Back

Multi-batch cytometry data integration for optimal immunophenotyping

Ogishi, M.; Yang, R.; Gruber, C.; Pelham, S.; Spaan, A. N.; Rosain, J.; Chbihi, M.; Han, J. E.; Rao, V. K.; Kainulainen, L.; Bustamante, J.; Boisson, B.; Bogunovic, D.; Boisson-Dupuis, S.; Casanova, J.-L.

2020-07-15 bioinformatics
10.1101/2020.07.14.202432 bioRxiv
Show abstract

We describe the integration of multi-batch cytometry datasets (iMUBAC), a flexible, robust, and scalable computational framework for unsupervised cell-type identification across multiple batches of high-dimensional cytometry datasets. After overlaying cells from healthy controls across multiple batches, iMUBAC learns batch-specific cell-type classification boundaries and identifies aberrant immunophenotypes in patient samples. We illustrate unbiased and streamlined immunophenotyping, using both in-house and public mass and flow cytometry datasets.

Matching journals

The top 3 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.