Semi-supervised single-cell cross-modality translation using Polarbear

Zhang, Ran; Meng-Papaxanthos, Laetitia; Vert, Jean-Philippe; Noble, William Stafford

doi:10.1101/2021.11.18.467517

Cited by 7 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate CMOT’s inferred gene and protein expressions, we calculated Pearson’s correlation coefficient between the inferred and measured expression values of each cell (cell-wise). Also, we computed the gene-wise correlation between inferred and measured expression values across cells for each gene [10]. For peak inference in open chromatin regions, we used AUROC to evaluate the quality of CMOT’s binarized inferred peaks [10].…”

Section: Methodsmentioning

confidence: 99%

“…This evaluation also applied to the state-of-art methods that we compared. Classifying known cell type using inferred expression: For the human brain data with known brain cell type information, we evaluated the CMOT inferred expression of cell-type marker genes for classifying the cell type and calculated the AUPRC of the classification [10]. To this end, given a cell type, we labeled all cells that belong to the cell type as positive and the rest as negative.…”

Section: Evaluation Inference Versus Measurementmentioning

confidence: 99%

“…Comparison with state-of-arts: We compared CMOT with existing state-of-art methods, Seurat [6], MOFA+ [7], TotalVI [4], and Polarbear [10]. We reported the number of genes with improved correlation/AUROC w.r.t.…”

Section: Evaluation Inference Versus Measurementmentioning

confidence: 99%

“…Mouse Brain: Next, we applied CMOT to a SNARE-seq dataset that jointly profiled gene expression and open chromatin regions of single cells in the adult mouse brain [24]. We also inferred gene expression from peak signals on open chromatin regions and compared CMOT with Polarbear [10] which previously used the same dataset. We split the dataset randomly into training, validation, and testing sets following Polarbear (using its source code).…”

Section: Single-cell Gene Expression Inference From Chromatin Accessi...mentioning

confidence: 99%

“…Babel [9] uses two autoencoders, one for each modality to infer a joint latent representation for cross-modal translation. Polarbear [10] also uses autoencoders, however, trains on both single and multi-modal data to infer each modality. However, such autoencoder-based approaches are unsupervised, and therefore lack a mechanism to introduce prior knowledge about underlying data distribution.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

CMOT: Cross Modality Optimal Transport for multimodal inference

Alatkar

Wang

2022

Preprint

View full text Add to dashboard Cite

Biological mechanisms are complex spanning multiple facets, each providing a unique view of the underlying mechanism. Recent single-cell technologies such as scRNA-seq and scATAC-seq have facilitated parallel probing into each of these facets, providing multimodal measurements of individual cells. An integrative analysis of these single-cell modalities can therefore provide a comprehensive understanding of specific cellular and molecular mechanisms. Despite the technological advances, simultaneous profiling of multiple modalities of single cells continues to be challenging as opposed to single modality measurements, and therefore, it may not always be feasible to conduct such profiling experiments (e.g., missing modalities). Furthermore, even with the available multimodalities, data integration remains elusive since modalities may not always have paired samples, leaving partial to no correspondence information. To address those challenges, we developed Cross-Modality Optimal Transport (CMOT), a computational approach to infer missing modalities of single cells based on optimal transport (OT). CMOT first aligns a group of cells (source) within available multi-modal data onto a common latent space. Then, it applies optimal transport to map the cells with a single modality (target) to the aligned cells in source from the same modality by minimizing their cost of transportation using Wasserstein distance. This distance can be regularized by prior knowledge (e.g., cell types) or induced cells clusters to improve mapping, and entropy of transport to speed up OT computations. Once transported, CMOT uses K-Nearest-Neighbors to infer the missing modality for the cells in target from another modality of mapped cells in source. Furthermore, the alignment of CMOT works for partially corresponding information from multi-modalities, i.e., allowing a fraction of unmatched cells in source. We evaluated CMOT on several emerging multi-modal datasets, e.g., gene and protein expression and chromatin accessibility in developing brain, cancers, and immunology. We found that not only does CMOT outperform existing state-of-art methods, but its inferred gene expression is biologically interpretable such as classifying cell types and cancer types.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Evaluation Inference Versus Measurementmentioning

confidence: 99%

Section: Evaluation Inference Versus Measurementmentioning

confidence: 99%

Section: Single-cell Gene Expression Inference From Chromatin Accessi...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CMOT: Cross Modality Optimal Transport for multimodal inference

Alatkar

Wang

2022

Preprint

View full text Add to dashboard Cite

show abstract

Single-cell omics: experimental workflow, data analyses and applications

Sun,

Li,

Sun

et al. 2024

Sci. China Life Sci.

View full text Add to dashboard Cite

Multi-condition and multi-modal temporal profile inference during mouse embryonic development

Zhang,

Qiu,

Filippova

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The emergence of single-cell time-series datasets enables modeling of changes in various types of cellular profiles over time. However, due to the disruptive nature of single-cell measurements, it is impossible to capture the full temporal trajectory of a particular cell. Furthermore, single-cell profiles can be collected at mismatched time points across different conditions (e.g., sex, batch, disease) and data modalities (e.g., scRNA-seq, scATAC-seq), which makes modeling challenging. Here we propose a joint modeling framework, Sunbear, for integrating multi-condition and multi-modal single-cell profiles across time. Sunbear can be used to impute single-cell temporal profile changes, align multi-dataset and multi-modal profiles across time, and extrapolate single-cell profiles in a missing modality. We applied Sunbear to reveal sex-biased transcription during mouse embryonic development and predict dynamic relationships between epigenetic priming and transcription for cells in which multi-modal profiles are unavailable. Sunbear thus enables the projection of single-cell time-series snapshots to multi-modal and multi-condition views of cellular trajectories.

show abstract

Semi-supervised single-cell cross-modality translation using Polarbear

Cited by 7 publications

References 26 publications

CMOT: Cross Modality Optimal Transport for multimodal inference

CMOT: Cross Modality Optimal Transport for multimodal inference

Single-cell omics: experimental workflow, data analyses and applications

Multi-condition and multi-modal temporal profile inference during mouse embryonic development

Contact Info

Product

Resources

About