PATTERNS Viewer

Welcome to PATTERNS Viewer


Explore the protein localization patterns within the PATTERNS dataset, as captured by the custom trained deep learning models. You can also explore how those patterns are affected by a Vaccinia virus infection and explore LiveDye images highlighting targetted organelles.

PATTERNS section


On the left hand side, pick an embedding deep learning model to see its projection of the initial PATTERNS data.

Available embedding models:

  • Swin-tuned - Swin transformer v2 (Liu et al., 2022) with custom fine-tuning on part of the data, only on protein channel (best performing model)
  • SubCell-tuned - Subcellular localization model (Gupta et al., 2025) with custom fine-tuning on part of the data, leveraging protein and DNA channels
  • Swin-raw - Swin transformer v2 (Liu et al., 2022) pretrained on ImageNet by the original authors
  • SubCell-raw - Subcellular localization model (Gupta et al., 2025) pretrained by the original authors
  • Randomized - Randomized baseline (embeddings from Swin-tuned model, randomly shuffled in each dimension individually)

Explore the intricate relationships and intersections with ground truth sources in particular from:


Vaccinia section


In the Gene shift tab, explore how Vaccinia virus infection affects the protein locations of individual genes, leveraging the Swin-tuned model.
The Barcode shift tab, allows an exploration of the Vaccinia virus infection on the level of barcodes.

LiveDye section


The Correlations tab presents preliminary data from a LiveDye campaign, where appart from PATTERNS imaging of individual proteins, additional dyes for selected organelles have been used (e.g., ER or Golgi). The images are embedded with the Swin-tuned model and the correlations between the individual dyes and the protein patterns are indicated.


For details, consult the information box provided in the i-information box on each page.

The viewer is a result of a collaboration between the JSB Lab of the University of Bonn and Appsilon.