SeedMe: Data sharing building blocks

The need for data sharing and rapid data access has become central with the rise of collaborative research in many disciplines. For the general public, several file sharing products are available that post and share files using web browsers. But for science data and research use, these products are not well suited. While consumer products get by with manual user interfaces to add and remove a few shared files, this is not practical for sharing large numbers of science data files, like those generated during and after large-scale computation. Instead, automated and scriptable mechanisms are required that can integrate into computation workflows to post files during and after computation jobs. Scientific data sharing also requires support for collaborative discussion of research results, quick rough-draft visualizations to analyze the data, and support for metadata and descriptive information that can record job and compute platform characteristics, input data, job parameters, job completion status, and other provenance information.<br>Here we describe work in progress under the umbrella of the <b>SeedMe (Stream, Encode, Explore and Disseminate My Experiments) project</b> that is developing scientific data-sharing and data management tools that cater to the unique needs of computational scientists. These tools support automated and scriptable access to shared data, browser-based data access, secure data storage, sharing with a project workgroup, data descriptions and metadata, threaded collaborative discussion, and light-weight visualization.

随着多学科协作研究的兴起，数据共享与快速数据获取的需求已成为核心关切。面向普通大众的网页端文件共享产品已较为成熟，可通过浏览器完成文件发布与共享，但这类产品并不适配科学数据与科研场景的需求。这类消费级产品仅依靠手动用户界面即可完成少量共享文件的增删操作，但对于大规模计算过程中及计算后产生的海量科学数据文件而言，这种方式并不实用。因此，亟需支持自动化与脚本化操作的机制，使其能够集成至计算工作流中，在计算任务执行期间及完成后自动完成文件发布。科学数据共享还需支持科研成果的协作讨论、用于数据分析的快速草稿可视化，同时需支持元数据（metadata）与描述性信息的存储，可记录计算任务、计算平台特性、输入数据、任务参数、任务完成状态及其他溯源信息。
本文介绍了**SeedMe（流式处理、编码、探索与传播我的实验，Stream, Encode, Explore and Disseminate My Experiments）**项目下的在研工作，该项目旨在开发适配计算科学家独特需求的科学数据共享与数据管理工具。这些工具可支持共享数据的自动化与脚本化访问、基于浏览器的数据访问、安全数据存储、项目工作组内的数据共享、数据描述与元数据管理、线程化协作讨论以及轻量级可视化功能。