Patterns最新文献_第7页

Are diffusion models ready for materials discovery in unexplored chemical space? 扩散模型是否准备好在未开发的化学空间中发现材料？

IF 10.8

Patterns Pub Date : 2026-04-13 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101537

Sanghyun Kim, Gihyeon Jeon, Seungwoo Hwang, Jiho Lee, Jisu Jung, Seungwu Han, Sungwoo Kang

引用次数: 0

A framework for reproducibly managing coupled research software and data assets based on shared transformation functions. 基于共享转换功能的可重复管理耦合研究软件和数据资产的框架。

IF 10.8

Patterns Pub Date : 2026-04-13 eCollection Date: 2026-05-08 DOI: 10.1016/j.patter.2026.101493

Patrick Kuckertz, Benjamin Fuchs, Julian Schönau, Hedda Gardian, Kevin Knosala, Eugenio Salvador Arellano Ruiz, Jan Göpfert, Hans Christian Gils, Jann M Weinand, Patrick Jochem, Jochen Linßen, Detlef Stolten

{"title":"A framework for reproducibly managing coupled research software and data assets based on shared transformation functions.","authors":"Patrick Kuckertz, Benjamin Fuchs, Julian Schönau, Hedda Gardian, Kevin Knosala, Eugenio Salvador Arellano Ruiz, Jan Göpfert, Hans Christian Gils, Jann M Weinand, Patrick Jochem, Jochen Linßen, Detlef Stolten","doi":"10.1016/j.patter.2026.101493","DOIUrl":"10.1016/j.patter.2026.101493","url":null,"abstract":"In computational science, coupling research software and data into workflows is essential for addressing complex research questions and ensuring reproducibility. However, current metadata schemas rarely provide sufficient information about data models in software interfaces and datasets, hindering their effective integration into workflows. Additionally, most workflow management tools are not designed to handle metadata for process reproduction. This article refines the DataDesc metadata schema to annotate data models not only in software interfaces but also in datasets and presents an extension to the DataDesc framework for automatically comparing data models and identifying transformation requirements. The ioProc workflow manager is introduced to bundle shared transformation functions into adapter workflows and ensure transparent process documentation. Two use cases from energy systems analysis demonstrate the workflow design and implementation approaches. Overall, this article bridges the gap between abstract guidelines, such as the findability, accessibility, interoperability, and reusability (FAIR) principles, and researchers' daily data- and software-driven analyses, promoting reusability, reproducibility, and transparency in science.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 5","pages":"101493"},"PeriodicalIF":10.8,"publicationDate":"2026-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13161688/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147934054","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

Intentional policy graphs: A pipeline for explaining agent behavior through intentions. 意向策略图：通过意向解释代理行为的管道。

IF 10.8

Patterns Pub Date : 2026-04-10 DOI: 10.1016/j.patter.2026.101513

Victor Gimenez-Abalos, Sergio Alvarez-Napagao, Adrian Tormos, Sara Montese, Ulises Cortés, Javier Vázquez-Salceda

{"title":"Intentional policy graphs: A pipeline for explaining agent behavior through intentions.","authors":"Victor Gimenez-Abalos, Sergio Alvarez-Napagao, Adrian Tormos, Sara Montese, Ulises Cortés, Javier Vázquez-Salceda","doi":"10.1016/j.patter.2026.101513","DOIUrl":"10.1016/j.patter.2026.101513","url":null,"abstract":"Agents increasingly operate in complex environments, where coherent behavior often emerges from opaque decision-making processes. While such systems can be highly effective, this lack of transparency limits trust, auditing, and meaningful human understanding. We introduce intentional policy graphs, a post hoc, model-agnostic framework that explains agent behavior in terms of intentions: probabilistic commitments to desired outcomes inferred from partial observations. By extending policy graphs with a formal notion of intention, we move beyond action-level descriptions toward telic explanations of why agents pursue particular trajectories. The framework provides a complete construction pipeline, design principles, and quantitative metrics that explicitly characterize the trade-off between interpretability and reliability. Intentions support structured answers to what, how, and why questions, enabling both local and global explanations of behavior. We demonstrate the approach in a cooperative multi-agent game and on real-world human driving data, highlighting its generality and explanatory power without access to internal reasoning models.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 4","pages":"101513"},"PeriodicalIF":10.8,"publicationDate":"2026-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13083655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147724025","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

