Welcome to Steamboat’s documentation!
Steamboat is an interpretable machine learning framework leveraging a self-supervised, multi-head attention model that uniquely decomposes the gene expression of a cell into multiple key factors:
intrinsic cell programs,
neighboring cell communication, and
long-range interactions.
These pieces of information are used to generate cell embedding, cell network, and reconstructed gene expression.
In the following sections, you Please refer to respective sections for installation, tutorials, and Steamboat API.
Source code for Steamboat is available as a GitHub repository.
Contents:
- Installation
- Tutorials
- A tiny simulation
- Ovarian cancer data analysis
- Train on mouse brain data
- Interpret the results on mouse brain data
- Spatial perturbation tasks on mouse brain data
- Investigating Global Attention and Prognosis on Colorectal CODEX data
- Evaluating Spatial Perturbation Prediction on Perturb-FISH Data
- Generalization of Steamboat to Slide-tags Data
- Selecting number of heads on Slide-tags Data
- Generalization of Steamboat to Visium Data
- Steamboat API
- Contact