We then trained a support vector classifier to discriminate all of these labels, using the training set of preliminary clusters manually annotated with class labels. We sampled 100 cells per cluster and used 80% of this dataset to optimize the classifier, and the remaining 20% to assess performance. On average, the classification accuracy was 93% for non-cycling cells. The precision and recall for neurons was 93% and 99%, respectively. That is, 99% of all neurons were classified correctly, and 93% of all cells classified as neurons were actually neurons. The classifier struggled to distinguish cycling cells, presumably because they shared most gene expression with their non-cycling counterparts. For this reason, we always pooled cycling and non-cycling cells after classification. The table below shows the accuracy for all major classes of interest:PrecisionRecallastrocyte87%96%astrocyte, cycling59%38%bergmann-glia100%97%blood77%65%ependymal98%97%immune96%98%neurons93%99%neurons, cycling63%54%oec100%95%oligos91%97%oligos, cycling39%19%satellite-glia90%95%satellite-glia, cycling91%88%schwann100%100%choroid100%80%vascular87%97%vascular, cycling100%25%average (non-cycling)93%93%
