Loki2 documentation

Loki2 is a single-cell pathology foundation model that uses an encoder–decoder architecture to reliably translate nucleus morphology into molecular-level information. Loki2 is trained on UniSeg, a pan-tissue resource of 15 million cells with paired segmentation and transcriptomic measurements from multiple spatial technologies. This training strategy enables three capabilities from hematoxylin and eosin (H&E) images alone: universal cell type inference, in silico spatial transcriptomics by retrieving transcriptionally matched cells from reference atlases, and continuous morphological pseudotime inference of cell state transitions. By further aggregating single-cell features, Loki2 supports in silico protein staining and whole-slide clinical inference. These results show that routine histology contains far richer molecular and cellular information than previously recognized, and that Loki2 provides a general framework for accessing this information across technologies, tissues, disease contexts, and scales.

Please find our github on GitHub.

API

• API Reference
  • loki2

Tutorials

• Installation
• Loki2 Cell Type Inference
  • Data Requirements
  • Cell Detection
  • Load Sample
  • Plot Image
  • Plot Cell Types
  • Plot UMAP
• Loki2 Morphology-to-Transcriptome Retrieval
  • Data Requirements
  • Prepare Training Data
  • Training
  • Retrieve from scRNA Data
  • Load Retrieval Results
  • Plot scRNA Data
  • Plot Loki2 Retrieval Results
• Loki2 Morphological Pseudotime Inference - Colorectal Cancer Samples
  • Data Requirements
  • Load Data
  • Assemble the Three Samples on One Slide for Visualization
  • Check the Topology and Gradient in Image Embeddings Among Samples
  • Prepare Data and Perform Clustering
  • Select Starting Cell for Pseudotime
  • Infer Pseudotime
  • Visualize Pseudotime
  • Plot Trajectory
• Loki2 Morphological Pseudotime Inference - Prostate Cancer Sample
  • Data Requirements
  • Load Data
  • Visualize Region of Interest
  • Prepare Data and Perform Clustering
  • Select Starting Cell for Pseudotime
  • Infer Pseudotime
  • Visualize Pseudotime
  • Plot Trajectory
• Loki2 in silico Immunostaining
  • Data Requirements
  • Examples of PanCK Marker
  • Examples of CD45RO Marker
• Loki2 Cell-level Multiple Instance Learning
  • MIL Model
  • Plot Attention Heatmaps on WSI