Multi-task learning from multimodal single-cell omics with Matilda

Hao, Huang; Yang, Pengyi

doi:10.1093/nar/gkad157

Cited by 14 publications

(7 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…S2, Methods). Ocelli was benchmarked against (i) graph-based method, WNN [43]; (ii) statistical framework for multimodal factor analysis, MOFA+ [44]; (iii) deep learning-based methods - Cobolt [35], scMM [36], Matilda [37], MultiVI [38]; and (iv) canonical correlation analysis method MOJITOO [48] (Supplementary Fig. S2a, Methods).…”

Section: Resultsmentioning

confidence: 99%

“…Scalability is a significant challenge for emerging computational methods in high-throughput single-cell genomics. We tested the scalability of Cobolt v0.0.1 [35], Matilda (first release version) [37], MDM, MOFA+ v0.7.0 [44], MOJITOO v1.0 [48], MultiVI v.0.19.0 [38], scMM v1.0.0 [36], and WNN (implemented in Seurat v4.9.9) [43] methods.…”

Section: Benchmarking Scalabilitymentioning

confidence: 99%

“…Deep learning [32] is the dominant branch of machine learning that gained popularity due to the increasing computational capabilities of modern computers [33]. While the variety of deep learning models is enormous, autoencoder architecture [34] has become the leading tool for visualizing multimodal single-cell data [35][36][37][38]. Autoencoder is a neural network that encodes and compresses complex, high-dimensional data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ocelli: an open-source tool for the visualization of developmental multimodal single-cell data

Rutkowski,

Tabaka

2023

Preprint

View full text Add to dashboard Cite

The recent expansion of single-cell technologies has enabled simultaneous genome-wide measurements of multiple modalities in the same single cell. The potential to jointly profile such modalities as gene expression, chromatin accessibility, protein epitopes, or multiple histone modifications at single-cell resolution represents a compelling opportunity to study developmental processes at multiple layers of gene regulation. Here, we present Ocelli, a lightweight Python package for scalable visualization and exploration of developmental multimodal single-cell data. The core functionality of Ocelli focuses on diffusion-based modeling of developmental processes. Ocelli addresses common tasks in developmental single-cell data analysis, such as visualization of cells on a low-dimensional embedding that preserves the continuity of the developmental progression of cells, identification of rare and transient cell states, integration with trajectory inference algorithms, and imputation of undetected feature counts. Extensive benchmarking shows that Ocelli outperforms existing methods regarding computational time and quality of the reconstructed low-dimensional representation of developmental data.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Benchmarking Scalabilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ocelli: an open-source tool for the visualization of developmental multimodal single-cell data

Rutkowski,

Tabaka

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning models excel in processing large datasets and approximating continuous relationships within the data, making them highly suitable for handling single-cell data to infer functional GRNs. A notable application is the use of autoencoders for dimension reduction and identifying potential regulatory relationships from various types of single-cell omics input data ( Liu et al., 2023a ). Additionally, many innovative approaches have emerged to utilize the matched scRNA-seq and scATAC-seq data ( Ma et al., 2023a ; Yuan and Duren, 2024 ).…”

Section: Reconstruction Of Transcriptional Regulatory Network With Mu...mentioning

confidence: 99%

Recent advances in exploring transcriptional regulatory landscape of crops

Huo,

Song,

2024

Front. Plant Sci.

View full text Add to dashboard Cite

Crop breeding entails developing and selecting plant varieties with improved agronomic traits. Modern molecular techniques, such as genome editing, enable more efficient manipulation of plant phenotype by altering the expression of particular regulatory or functional genes. Hence, it is essential to thoroughly comprehend the transcriptional regulatory mechanisms that underpin these traits. In the multi-omics era, a large amount of omics data has been generated for diverse crop species, including genomics, epigenomics, transcriptomics, proteomics, and single-cell omics. The abundant data resources and the emergence of advanced computational tools offer unprecedented opportunities for obtaining a holistic view and profound understanding of the regulatory processes linked to desirable traits. This review focuses on integrated network approaches that utilize multi-omics data to investigate gene expression regulation. Various types of regulatory networks and their inference methods are discussed, focusing on recent advancements in crop plants. The integration of multi-omics data has been proven to be crucial for the construction of high-confidence regulatory networks. With the refinement of these methodologies, they will significantly enhance crop breeding efforts and contribute to global food security.

show abstract

“…That is, predictions made by these models are often hard to interpret, especially towards understanding the underlying molecular mechanisms that drive cellular processes and phenotype. To this end, improving model interpretability has attracted increasing attention, in particular, in applications such as identifying molecular regulators and reconstructing biological networks ( Fortelny and Bock 2020 , Chen et al 2023 , Huang et al 2023 , Liu et al 2023 , Lotfollahi et al 2023 ).…”

Section: Introductionmentioning

confidence: 99%

Interpretable deep learning in single-cell omics

Wagle,

Long,

Chen

et al. 2024

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Motivation Single-cell omics technologies have enabled the quantification of molecular profiles in individual cells at an unparalleled resolution. Deep learning, a rapidly evolving sub-field of machine learning, has instilled a significant interest in single-cell omics research due to its remarkable success in analysing heterogeneous high-dimensional single-cell omics data. Nevertheless, the inherent multi-layer nonlinear architecture of deep learning models often makes them ‘black boxes’ as the reasoning behind predictions is often unknown and not transparent to the user. This has stimulated an increasing body of research for addressing the lack of interpretability in deep learning models, especially in single-cell omics data analyses, where the identification and understanding of molecular regulators are crucial for interpreting model predictions and directing downstream experimental validations. Results In this work, we introduce the basics of single-cell omics technologies and the concept of interpretable deep learning. This is followed by a review of the recent interpretable deep learning models applied to various single-cell omics research. Lastly, we highlight the current limitations and discuss potential future directions.

show abstract

Multi-task learning from multimodal single-cell omics with Matilda

Cited by 14 publications

References 43 publications

Ocelli: an open-source tool for the visualization of developmental multimodal single-cell data

Ocelli: an open-source tool for the visualization of developmental multimodal single-cell data

Recent advances in exploring transcriptional regulatory landscape of crops

Interpretable deep learning in single-cell omics

Contact Info

Product

Resources

About