MultiVI: deep generative model for the integration of multimodal data

Tal Ashuach; Mariano I Gabitto; Rohan V Koodli; Giuseppe-Antonio Saldi; Michael I Jordan; Nir Yosef

doi:10.1038/s41592-023-01909-9

MultiVI: deep generative model for the integration of multimodal data

Nat Methods. 2023 Aug;20(8):1222-1231. doi: 10.1038/s41592-023-01909-9. Epub 2023 Jun 29.

Authors

Tal Ashuach^#^{1

2}, Mariano I Gabitto^#^{3

4

5}, Rohan V Koodli², Giuseppe-Antonio Saldi⁶, Michael I Jordan^{2

7}, Nir Yosef^{8

9

10}

Affiliations

¹ Center for Computational Biology, University of California, Berkeley, CA, USA.
² Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA.
³ Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA. [email protected].
⁴ Department of Statistics, University of California, Berkeley, Berkeley, CA, USA. [email protected].
⁵ Allen Institute for Brain Science, Seattle, WA, USA. [email protected].
⁶ Allen Institute for Brain Science, Seattle, WA, USA.
⁷ Department of Statistics, University of California, Berkeley, Berkeley, CA, USA.
⁸ Center for Computational Biology, University of California, Berkeley, CA, USA. [email protected].
⁹ Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA. [email protected].
¹⁰ Department of Systems Immunology, Weizmann Institute of Science, Rehovot, Israel. [email protected].

^# Contributed equally.

Abstract

Jointly profiling the transcriptome, chromatin accessibility and other molecular properties of single cells offers a powerful way to study cellular diversity. Here we present MultiVI, a probabilistic model to analyze such multiomic data and leverage it to enhance single-modality datasets. MultiVI creates a joint representation that allows an analysis of all modalities included in the multiomic input data, even for cells for which one or more modalities are missing. It is available at scvi-tools.org .

MultiVI: deep generative model for the integration of multimodal data

Authors

Affiliations

Abstract

Publication types

MeSH terms

Grants and funding