Navigating the manifold: A transformative approach to AI image generation. 导航歧管：人工智能图像生成的变革性方法。

IF 10.8

Patterns Pub Date : 2026-04-10 DOI: 10.1016/j.patter.2026.101539

Alec D MacCall

引用次数: 0

Organizing across disciplines to tackle shared computational challenges. 跨学科组织以解决共享的计算挑战。

IF 10.8

Patterns Pub Date : 2026-04-10 DOI: 10.1016/j.patter.2026.101518

Wojtek Treyde, Aleksy Kwiatkowski, Jascha Achterberg, Danyal Akarca, Martin Buttenschoen, Rory T Byrne, Kieran Didi, Kristina Kordova, Jakub Lála, Jonathon Langford, Austin M Mroz, Puria Radmard, Filip T Szczypiński, Eva Sevenster, Inga Van den Bossche, Michał Wójcik

引用次数: 0

Breaking the glass ceiling: An interview with Yuhao (Jet) Zhou, María Óskarsdóttir, and Cristián Bravo. 打破玻璃天花板：采访周宇浩（Jet） María Óskarsdóttir和Cristián Bravo。

IF 10.8

Patterns Pub Date : 2026-04-10 DOI: 10.1016/j.patter.2026.101541

Yuhao Zhou, María Óskarsdóttir, Cristián Bravo

引用次数: 0

Helix 1.0: An open-source framework for reproducible and interpretable machine learning on tabular scientific data. Helix 1.0：一个开源框架，用于在表格科学数据上进行可重复和可解释的机器学习。

IF 10.8

Patterns Pub Date : 2026-04-01 eCollection Date: 2026-05-08 DOI: 10.1016/j.patter.2026.101536

Eduardo Aguilar-Bejarano, Daniel Lea, Karthikeyan Sivakumar, Jimiama M Mase, Reza Omidvar, Ruizhe Li, Troy Kettle, James Mitchell-White, Morgan R Alexander, David A Winkler, Grazziela Figueredo

{"title":"Helix 1.0: An open-source framework for reproducible and interpretable machine learning on tabular scientific data.","authors":"Eduardo Aguilar-Bejarano, Daniel Lea, Karthikeyan Sivakumar, Jimiama M Mase, Reza Omidvar, Ruizhe Li, Troy Kettle, James Mitchell-White, Morgan R Alexander, David A Winkler, Grazziela Figueredo","doi":"10.1016/j.patter.2026.101536","DOIUrl":"10.1016/j.patter.2026.101536","url":null,"abstract":"Helix is an open-source, extensible, Python-based software framework to facilitate reproducible and interpretable machine learning workflows for tabular data. It addresses the growing need for transparent experimental data analytics provenance, ensuring that the entire analytical process-including decisions around data transformation and methodological choices-is documented, accessible, reproducible, and comprehensible to relevant stakeholders. The platform comprises modules for standardized data preprocessing, visualization, machine learning model training, evaluation, interpretation, results inspection, and model prediction for unseen data. To further empower researchers without formal training in data science to derive meaningful and actionable insights, Helix features a user-friendly interface that enables the design of computational experiments and inspection of outcomes, including a novel interpretation approach to machine learning decisions using linguistic terms all within an integrated environment.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 5","pages":"101536"},"PeriodicalIF":10.8,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13161695/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147934104","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

Zero-shot reconstruction of mutant spatial transcriptomes. 突变体空间转录组的零射击重建。

IF 10.8

Patterns Pub Date : 2026-03-31 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101521

