arXiv：cs.AI· Carles Navarro, Mariona Torrens, Philipp Th\"olke, Stefan Doerr, Gianni De Fabritiis·· 7 小时前AI 评分39
Speak to a Protein：交互式多模态蛋白质协同科学家
Speak to a Protein: An Interactive Multimodal Co-Scientist
AI 导读
Speak to a Protein 将蛋白质分析变成与 AI 协同科学家的交互式多模态对话，可检索整合文献、结构与配体数据，并在实时 3D 场景中高亮、标注、操作和查看可视化。该系统还能按需生成并运行代码，用文字和图形解释结果，已在结合口袋、构象变化与构效关系等问题上做实时演示。它降低了高级结构分析门槛，缩短从提问到证据的时间，可免费访问。
正文
Abstract:Building a working mental model of a protein typically requires weeks of reading, cross-referencing crystal and predicted structures, and inspecting ligand complexes, an effort that is slow, unevenly accessible, and often requires specialized computational skills. We introduce \emph{Speak to a Protein}, a new capability that turns protein analysis into an interactive, multimodal dialogue with an expert co-scientist. The AI system retrieves and synthesizes relevant literature, structures, and ligand data; grounds answers in a live 3D scene; and can highlight, annotate, manipulate and see the visualization. It also generates and runs code when needed, explaining results in both text and graphics. We demonstrate these capabilities on relevant proteins, posing questions about binding pockets, conformational changes, or structure-activity relationships to test ideas in real time. \emph{Speak to a Protein} reduces the time from question to evidence, lowers the barrier to advanced structural analysis, and enables hypothesis generation by tightly coupling language, code, and 3D structures. \emph{Speak to a Protein} is freely accessible at this https URL.
| Subjects: | Biomolecules (q-bio.BM); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.17826 [q-bio.BM] |
| (or arXiv:2510.17826v2 [q-bio.BM] for this version) | |
| https://doi.org/10.48550/arXiv.2510.17826 arXiv-issued DOI via DataCite |
Submission history
From: Gianni De Fabritiis [view email]
[v1]
Wed, 1 Oct 2025 22:12:34 UTC (4,446 KB)
[v2]
Tue, 6 Oct 2026 13:19:04 UTC (10,207 KB)
来源：arXiv：cs.AI · arxiv.org