空间生物学家如何指导和验证AI辅助分析
How Spatial Biologists Direct and Verify AI-Assisted Analyses
- Harvard University(哈佛大学)
- Heidelberg University(海德堡大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
本研究通过观察十位空间生物学家使用Claude Science,揭示他们如何指导和验证AI代理分析,并提出四个设计方向以支持执行控制、交互视图、信息透明和可访问验证。
AI中文摘要:
空间生物学家使用可视化来评估组织数据的计算分析。我们研究了当AI代理执行此类工作时,他们如何指导和验证分析。我们综合了十四次情境调查的工作流程,进行了形成性试点,随后对十位空间生物学家进行了观察研究,他们使用Claude Science分析自己的数据。参与者重视在绘图、定位感兴趣细胞以及他们认为费力或无法自行完成的任务方面获得的帮助。评估代理的工作涉及获取合适的证据,有时需要通过外部工具进行额外工作,并利用组织及其标记物的知识进行解释。科学家还寻求有关正在进行的计算的信息,以决定分析应如何进行。我们贡献了工作流程综合、科学家指导和验证代理分析的经验性描述,以及四个设计方向,涉及执行控制、熟悉的交互视图、源代码和执行信息,以及跨计算设置和经验的可访问验证。
英文摘要:
Spatial biologists use visualization to assess computational analyses of tissue data. We examine how they direct and verify analyses when an AI agent performs this work. We synthesized workflows from fourteen contextual inquiries and conducted a formative pilot followed by an observational study with ten spatial biologists using Claude Science on their own data. Participants valued help with plotting, locating cells of interest, and tasks they found laborious or could not otherwise perform. Assessing the agent's work involved obtaining suitable evidence, sometimes through additional work in external tools, and interpreting it using knowledge of the tissue and its markers. Scientists also sought information about ongoing computation to decide how analysis should proceed. We contribute a workflow synthesis, an empirical account of scientists directing and verifying agentic analyses, and four design directions addressing execution control, familiar interactive views, source and execution information, and accessible verification across computing setups and experience.