4.7 Article

A universal framework for single-cell multi-omics data integration with graph convolutional networks

Related references

Note: Only part of the references are listed.
Article Biochemical Research Methods

SMILE: mutual information learning for integration of single-cell omics data

Yang Xu et al.

Summary: SMILE is an unsupervised deep learning algorithm that successfully integrates multi-source single-cell omics data and removes batch effects. By maximizing mutual information, it can project cell types from different tissues into a shared space and integrate data from different modalities.

BIOINFORMATICS (2022)

Review Biochemical Research Methods

A roadmap for multi-omics data integration using deep learning

Mingon Kang et al.

Summary: High-throughput next-generation sequencing allows for the generation of large amounts of multi-omics data, which has revolutionized biomedical research by providing a more comprehensive understanding of biological systems and disease development mechanisms. Deep learning algorithms have emerged as a promising method in multi-omics data analysis due to their predictive performance and ability to capture nonlinear and hierarchical features. However, integrating and translating multi-omics data into functional insights remains a challenge, but there is a clear trend towards incorporating multi-omics analysis in biomedical research to explain complex relationships between molecular layers.

BRIEFINGS IN BIOINFORMATICS (2022)

Article Biochemical Research Methods

Manifold alignment for heterogeneous single-cell multi-omics data integration using Pamona

Kai Cao et al.

Summary: Motivated by the need for effective approaches to integrate single-cell multi-omics data, this study presents Pamona, a partial Gromov-Wasserstein distance-based manifold alignment framework. It aims to delineate and represent the shared and dataset-specific cellular structures across modalities. Pamona demonstrates superior performance in accurately identifying shared and dataset-specific cells, recovering and aligning cellular structures, outperforming existing methods. The framework also allows for the incorporation of prior information to enhance alignment quality.

BIOINFORMATICS (2022)

Review Genetics & Heredity

Intricacies of single-cell multi-omics data integration

Pia Rautenstrauch et al.

Summary: A wealth of single-cell protocols enables the characterization of molecular layers at unprecedented resolution. Integrating multi-modal single-cell data to find cell-to-cell correspondences is challenging and requires considering biological abstraction and modal discrepancies.

TRENDS IN GENETICS (2022)

Article Biotechnology & Applied Microbiology

Bi-order multimodal integration of single-cell data

Jinzhuang Dou et al.

Summary: Integrating single-cell multiomics profiles generated by different single-cell technologies from the same biological sample remains challenging. Previous approaches have only provided approximate solutions. This study presents a novel mathematical solution called bi-order canonical correlation analysis (bi-CCA) that iteratively aligns the rows and columns of data matrices to generate accurate multimodal co-embeddings and discover cellular identity.

GENOME BIOLOGY (2022)

Review Biochemical Research Methods

Computational methods for the integrative analysis of single-cell data

Mattia Forcato et al.

Summary: Recent advances in single-cell technologies are providing exciting opportunities for dissecting tissue heterogeneity and investigating cell identity, fate and function. However, combining different single-cell genomic signals is computationally challenging and requires integrative analysis.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemical Research Methods

Ensemble learning models that predict surface protein abundance from single-cell multimodal omics data

Fan Xu et al.

Summary: In this study, different machine learning methods were compared and ensemble learning was found to outperform neural network models, with Random Forest performing the best overall. The feature importance scores from Random Forest were used to interpret biological mechanisms underlying the prediction, aiding in improving prediction performance. This research demonstrates the effectiveness of ensemble learning for reliable protein abundance prediction using single-cell multimodal omics data, and opens up avenues for knowledge discovery through mining large-scale single-cell multi-omics data.

METHODS (2021)

Article Biochemical Research Methods

ColorCells: a database of expression, classification and functions of lncRNAs in single cells

Ling-Ling Zheng et al.

Summary: The study developed ColorCells, a resource for comparative analysis of lncRNAs expression, classification, and functions in single-cell RNA-Seq data, identifying many cell-specific lncRNAs that show expression variability between different cell clusters and possess comparable cell classification ability to known marker genes; the cell-specific lncRNAs have been validated through in vitro experiments, and it was found that lncRNAs are typically co-expressed with mRNAs in the same cell cluster, which can help uncover their functions.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemical Research Methods

scGMAI: a Gaussian mixture model for clustering single-cell RNA-Seq data based on deep autoencoder

Bin Yu et al.

Summary: The scGMAI is a new single-cell Gaussian mixture clustering method that utilizes autoencoder networks and FastICA to accurately cluster and identify cell types from scRNA-Seq data, showing great potential in data analysis.

