arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.00601cs.DLq-bio.QM
收藏

Album: 科学成像流程的可执行构建模块,从共享到LLM辅助编排

Album: executable building blocks for scientific imaging routines, from sharing to LLM-assisted orchestration

Max Delbrück Center for Molecular Medicine in the Helmholtz Association(马克斯·德尔布吕克分子医学中心);Helmholtz Imaging, Max Delbrück Center for Molecular Medicine in the Helmholtz Association(亥姆霍兹成像,马克斯·德尔布吕克分子医学中心);Humboldt-Universität zu Berlin, Faculty of Mathematics and Natural Sciences(柏林洪堡大学数学与自然科学学院);Biohub(生物枢纽)

Jan Philipp Albrecht, Deborah Schmidt, Lucas Rieckert, Maximilian Otto, Kyle Harrington

AI总结:

Album通过两个核心机制实现科学流程的可执行打包与共享,支持可复现执行和LLM辅助编排,适用于多领域科学应用。

摘要:

开源科学软件是推动科学进步的主要驱动力,但其开发和重用在协作环境中仍面临困难。研究人员反复遇到四个挑战:发现和复现现有流程、适应新用例、跨协作者共享和扩展、以及通过可复现执行环境稳定流程。我们提出了Album,一个通过两个最小原语打包和共享科学流程的开源框架:(i) 解决方案,一个Python原生的可执行入口点,结合机器可读元数据、参数、环境规范和生命周期钩子;(ii) 目录,一个去中心化的git原生分发机制,具有索引搜索和可选网页渲染,用于发现、溯源和治理。Album采用双上下文执行模型,在主机控制器评估清单并准备每种解决方案环境的同时,生命周期钩子在隔离的解决方案环境中执行。这种设计支持可复现执行、环境设置后执行以及具有不兼容依赖项的流程编排。Album可以与LLM代理结合使用:解决方案可以由LLM协助起草和修订,MCP接口将目录化的解决方案暴露为可调用工具,用于工具导向的发现和编排。我们通过四个真实世界成像部署评估Album,涵盖交互式可视化电子显微镜数据、多种分割方法整合、冷冻电镜断层扫描竞赛工作流编排以及矿物定量管道。总体而言,Album通过使科学流程成为可执行、可共享的artifact,补充了包管理器、工作流系统和容器运行时。文档和示例可在https://album.solutions获取。

英文摘要:

Open-source scientific software is a major driver of scientific progress, yet its development and reuse remain difficult in collaborative settings. Researchers repeatedly face four recurring challenges: discovering and reproducing existing routines, adapting them for new use cases, sharing and scaling them across collaborators, and stabilizing them with reproducible execution environments. We present Album, an open-source framework for packaging and sharing scientific routines as executable artifacts through two minimal primitives: (i) the solution, a Python-native executable entry point that combines machine-readable metadata, arguments, environment specifications, and lifecycle hooks; and (ii) the catalog, a decentralized, git-native distribution mechanism with indexed search and optional web rendering for discovery, provenance, and governance. Album uses a two-context execution model in which a host controller evaluates manifests and prepares per-solution environments, while lifecycle hooks execute inside isolated solution environments. This design supports reproducible execution, post-environment setup, and the composition of routines with incompatible dependencies. Album can be used in conjunction with LLM agents: solutions can be drafted and revised with LLM assistance, and a MCP interface exposes cataloged solutions as callable tools for tool-grounded discovery and orchestration. We evaluate Album through four realworld imaging deployments spanning interactive visualization of electron microscopy data, integration of multiple segmentation methods, the orchestration of cryo-electron tomography competition workflows, and mineral quantification pipelines. Overall, Album complements package managers, workflow systems, and container runtimes by making scientific routines executable, shareable artifacts. Documentation and examples are available at https://album.solutions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