bmVAE: a variational autoencoder method for clustering single-cell mutation data

Yan, Jiaqian; Ma, Ming; Yu, Zhenhua

doi:10.1093/bioinformatics/btac790

Cited by 12 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Solutions containing small clusters with less than 3 cells are marked as invalid and excluded. The effectiveness of the adopted GMM-based clustering approach has been demonstrated in previous studies [ 20 , 21 ].…”

Section: Methodsmentioning

confidence: 92%

“…For instance, Dhaka [ 20 ] uses a variational autoencoder (VAE) to reveal ITH from single-cell copy number alteration (CNA) or gene expression data. bmVAE [ 21 ] clusters single-cell mutation data based on a VAE model and estimates subclonal genotypes using a Gibbs sampling method. To jointly infer tumor subclones and single-cell CNAs, rcCAE [ 19 ] employs a convolutional AE to enhance the quality of scDNA-seq data and simultaneously learn representations of cells.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

scGAL: unmask tumor clonal substructure by jointly analyzing independent single-cell copy number and scRNA-seq data

Li,

Shi,

Song

et al. 2024

BMC Genomics

Self Cite

View full text Add to dashboard Cite

Background Accurately deciphering clonal copy number substructure can provide insights into the evolutionary mechanism of cancer, and clustering single-cell copy number profiles has become an effective means to unmask intra-tumor heterogeneity (ITH). However, copy numbers inferred from single-cell DNA sequencing (scDNA-seq) data are error-prone due to technically confounding factors such as amplification bias and allele-dropout, and this makes it difficult to precisely identify the ITH. Results We introduce a hybrid model called scGAL to infer clonal copy number substructure. It combines an autoencoder with a generative adversarial network to jointly analyze independent single-cell copy number profiles and gene expression data from same cell line. Under an adversarial learning framework, scGAL exploits complementary information from gene expression data to relieve the effects of noise in copy number data, and learns latent representations of scDNA-seq cells for accurate inference of the ITH. Evaluation results on three real cancer datasets suggest scGAL is able to accurately infer clonal architecture and surpasses other similar methods. In addition, assessment of scGAL on various simulated datasets demonstrates its high robustness against the changes of data size and distribution. scGAL can be accessed at: https://github.com/zhyu-lab/scgal. Conclusions Joint analysis of independent single-cell copy number and gene expression data from a same cell line can effectively exploit complementary information from individual omics, and thus gives more refined indication of clonal copy number substructure.

show abstract

Section: Methodsmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

scGAL: unmask tumor clonal substructure by jointly analyzing independent single-cell copy number and scRNA-seq data

Li,

Shi,

Song

et al. 2024

BMC Genomics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The VAE is composed of an encoder and a decoder. The original formulation was proposed in [26] and has been adapted for single cell data analysis by several tools published to data, including scVI, scVAE and bmVAE [27,28,29], among others.…”

Section: Vaementioning

confidence: 99%

SPARROW reveals cell states and functions influenced by microenvironment zones in complex tissues

Zhao,

Garber,

Gustafson

et al. 2024

Preprint

View full text Add to dashboard Cite

Spatially resolved transcriptomics technologies have significantly enhanced our ability to understand cellular characteristics within tissue contexts. However, they present a trade-off between spatial resolution and transcriptome coverage. This limitation, compounded with analytical tools treating cell type inference and cellular neighbourhood identification as separate processes, hinders a unified understanding of tissue features across scales. Our computational framework, SPARROW, infers cell types and delineates cellular organization patterns as microenvironment zones using an interconnected architecture. SPARROW algorithmically achieves single cell spatial resolution and whole transcriptome coverage by integrating spatially resolved transcriptomics and scRNA-seq data. Using SPARROW, we identified established and novel microenvironment zone-specific ligand-receptor mediated interactions in human tonsils, discoveries that would not be possible using either modality alone. Moreover, SPARROW uncovered novel cell states in the mouse hypothalamus, underscoring the influence of microenvironment zones on cell identities. Lastly, through its common latent spaces that facilitate cross-tissue comparisons, SPARROW revealed distinct inflammation states between different lymph node tissues. Overall, SPARROW integrates cellular gene expression with spatial organization, providing a comprehensive characterization of tissue features across scales and samples.

show abstract

“…Deep learning models have shown excellent performance in learning latent representations of high-dimensional single-cell data. For instance, variational autoencoder models enable more accurate clustering of single cells over a latent space [ 21 , 22 ]. The encoding–decoding process could be treated as a distillation process that fetches effective latent representations from noisy single-cell data by reconstructing the original data.…”

Section: Introductionmentioning

confidence: 99%

Inferring single-cell copy number profiles through cross-cell segmentation of read counts

Liu,

Shi,

2024

BMC Genomics

Self Cite

View full text Add to dashboard Cite

Background Copy number alteration (CNA) is one of the major genomic variations that frequently occur in cancers, and accurate inference of CNAs is essential for unmasking intra-tumor heterogeneity (ITH) and tumor evolutionary history. Single-cell DNA sequencing (scDNA-seq) makes it convenient to profile CNAs at single-cell resolution, and thus aids in better characterization of ITH. Despite that several computational methods have been proposed to decipher single-cell CNAs, their performance is limited in either breakpoint detection or copy number estimation due to the high dimensionality and noisy nature of read counts data. Results By treating breakpoint detection as a process to segment high dimensional read count sequence, we develop a novel method called DeepCNA for cross-cell segmentation of read count sequence and per-cell inference of CNAs. To cope with the difficulty of segmentation, an autoencoder (AE) network is employed in DeepCNA to project the original data into a low-dimensional space, where the breakpoints can be efficiently detected along each latent dimension and further merged to obtain the final breakpoints. Unlike the existing methods that manually calculate certain statistics of read counts to find breakpoints, the AE model makes it convenient to automatically learn the representations. Based on the inferred breakpoints, we employ a mixture model to predict copy numbers of segments for each cell, and leverage expectation–maximization algorithm to efficiently estimate cell ploidy by exploring the most abundant copy number state. Benchmarking results on simulated and real data demonstrate our method is able to accurately infer breakpoints as well as absolute copy numbers and surpasses the existing methods under different test conditions. DeepCNA can be accessed at: https://github.com/zhyu-lab/deepcna. Conclusions Profiling single-cell CNAs based on deep learning is becoming a new paradigm of scDNA-seq data analysis, and DeepCNA is an enhancement to the current arsenal of computational methods for investigating cancer genomics.

show abstract

bmVAE: a variational autoencoder method for clustering single-cell mutation data

Cited by 12 publications

References 37 publications

scGAL: unmask tumor clonal substructure by jointly analyzing independent single-cell copy number and scRNA-seq data

scGAL: unmask tumor clonal substructure by jointly analyzing independent single-cell copy number and scRNA-seq data

SPARROW reveals cell states and functions influenced by microenvironment zones in complex tissues

Inferring single-cell copy number profiles through cross-cell segmentation of read counts

Contact Info

Product

Resources

About