Semi-supervised adversarial neural networks for single-cell classification.

Annotating cell identities is a common bottleneck in the analysis of single-cell genomics experiments. Here, we present scNym, a semi-supervised, adversarial neural network that learns to transfer cell identity annotations from one experiment to another. scNym takes advantage of information in both labeled datasets and new, unlabeled datasets to learn rich representations of cell identity that enable effective annotation transfer. We show that scNym effectively transfers annotations across experiments despite biological and technical differences, achieving performance superior to existing methods. We also show that scNym models can synthesize information from multiple training and target datasets to improve performance. In addition to high performance, we show that scNym models are well-calibrated and interpretable with saliency methods.