Simon Warchol, Robert Krueger, Ajit Johnson Nirmal, Giorgio Gaglia, Jared Jessup, Cecily C. Ritch, John Hoffer, Jeremy Muhlich, Megan L. Burger, Tyler Jacks, Sandro Santagata, Peter K. Sorger, Hanspeter Pfister (* Indicates equal contribution)
Published in IEEE Transactions on Visualization and Computer Graphics and presented at IEEE Vis 2022: 10.1109/TVCG.2022.3209378
Pre-print 10.1109/TVCG.2022.3209378
Visinity is part of the Minerva Analysis suite of tools from the Lab of Systems Pharmacology at Harvard Medical School and the Visual Computing Group at Harvard SEAS.
This is an openseadragon based Cellular Image Viewing and Analysis Tool. It is built with a python Flask backend and a Node.js javascript frontend.
Visinity interface. a) Image viewer: multiplex whole-slide tissue images highlighting spatial cell arrangement. b) Cohort view: search, apply, compare spatial patterns across different specimens. c) Neighborhood composition view: visualizes cell types that make up cell neighborhoods; d) UMAP embedding view: encodes cells with similar neighborhood as dots close to each other; e) Correlation matrix: pairwise interactions between cells; f) Comparison \& summary view: different small multiple encodings of extracted patterns. g) Neighborhood search: finds cells with similar neighborhood; h) Interactive clustering: automated detection of neighborhood patterns; i) Annotation panel: save and name patterns; j) Channel selection: color and combine image channels.
Import requires an image,segmentation mask, single cell quantification, and cell types. See example dataset.
Importing cohort data requires pressing the add linked dataset button and importing all specimens at once
Match CSV columns with channels in the image via the GUI.
For more info about the specific features of the system and their use, see the pre-print.
Releases can be found here: https://github.com/labsyspharm/Visinity/releases These are executables for Windows and MacOS that can be run locally without any installations.
git clone https://github.com/labsyspharm/visinity.git
Create env: conda env create -f requirements.yml
Active environment: conda activate visinity
python run.py
- Runs the webserver
Access the tool via http://localhost:8000/
This step is only needed when you plan to edit js code. The codebase already included bundled js files.
/minerva_analysis/client
and run npm install
to install all packages listed in package.json.npm run start
to package the Javascript, or run npm run watch
if you plan on editing dependenciesAny tagged commit to a branch will trigger a build, where tag == commit message
. This will appear under releases. Note building may take ~10 min.
Tagging Conventions: All release tags should look like v{version_number}_{branch_name}
.
npm ssh errors from viawebgl
can be solved w/
npm cache clear --force && npm install --no-shrinkwrap --update-binary