Automated optimized parameters for T-distributed stochastic neighbor embedding improve visualization and allow analysis of large datasets
Anna C. Belkina, Christopher O. Ciccolella, Rina Anno, Richard Halpert, Josef Špidlen, Jennifer E Snyder-Cappione
The paper introduces opt-SNE, an automated t-SNE parameter selection tool that improves visualization and analysis of large single-cell datasets by optimizing early exaggeration and gradient descent settings.
Nature Communications · Nov 28, 2019Peer-reviewedBioinformatics