Back

A Probabilistic Approach For Registration Of Multi-Modal Spatial Transcriptomics Data

Qiang, Y.

2021-10-07 bioinformatics
10.1101/2021.10.05.463196 bioRxiv
Show abstract

Observing the spatial characteristics of gene expression by image-based spatial transcriptomics technology allows studying gene activity across different cells and intracellular structures. We present a probabilistic approach for the registration and analysis of transcriptome images and immunostaining images. The method is based on particle filters and jointly exploits intensity information and image features. We applied our approach to synthetic data as well as real transcriptome images and immunostaining microscopy images of the mouse brain. It turns out that our approach accurately registers the multi-modal images and yields better results than a state-of-the-art method.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.