Yasushi Okochi, Takaaki Matsui, Shunta Sakaguchi, Takefumi Kondo, Honda Naoki

{"title":"Zero-shot reconstruction of mutant spatial transcriptomes.","authors":"Yasushi Okochi, Takaaki Matsui, Shunta Sakaguchi, Takefumi Kondo, Honda Naoki","doi":"10.1016/j.patter.2026.101521","DOIUrl":"10.1016/j.patter.2026.101521","url":null,"abstract":"Mutant analysis is the core of biological/pathological research, and measuring spatial transcriptomes can facilitate the understanding of the disorganized tissue phenotype. However, the high cost and technical challenges of spatial transcriptome experiments hinder the investigation of large numbers of mutants. Spatial transcriptomes have also been computationally predicted from single-cell RNA sequencing data using teaching data of spatial expression of certain genes, but the lack of teaching data for most mutants remains challenging. In various machine-learning tasks, zero-shot learning offers potential for predictions without teaching data. Here, we provided ZENomix, the zero-shot framework for predicting mutant spatial transcriptomes without teaching data (e.g., mutant spatial atlases). ZENomix accurately predicted spatial transcriptomes in Alzheimer's model mice, Alzheimer's human brains, and Nodal-signaling-deficient mutant zebrafish embryos. We proposed a ZENomix-based screening approach, identifying Nodal-downregulated genes in zebrafish. We expect that ZENomix offers phenotypic insights by leveraging the enormous amount of mutant/disease single-cell RNA sequencing data.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 6","pages":"101521"},"PeriodicalIF":10.8,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13280724/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148296766","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

The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence. 人工智能风险存储库：人工智能风险的元审查、数据库和分类。

IF 10.8

Patterns Pub Date : 2026-03-30 eCollection Date: 2026-05-08 DOI: 10.1016/j.patter.2026.101517

Peter Slattery, Alexander K Saeri, Emily A C Grundy, Jess Graham, Michael Noetel, Risto Uuk, James Dao, Soroush Pour, Stephen Casper, Neil Thompson

{"title":"The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence.","authors":"Peter Slattery, Alexander K Saeri, Emily A C Grundy, Jess Graham, Michael Noetel, Risto Uuk, James Dao, Soroush Pour, Stephen Casper, Neil Thompson","doi":"10.1016/j.patter.2026.101517","DOIUrl":"10.1016/j.patter.2026.101517","url":null,"abstract":"The risks posed by artificial intelligence (AI) concern academics, auditors, policymakers, AI companies, and the public. Researchers, policymakers, and technology companies discuss AI risks using inconsistent terminology-the same word may describe different problems, while different words describe identical concerns. This fragmentation impedes coordinated responses to AI challenges. We address this by creating the AI Risk Repository: a living database of 1,725 risks extracted from 74 existing taxonomies and frameworks. We organize these risks using two complementary classification systems. The Causal Taxonomy classifies risks by their origins: which entity causes them (human or AI), whether intentional, and when they occur (before or after deployment). The Domain Taxonomy classifies risks by their effects across seven areas, from discrimination and privacy violations to misinformation and weapons development. This shared reference enables more coordinated approaches to discussing, researching, auditing, and governing AI systems across sectors and jurisdictions.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 5","pages":"101517"},"PeriodicalIF":10.8,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13161690/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147934098","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

Dendritic nonlinearities mitigate communication costs. 树状非线性降低了通信成本。

IF 10.8

Patterns Pub Date : 2026-03-30 eCollection Date: 2026-06-12 DOI: 10.1016/j.patter.2026.101520

Xundong Wu, Pengfei Zhao, Zilin Yu, Lei Ma, Yifan Gao, Ka-Wa Yip, Huajin Tang, Gang Pan, Panayiota Poirazi, Tiejun Huang

{"title":"Dendritic nonlinearities mitigate communication costs.","authors":"Xundong Wu, Pengfei Zhao, Zilin Yu, Lei Ma, Yifan Gao, Ka-Wa Yip, Huajin Tang, Gang Pan, Panayiota Poirazi, Tiejun Huang","doi":"10.1016/j.patter.2026.101520","DOIUrl":"10.1016/j.patter.2026.101520","url":null,"abstract":"Why have modern artificial neural networks not adopted the nonlinear dendritic structures found in biological brain cells, and what is the core advantage of such active dendritic units? While early studies suggested that dendritic nonlinearities can enhance learning capabilities by boosting capacity, we provide empirical evidence reassessing this. Using extensive machine learning experiments, we show that dendritic nonlinearities in neural networks offer comparable learning capacity to standard point-neuron models when controlled for parametric complexity. Instead, we believe that their key advantage lies in enabling network scaling while substantially reducing communication costs via localized feature aggregation. Our experiments and analysis suggest that incorporating nonlinear dendritic architectures can significantly lower memory access or data transfer overhead during neural network inference-the primary sources of energy consumption in modern AI systems-and potentially during training as well. We argue that these insights motivate further theoretical and architectural exploration of dendritic-like structures in artificial neural networks.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"7 6","pages":"101520"},"PeriodicalIF":10.8,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13280677/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148296660","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