The format of the output of trainSingleR() has changed and is no longer back-compatible.
recompute=FALSE in trainSingleR() does nothing; all integrated analyses are now done with recompute=TRUE.
To that end, combineCommonResults() is also deprecated.
genes = "sd" and its associated options in trainSingleR() are no longer supported.
first.labels is no longer reported in classifySingleR().
Added another parallelization mechanism via num.threads= and C++11 threads.
This should be much more memory efficient than using BiocParallel.
combineRecomputedScores() will automatically handle mismatches in the input references by default.
Relaxed the requirements for consistent row names in combineRecomputedResults().
Support sparse DelayedArray inputs in classifySingleR().
Parallelize over labels instead of rows in aggregateReference(), with minor changes in the setting of the seed.
Restrict the PCA to the top 1000 most highly variable genes, for speed.
Migrated all of the dataset getter functions to the celldex package.
Streamlined the vignette to point to the book at http://bioconductor.org/books/devel/SingleRBook/.
Added a restrict= argument to trainSingleR() and SingleR() to easily restrict to a subset of features.
Deprecated the method= argument in SingleR().
Protect against accidental data.frames in ref= or test= in all functions.
Added support for consolidating labels from multiple references via combineResults().
Added mappings to standardized Cell Ontology terms in all *Data() functions.
Changed the name of the labels input of plotScoreDistribution() to labels.use for consistency across functions.
Fixed a label from adipocytes to astrocytes in BlueprintEncodeData().
Removed umlauts from labels (e.g., naive) in NovershternHematopoieticData() to avoid problems with Windows.
Perform PCA before clustering in aggregateReference() for speed and memory efficiency.
Modified genes="all" behavior in trainSingleR() to report DE-based markers for fine-tuning only.
New package SingleR for cell type annotation.