- omni_batch_py, batch_integration_py
Currently the following benchmarks are part of omnibenchmark:
|omni_batch_py, batch_integration_py, omni-batch-py||Methods to integrate/correct batch effects in sc-RNA-seq data||https://renkulab.io/projects/omnibenchmark/omni-batch-py/orchestrator-py|
|omniclustering||Clustering methods for scRNA-seq data||https://renkulab.io/knowledge-graph/projects/omb_benchmarks/omniclustering/orchestrator|
|omniclustering_pinned||Reproduced clustering methods for scRNA-seq data benchmark||https://renkulab.io/knowledge-graph/projects/omb_benchmarks/omniclustering/orchestrator_pinned|
|iris_example||Example benchmark using the iris dataset||https://renkulab.io/projects/omnibenchmark/iris_example/iris-orchestrator|
|spatial-clustering||Clustering methods for spatial transcriptomics data||https://renkulab.io/projects/omb_benchmarks/omni_srt_clustering/orchestrator|
Missing a benchmark? Get in contact to suggest or start a new:
Robinson Group Departement of Molecular Life Sciences University of Zurich
All projects and datasets that are currently part of omnibenchmark. Benchmarks can have all kinds of architectures and inter-benchmark connections (shared projects). Over the time the architecture of a benchmark can change and adapt.
An example benchmark running some example methods on the iris dataset. This benchmark serves as a simple show case and starting point to familiarize with different possible project setups and their connections in omnibenchmark.
This benchmarks evaluates clustering methods for single cell RNAseq data. It is the continuous extension of A systematic performance evaluation of clustering methods for single-cell RNA-seq data by Duò A, Robinson MD and Soneson C from 2018.
This benchmarks evaluates clustering methods for single cell RNAseq data. It is a reproduction of A systematic performance evaluation of clustering methods for single-cell RNA-seq data by Duò A, Robinson MD and Soneson C from 2018 and not intended for continuous updates.
A benchmark to evaluate batch correction/data integration methods for single cell RNA-seq data. While many of the methods could also be applied to map cells from different modalities this benchmark focuses on data from the same modality, but different batches with different complexities.
A benchmark to evaluate clustering methods for spatial transcriptomics data.