Skip to content

sciluna/sbgn-flow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SBGNFlow

SBGNFlow is an AI-assisted and interactive workflow for generation, merging/splitting and layout of SBGN pathway maps. It supports the iterative curation of biological pathways through three modular steps that can be used in any order or combination.

The first step enables automatic conversion of hand-drawn SBGN sketches into machine-readable SBGN-ML using multimodal large language models (LLMs). It also provides an interactive interface for quickly correcting recognition errors and performing text-based edits, while biological identifiers are mapped automatically to facilitate annotation effort.

The second step supports layout-aware merging and splitting of maps, enabling users to incrementally construct larger pathway diagrams or reorganize existing networks into smaller multi-glyph components.

The final step introduces SBGN-specific layout refinement methods, combining user-guided node adjustments with automated layout polishing to improve the clarity and quality of pathway maps.

Click here for a demo.

SBGNFlow.mov

Software

Running a Local Instance

In order to deploy and run a local instance of the application, please follow the steps below (we recommend the use of version 20.14.0 of node.js):

  • Installation
git clone https://github.com/sciluna/sbgn-flow.git
cd sbgn-flow
npm install 
  • Running the tool
npm run start

Then, open a web browser and navigate to http://localhost:3000/. Please note that the default port is 3000 but you can run it in another port by setting 'PORT' environment variable.

Dependencies

Each module of the workflow is developed as a standalone library/web service and is used in SBGNFlow directly or with slight adjustments.

Credits

SBGNFlow uses Cytoscape.js for graph visualization and other graph-related operations. Third-party libraries used in demo: Fomantic-UI, FileSaver.js, cytoscape-context-menus, cytoscape-sbgn-stylesheet, cytoscape-fcose, cytoscape-layout-utilities, libsbgn.js, sbgnml-to-cytoscape, xml-formatter.

Team

Hasan Balci and Augustin Luna of Luna Lab

About

SBGNFlow — an AI-assisted and interactive workflow for generation, merging/splitting and layout of SBGN pathway maps.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors