Abstract
“The advent of single-cell RNA-sequencing (scRNA-seq) has driven significant computational methodsdevelopment for all steps in the scRNA-seq data analysis pipeline, including filtering, normalization, andclustering. The large number of methods and their resulting parameter combinations has created a combinatorialset of possible pipelines to analyze scRNA-seq data, which leads to the obvious question: which isbest? Several benchmarking studies have sought to compare methods to answer this, but frequently findvariable performance depending on dataset and pipeline characteristics. Alternatively, the large number ofpublicly available scRNA-seq datasets along with advances in supervised machine learning raise a tantalizingpossibility: could the optimal pipeline be predicted for a given dataset? Here we begin to answer thisquestion by applying 288 scRNA-seq analysis pipelines to 86 datasets and quantifying pipeline success viaa range of measures evaluating cluster purity and biological plausibility.
NETL
NSTL