Fig. 1
From: SMaSH: a scalable, general marker gene identification framework for single-cell RNA-sequencing
![Fig. 1](http://media.springernature.com/full/springer-static/image/art%3A10.1186%2Fs12859-022-04860-2/MediaObjects/12859_2022_4860_Fig1_HTML.png)
The SMaSH framework. A SMaSH works directly from the counts matrix, producing a dictionary relating the user-defined classes of interest (e.g. cell type annotations) to top marker genes for each class (default top 5). B SMaSH filters and ranks genes according to an ensemble learning model or a deep neural network