Fig. 4: Benchmarking results on lung atlas dataset.

Created in BioRender. He, C. (2025) https://BioRender.com/sii3x0l(a) Batch composition and nested batch effects in the lung atlas dataset, including three studies, two sequencing technologies, and two tissue types. b Scatterplot of average bio-conservation score against the average batch correction score for each method. c UMAP visualization contrasting the unintegrated pancreatic islet dataset with its integrated counterparts using scCRAFT and two other most popular benchmarking methods. The top panel shows the integration of different batches (samples), the middle panel shows the cell types, and the bottom panel shows the distribution of negative, positive, and true positive cells. Positive cells are those surrounded by cells of the same type, while true positive cells are a subset of positive cells whose surrounding batch distribution matches the global batch distribution for that cell type.