JSOM: Jointly-evolving self-organizing maps for alignment of biological datasets and identification of related clusters

Abstract

With the rapid advances of various single-cell technologies, an increasing number of single-cell datasets are being generated, and the computational tools for aligning the datasets which make subsequent integration or meta-analysis possible have become critical. Typically, single-cell datasets from different technologies cannot be directly combined or concatenated, due to the innate difference in the data, such as the number of measured parameters and the distributions. Even datasets generated by the same technology are often affected by the batch effect. A computational approach for aligning different datasets and hence identifying related clusters will be useful for data integration and interpretation in large scale single-cell experiments. Our proposed algorithm called JSOM, a variation of the Self-organizing map, aligns two related datasets that contain similar clusters, by constructing two maps—low-dimensional discretized representation of datasets–that jointly evolve according to both datasets. Here we applied the JSOM algorithm to flow cytometry, mass cytometry, and single-cell RNA sequencing datasets. The resulting JSOM maps not only align the related clusters in the two datasets but also preserve the topology of the datasets so that the maps could be used for further analysis, such as clustering.

The Route of Vaccine Administration Determines Whether Blood Neutrophils Undergo Long-Term Phenotypic Modifications

“…This is due to technical differences, called batch effects, that affect the signal intensity (on which commonly used unsupervised analytical methods, such as SPADE, visNE, FlowSOM, CITRUS, and UMAP, are based) and need to be distinguished from true biological variability ( 28 ). Several algorithms have been proposed to normalize signal intensity to reduce batch effects before unsupervised cell cluster identification and to compare multiple datasets, such as CytofRUV ( 29 ), and JSOM ( 30 ). iMUBAC can even compare different datasets in the absence of shared technical replicates, used as reference samples, by overlaying cells from several healthy controls as anchors ( 31 ).…”