A supervised ontology-aware cell annotation method for single-cell transcriptomic data

Nimish Magre, Ebtisam Alshehri, Fedor Grab, Yerdos Ordabayev, Mehrtash Babadi, Stephen J. Fleming

Keywords: scRNA-seq, single-cell, transcriptomics, cell ontology, cell annotation, cell type prediction

Abstract: Many single-cell RNA-seq annotation methods ignore the hierarchical nature of cell type classification. We present a probability propagation strategy that enforces ontological consistency and improves performance when applied to existing models without retraining. Combined with a lightweight logistic regression model trained on 42 million human cells, this yields SOCAM, a fast and interpretable classifier. We also introduce a hop-based F1 score for ontology-aware evaluation. Code and models are available open source.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 135