Donor-specific, but not sex-specific, signatures dominate cell-type classification in lung scRNA-seq data.

Transcriptomic differences between individuals and sexes are well-documented across tissues, affecting cell-type identity. Single-cell atlases often have skewed sex ratios or limited donor diversity, potentially leading to sex- or donor-biased annotations using automatic classification methods. This might cause models to exacerbate existing biases from their training data. We investigated this by varying the sex ratio in a training set and assessing a cell-type classifier's performance on fixed single-sex test sets. To separate sex and donor effects, we ran the experiment with and without donor information. We found that differences between donors negatively impact classification, as evidenced by poorer performance on unseen donors. However, this is not primarily due to sex bias; the model classified male and female cells similarly well, even when trained on highly sex-skewed data. We also found that large sex-based abundance differences between cell types can confound performance interpretation, creating apparent sex-biased patterns. Our findings suggest that atlas creators and classifier developers must carefully consider donor-specific biases in scRNA-seq data.