,"publicationDate":"2026-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13366524/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148449672","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

H3BERTa: A CDR-H3-specific language model for antibody repertoire analysis. H3BERTa：用于抗体库分析的cdr - h3特异性语言模型。

IF 10.8

Patterns Pub Date : 2026-05-20 eCollection Date: 2026-07-10 DOI: 10.1016/j.patter.2026.101561

Chiara Rodella, Thomas Lemmin

{"title":"H3BERTa: A CDR-H3-specific language model for antibody repertoire analysis.","authors":"Chiara Rodella, Thomas Lemmin","doi":"10.1016/j.patter.2026.101561","DOIUrl":"10.1016/j.patter.2026.101561","url":null,"abstract":"Antibodies are central to immune defense and therapeutic design, yet predicting functional sequences remains challenging. Deep learning models trained on full variable regions often struggle due to sparse experimental data, signal dilution from conserved framework residues, and extreme diversity of hypervariable loops. The heavy-chain complementarity-determining region 3 (CDR-H3) is the most variable segment, shaping antigen specificity and immune diversity. Here, we present H3BERTa, a language model trained solely on CDR-H3 sequences to assess the extent of biological information encoded by this region. H3BERTa embeddings recapitulate immunologically relevant features, including J-gene usage, inferred B cell maturation state, and antigen binding. Pseudo-perplexity profiles enable repertoire analysis, distinguishing healthy from human immunodeficiency virus type 1 (HIV-1)-derived sequences and suggesting measurable immune response signatures. These embeddings support classifiers for broadly neutralizing antibodies using limited labeled data, highlighting utility for antibody discovery. CDR-H3 alone encodes a rich immunological signal, which H3BERTa captures, offering a focused tool for repertoire analysis and antibody engineering.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 7","pages":"101561"},"PeriodicalIF":10.8,"publicationDate":"2026-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13366522/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148449698","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

Spacing effect improves generalization in biological and artificial systems. 间距效应提高了生物系统和人工系统的泛化。

IF 10.8

Patterns Pub Date : 2026-05-19 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101564

Guanglong Sun, Ning Huang, Hongwei Yan, Jun Zhou, Qian Li, Bo Lei, Yi Zhong, Liyuan Wang

{"title":"Spacing effect improves generalization in biological and artificial systems.","authors":"Guanglong Sun, Ning Huang, Hongwei Yan, Jun Zhou, Qian Li, Bo Lei, Yi Zhong, Liyuan Wang","doi":"10.1016/j.patter.2026.101564","DOIUrl":"10.1016/j.patter.2026.101564","url":null,"abstract":"Generalization is a fundamental criterion for evaluating learning effectiveness, a domain where biological intelligence excels yet artificial intelligence faces challenges. In biological learning and memory, the well-documented spacing effect shows that appropriately spaced intervals between learning trials significantly improve behavioral performance. While multiple theories have been proposed to explain its underlying mechanisms, one compelling hypothesis is that spaced training promotes integration of input and innate variations, thereby enhancing generalization to novel but related scenarios. Here, we examine this hypothesis by introducing a bio-inspired spacing effect into artificial neural networks, integrating input and innate variations across spaced intervals at neuronal, synaptic, and network levels. These spaced ensemble strategies yield significant performance gains across benchmark datasets and network architectures. Biological experiments on Drosophila further validate the complementary effect of appropriate variations and spaced intervals in improving generalization, which together reveal a convergent computational principle of biological learning and machine learning.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 6","pages":"101564"},"PeriodicalIF":10.8,"publicationDate":"2026-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13280723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148296685","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

Neural rhythms as priors of speech computations. 神经节律作为言语计算的先验。

IF 10.8

Patterns Pub Date : 2026-05-19 eCollection Date: 2026-08-14 DOI: 10.1016/j.patter.2026.101563

Nand Chandravadia, Nabil Imam

引用次数: 0