with known identities which can classify unlabeled cells. We then hold back the PCP identity of some cells and attempt to predict their identities using this sub-network of known identities. The efficacy of this test, reported as mean area under the receiver operator characteristic curve (AUROC), maps to the probability of a correct assignment when making a single binary choice (Figure 2A). Having constructed a computational assay for cell identity, we vary the transcriptomic features (e.g. gene families) used to characterize cells as neighbors. This computation screen thus selects gene ensemble features which jointly distinguish cell identities.
