Scalable semi-supervised dimensionality reduction with GPU-accelerated EmbedSOM
This provides faster, user-steerable visualization tools for scientists working with large datasets like single-cell cytometry, though it builds incrementally on existing EmbedSOM methods.
The authors tackled the problem of slow and unsupervised dimensionality reduction for large datasets by developing BlosSOM, a GPU-accelerated semi-supervised software that enables interactive visualization of millions of data points with user guidance.
Dimensionality reduction methods have found vast application as visualization tools in diverse areas of science. Although many different methods exist, their performance is often insufficient for providing quick insight into many contemporary datasets, and the unsupervised mode of use prevents the users from utilizing the methods for dataset exploration and fine-tuning the details for improved visualization quality. We present BlosSOM, a high-performance semi-supervised dimensionality reduction software for interactive user-steerable visualization of high-dimensional datasets with millions of individual data points. BlosSOM builds on a GPU-accelerated implementation of the EmbedSOM algorithm, complemented by several landmark-based algorithms for interfacing the unsupervised model learning algorithms with the user supervision. We show the application of BlosSOM on realistic datasets, where it helps to produce high-quality visualizations that incorporate user-specified layout and focus on certain features. We believe the semi-supervised dimensionality reduction will improve the data visualization possibilities for science areas such as single-cell cytometry, and provide a fast and efficient base methodology for new directions in dataset exploration and annotation.