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

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.Author summary: Biological datasets are now generated more than ever as many data acquisition technologies have been developed over the years, especially single-cell technologies. With increasing amounts of datasets available for larger scale studies, robust computational tools that could align datasets are needed for data integration and interpretation. We present a new algorithm that can align two biological datasets and demonstrated that the algorithm can work with data generated from different data acquisition technologies. Our proposed algorithm produces low dimensional representations of two datasets to align them in a way that preserves the topology of the respective datasets. Such aligned maps facilitate further analysis, such as clustering. The proposed algorithm showed promising results when applied to different combinations of datasets, i.e., flow cytometry to flow cytometry, flow cytometry to mass cytometry, and two different single-cell RNA sequencing technologies. Therefore, our newly developed algorithm could potentially lead to new discoveries that were once difficult to obtain.