Back

Hierarchical cross-entropy loss improves atlas-scale single-cell annotation models

Cultrera di Montesano, S.; D'Ascenzo, D.; Raghavan, S.; Amini, A. P.; Winter, P.; Crawford, L.

2025-04-23 cell biology
10.1101/2025.04.23.650210 bioRxiv
Show abstract

Accurately annotating cell types is essential for extracting biological insight from single-cell RNA-seq data. Although cell types are naturally organized into hierarchical ontologies, most computational models do not explicitly incorporate this structure into their training objectives. We introduce a hierarchical cross-entropy loss that aligns model objectives with biological structure. Applied to architectures ranging from linear models to transformers, this simple modification significantly improves out-of-distribution performance (12-15%) without added computational cost.

Matching journals

The top 7 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.