Atlas Interpolation

The Allen Brain Institute hosts a rich database of mouse brain imagery. It contains a large number of gene expression datasets obtained through the in situ hybridization (ISH) staining. While for a given gene a number of datasets corresponding to different specimen can be found, each of these datasets only contains sparse section images that do not form a continuous volume. This package explores techniques that allow to interpolate the missing slices and thus reconstruct whole gene expression volumes.

Contents

• Installation
  • Python Version and Environment
  • Install “Atlas Interpolation”
• Data
  • Remote Storage Access
  • Model Checkpoints
  • Section Images and Datasets
  • New ISH datasets (advanced, optional)
• Examples
  • Pair Interpolation
  • Optical Flow Models
  • Predict an Entire Gene Volume (Longer Runtime)
• Vendors

API Reference

• atlinter package
  • Subpackages
  • Submodules
  • Module contents