scMultiBench

scMultiBench is a benchmark of single-cell multimodal integration methods. The multibench package runs 36 of them from Python or the command line and scores their output with the benchmark's metrics.

pip install multibench-sc

Get started How it works

1 Run a method

Run Run a method Run any of 36 integration methods in separate environments.

Evaluate Evaluate a run Score a run output with scIB batch-correction and bio-conservation metrics.

Plot Plot results Load the stored results and draw bubble tables and rankings.

Explore Interactive explorer Browse the full benchmark results in the Shiny explorer.

36 methods, one API Vertical, diagonal, mosaic and cross integration through the multibench API. The methods run in separate environments.

scIB metrics Bio-conservation scores (ARI, NMI, ASW, iASW, iF1, cLISI) and batch-correction scores (ASW_batch, GC, iLISI, kBET), combined into rank scores per method.

Compare methods Rank methods for your data with mtb.recommend, or browse the full rankings in the explorer.