Scbean: a python library for single-cell multi-omics data analysis

Abstract

Summary: Single-cell multi-omics technologies provide a unique platform for characterizing cell states and reconstructing developmental process by simultaneously quantifying and integrating molecular signatures across various modalities, including genome, transcriptome, epigenome, and other omics layers. However, there is still an urgent unmet need for novel computational tools in this nascent field, which are critical for both effective and efficient interrogation of functionality across different omics modalities. Scbean represents a user-friendly Python library, designed to seamlessly incorporate a diverse array of models for the examination of single-cell data, encompassing both paired and unpaired multi-omics data. The library offers uniform and straightforward interfaces for tasks, such as dimensionality reduction, batch effect elimination, cell label transfer from well-annotated scRNA-seq data to scATAC-seq data, and the identification of spatially variable genes. Moreover, Scbean's models are engineered to harness the computational power of GPU acceleration through Tensorflow, rendering them capable of effortlessly handling datasets comprising millions of cells.

Availability and implementation: Scbean is released on the Python Package Index (PyPI) (https://pypi.org/project/scbean/) and GitHub (https://github.com/jhu99/scbean) under the MIT license. The documentation and example code can be found at https://scbean.readthedocs.io/en/latest/.

Figure 1.

Overview of a multi-omics dataset pipeline employing Scbean. (A) Data collection, preprocessing, and loading data into APIs in Scbean. (B) The latent embedding obtained through the integration process can be leveraged for various subsequent analyses, including identification of marker genes, batch normalization, clustering, and trajectory analysis. Furthermore, results generated by VISGP can be instrumental not only in identifying spatially variable genes but also in elucidating the tissue’s structural anatomy.

Figure 2.

Four APIs of SCBEAN. DAVAE supports integration of scRNA-seq, scATAC-seq, and spatial transcriptomics based on domain-adversarial and variational approximation. VIPCCA supports integration of unpaired single-cell multi-omics data, differential gene expression analysis based on non-linear canonical correlation analysis. VIMCCA supports joint-analysis of paired multi-modal single-cell datasets based on a multi-view latent variable model. VISGP supports the discovery of spatially variable genes exhibiting distinct expression patterns in spatial transcriptomic data.