CyChat: a conversational Cytoscape app for no-code, reproducible network analysis
- 1University of Hamburg
Abstract
Network-based analyses of molecular interactions are useful for interpreting high-throughput omics data and identifying therapeutic targets. Cytoscape is the standard platform for these tasks, but users face a trade-off between accessible graphical workflows that are difficult to document and reproducible automation in Python or R that requires programming expertise. General-purpose coding assistants can generate Cytoscape Automation scripts, but remain external to Cytoscape. We present CyChat, a Cytoscape Desktop app that integrates a chat interface and a large language model (LLM) agent into the application. CyChat translates natural language into executable Cytoscape Automation workflows, runs generated Python code, and exports chat sessions with executed code as standalone Jupyter notebooks. To reduce setup barriers, CyChat includes an embedded Python runtime and supports both cloud-based and locally hosted LLMs. CyChat was evaluated across ten Cytoscape workflows using seven LLM providers, each represented by one LLM. The strongest configuration achieves a pass rate above 99%. In a qualitative evaluation based on a published network visualization, CyChat completes the task in 1.5-5 minutes, compared with 15-20 minutes for manual GUI workflows by computational biologists. CyChat is available through the Cytoscape App Store at https://apps.cytoscape.org/apps/cychat.
Related
- The behaviour bends, the code holds: working-memory category information in the multiple-demand network across graded interruption
- OSIRIS-MCP: Towards secure conversational access to research information in OSIRIS
- Using conversational artificial intelligence to dissect the psychoneuroimmunology of social safety and threat
- Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role
- Asking the Data: Conversational Interrogation of LC-MS/MS Proteomics Data Sets with an LLM Agent
BibTeX
@misc{liebold2026cychat,
title = {{CyChat: a conversational Cytoscape app for no-code, reproducible network analysis}},
author = {J. Liebold and M. Stahl and J.-O. Schulze and M. M. Razavi and G. B. Bader and S. Kurtz and J. Baumbach},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.28.747833},
url = {https://www.biorxiv.org/content/10.64898/2026.08.28.747833v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - CyChat: a conversational Cytoscape app for no-code, reproducible network analysis
AU - J. Liebold
AU - M. Stahl
AU - J.-O. Schulze
AU - M. M. Razavi
AU - G. B. Bader
AU - S. Kurtz
AU - J. Baumbach
PY - 2026
DA - 2026/08/28
PB - bioRxiv
DO - 10.64898/2026.08.28.747833
UR - https://www.biorxiv.org/content/10.64898/2026.08.28.747833v1
AB - Network-based analyses of molecular interactions are useful for interpreting high-throughput omics data and identifying therapeutic targets. Cytoscape is the standard platform for these tasks, but users face a trade-off between accessible graphical workflows that are difficult to document and reproducible automation in Python or R that requires programming expertise. General-purpose coding assistants can generate Cytoscape Automation scripts, but remain external to Cytoscape. We present CyChat, a Cytoscape Desktop app that integrates a chat interface and a large language model (LLM) agent into the application. CyChat translates natural language into executable Cytoscape Automation workflows, runs generated Python code, and exports chat sessions with executed code as standalone Jupyter notebooks. To reduce setup barriers, CyChat includes an embedded Python runtime and supports both cloud-based and locally hosted LLMs. CyChat was evaluated across ten Cytoscape workflows using seven LLM providers, each represented by one LLM. The strongest configuration achieves a pass rate above 99%. In a qualitative evaluation based on a published network visualization, CyChat completes the task in 1.5-5 minutes, compared with 15-20 minutes for manual GUI workflows by computational biologists. CyChat is available through the Cytoscape App Store at https://apps.cytoscape.org/apps/cychat.
ER -