SiVAE: Interpretable Deep Generative Models for Single-cell Transcriptomes

Overview

Journal Genome Biol

Specialties Biology
Genetics

Date 2023 Feb 21

PMID 36803416

Authors

Yongin Choi

Ruoxin Li

Gerald Quon

Affiliations

Soon will be listed here.

Abstract

Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. We present siVAE, a VAE that is interpretable by design, thereby enhancing downstream analysis tasks. Through interpretation, siVAE also identifies gene modules and hubs without explicit gene network inference. We use siVAE to identify gene modules whose connectivity is associated with diverse phenotypes such as iPSC neuronal differentiation efficiency and dementia, showcasing the wide applicability of interpretable generative models for genomic data analysis.

Citing Articles

Infusing structural assumptions into dimensionality reduction for single-cell RNA sequencing data to identify small gene sets.

Hackenberg M, Brunn N, Vogel T, Binder H Commun Biol. 2025; 8(1):414.

PMID: 40069486 PMC: 11897155. DOI: 10.1038/s42003-025-07872-9.

Interpretable single-cell factor decomposition using sciRED.

Pouyabahar D, Andrews T, Bader G Nat Commun. 2025; 16(1):1878.

PMID: 39987196 PMC: 11846867. DOI: 10.1038/s41467-025-57157-2.

Towards the Next Generation of Data-Driven Therapeutics Using Spatially Resolved Single-Cell Technologies and Generative AI.

Rodov A, Baniadam H, Zeiser R, Amit I, Yosef N, Wertheimer T Eur J Immunol. 2025; 55(2):e202451234.

PMID: 39964048 PMC: 11834372. DOI: 10.1002/eji.202451234.

BuDDI: Bulk Deconvolution with Domain Invariance to predict cell-type-specific perturbations from bulk.

Davidson N, Zhang F, Greene C PLoS Comput Biol. 2025; 21(1):e1012742.

PMID: 39823522 PMC: 11790236. DOI: 10.1371/journal.pcbi.1012742.

scGraph2Vec: a deep generative model for gene embedding augmented by graph neural network and single-cell omics data.

Lin S, Jia P Gigascience. 2024; 13.

PMID: 39704704 PMC: 11659981. DOI: 10.1093/gigascience/giae108.

References

Jiang L, Chen H, Pinello L, Yuan G . GiniClust: detecting rare cell types from single-cell gene expression data with Gini index. Genome Biol. 2016; 17(1):144. PMC: 4930624. DOI: 10.1186/s13059-016-1010-4. View

Bergen V, Lange M, Peidli S, Wolf F, Theis F . Generalizing RNA velocity to transient cell states through dynamical modeling. Nat Biotechnol. 2020; 38(12):1408-1414. DOI: 10.1038/s41587-020-0591-3. View

Wolf F, Angerer P, Theis F . SCANPY: large-scale single-cell gene expression data analysis. Genome Biol. 2018; 19(1):15. PMC: 5802054. DOI: 10.1186/s13059-017-1382-0. View

Castelo R, Roverato A . Reverse engineering molecular regulatory networks from microarray data with qp-graphs. J Comput Biol. 2009; 16(2):213-27. DOI: 10.1089/cmb.2008.08TT. View

Seninge L, Anastopoulos I, Ding H, Stuart J . VEGA is an interpretable generative model for inferring biological network activity in single-cell transcriptomics. Nat Commun. 2021; 12(1):5684. PMC: 8478947. DOI: 10.1038/s41467-021-26017-0. View

Popescu D, Botting R, Stephenson E, Green K, Webb S, Jardine L . Decoding human fetal liver haematopoiesis. Nature. 2019; 574(7778):365-371. PMC: 6861135. DOI: 10.1038/s41586-019-1652-y. View

Foroushani A, Agrahari R, Docking R, Chang L, Duns G, Hudoba M . Large-scale gene network analysis reveals the significance of extracellular matrix pathway and homeobox genes in acute myeloid leukemia: an introduction to the Pigengene package and its applications. BMC Med Genomics. 2017; 10(1):16. PMC: 5353782. DOI: 10.1186/s12920-017-0253-6. View

Jarada T, Rokne J, Alhajj R . SNF-NN: computational method to predict drug-disease interactions using similarity network fusion and neural networks. BMC Bioinformatics. 2021; 22(1):28. PMC: 7821180. DOI: 10.1186/s12859-020-03950-3. View

Zhang L, Chen X, Yin J . Prediction of Potential miRNA-Disease Associations Through a Novel Unsupervised Deep Learning Framework with Variational Autoencoder. Cells. 2019; 8(9). PMC: 6770222. DOI: 10.3390/cells8091040. View

10.

Qiu Y, Zheng H, Gevaert O . Genomic data imputation with variational auto-encoders. Gigascience. 2020; 9(8). PMC: 7407276. DOI: 10.1093/gigascience/giaa082. View

11.

Angerer P, Fischer D, Theis F, Scialdone A, Marr C . Automatic identification of relevant genes from low-dimensional embeddings of single-cell RNA-seq data. Bioinformatics. 2020; 36(15):4291-4295. PMC: 7520047. DOI: 10.1093/bioinformatics/btaa198. View

12.

Eraslan G, Simon L, Mircea M, Mueller N, Theis F . Single-cell RNA-seq denoising using a deep count autoencoder. Nat Commun. 2019; 10(1):390. PMC: 6344535. DOI: 10.1038/s41467-018-07931-2. View

13.

Choi Y, Li R, Quon G . siVAE: interpretable deep generative models for single-cell transcriptomes. Genome Biol. 2023; 24(1):29. PMC: 9940350. DOI: 10.1186/s13059-023-02850-y. View

14.

Chen H, Albergante L, Hsu J, Lareau C, Lo Bosco G, Guan J . Single-cell trajectories reconstruction, exploration and mapping of omics data with STREAM. Nat Commun. 2019; 10(1):1903. PMC: 6478907. DOI: 10.1038/s41467-019-09670-4. View

15.

Wu K, Yost K, Chang H, Zou J . BABEL enables cross-modality translation between multiomic profiles at single-cell resolution. Proc Natl Acad Sci U S A. 2021; 118(15). PMC: 8054007. DOI: 10.1073/pnas.2023070118. View

16.

Guo Y, Alexander K, Clark A, Grimson A, Yu H . Integrated network analysis reveals distinct regulatory roles of transcription factors and microRNAs. RNA. 2016; 22(11):1663-1672. PMC: 5066619. DOI: 10.1261/rna.048025.114. View

17.

Liesecke F, De Craene J, Besseau S, Courdavault V, Clastre M, Verges V . Improved gene co-expression network quality through expression dataset down-sampling and network aggregation. Sci Rep. 2019; 9(1):14431. PMC: 6783424. DOI: 10.1038/s41598-019-50885-8. View

18.

Goymer P . Network biology: why do we need hubs?. Nat Rev Genet. 2011; 9(9):650. DOI: 10.1038/nrg2450. View

19.

Ma S, Zhang B, LaFave L, Earl A, Chiang Z, Hu Y . Chromatin Potential Identified by Shared Single-Cell Profiling of RNA and Chromatin. Cell. 2020; 183(4):1103-1116.e20. PMC: 7669735. DOI: 10.1016/j.cell.2020.09.056. View

20.

Forni M, Peloggia J, Trudeau K, Shirihai O, Kowaltowski A . Murine Mesenchymal Stem Cell Commitment to Differentiation Is Regulated by Mitochondrial Dynamics. Stem Cells. 2015; 34(3):743-55. PMC: 4803524. DOI: 10.1002/stem.2248. View