BRIEFINGS IN BIOINFORMATICS (2021)

Review Biochemical Research Methods

Dynamics of transcriptional and post-transcriptional regulation

Mattia Furlan et al.

Summary: Despite RNA abundance being commonly assumed as a proxy for transcriptional activity, it is now possible to calculate how synthesis, processing, and degradation rates collectively determine the abundance of each gene's RNA. Different transcriptional outputs can correspond to different combinations of kinetic rates, indicating the existence of markedly different modes of gene expression regulation and their profound effects on gene self-expression regulation.

BRIEFINGS IN BIOINFORMATICS (2021)

Review Biochemical Research Methods

Unsupervised and self-supervised deep learning approaches for biomedical text mining

Mohamed Nadif et al.

Summary: Biomedical scientific literature is growing rapidly, making it challenging to identify relevant results; automated information extraction tools based on text mining techniques are essential; deep neural networks have significantly advanced this research field.

BRIEFINGS IN BIOINFORMATICS (2021)

Review Biotechnology & Applied Microbiology

Computational principles and challenges in single-cell data integration

Ricard Argelaguet et al.

Summary: The development of single-cell multimodal assays has provided a powerful tool for investigating cellular heterogeneity in multiple dimensions. Data integration is a key challenge in analyzing single-cell multimodal data, with existing strategies utilizing similar mathematical ideas but having distinct goals and principles.

NATURE BIOTECHNOLOGY (2021)

Article Multidisciplinary Sciences

Single cell transcriptional and chromatin accessibility profiling redefine cellular heterogeneity in the adult human kidney

Yoshiharu Muto et al.

Summary: The integration of single cell transcriptome and chromatin accessibility datasets provides deeper insights into cell heterogeneity, demonstrating the potential of single nucleus ATAC-seq in the identification of cell identity and functional heterogeneity. Differentially accessible chromatin regions in promoters associated with differentially expressed genes suggest the involvement of transcription factors like NF-kappa B in driving transitions between cell subpopulations within the kidney. This multi-omics approach improves the detection of unique cell states and redefines cellular heterogeneity in specific regions of the kidney.

NATURE COMMUNICATIONS (2021)

Article Biochemical Research Methods

Bacteriophage classification for assembled contigs using graph convolutional network

Jiayu Shang et al.

Summary: Bacteriophages, viruses that infect bacteria, play crucial roles in microbial biology, but their classification faces challenges due to high diversity and limited knowledge. A novel semi-supervised learning model called PhaGCN combines DNA and protein sequence features to classify phage contigs effectively, showing competitive performance against existing tools in both simulated and real sequencing data.

BIOINFORMATICS (2021)

Article Biochemical Research Methods

Deep cross-omics cycle attention model for joint analysis of single-cell multi-omics data

Chunman Zuo et al.

Summary: DCCA is a computational tool for joint analysis of single-cell multi-omics data, capable of dissecting cellular heterogeneity, denoising and aggregating data, and constructing links between multi-omics data. By fine-tuning networks and inferring new transcriptional regulatory relations, DCCA demonstrates superior capability in analyzing and understanding complex biological processes.

BIOINFORMATICS (2021)

Article Biochemistry & Molecular Biology

Integrated analysis of multimodal single-cell data

Yuhan Hao et al.

Summary: The study introduces a weighted-nearest neighbor analysis framework to learn the relative utility of each data type in each cell, enabling integrative analysis of multiple modalities. Applied to a CITE-seq dataset, the method constructs a multimodal reference atlas of the circulating immune system and successfully identifies and validates previously unreported lymphoid subpopulations.
Article Multidisciplinary Sciences

scGCN is a graph convolutional networks algorithm for knowledge transfer in single cell omics

Qianqian Song et al.

Summary: Single-cell omics is a rapidly growing area in genomics, but leveraging disparate datasets for analysis is challenging. The scGCN, a graph convolutional network, allows for effective knowledge transfer across different omics datasets.

NATURE COMMUNICATIONS (2021)

Article Biotechnology & Applied Microbiology

mbImpute: an accurate and robust imputation method for microbiome data

Ruochen Jiang et al.

Summary: A critical challenge in microbiome data analysis is the presence of non-biological zeros, which distorts taxon abundance distributions. The proposed method mbImpute aims to identify and recover likely non-biological zeros by borrowing information jointly from similar samples, similar taxa, and optional metadata. The results demonstrate that mbImpute improves the identification of disease-related taxa in microbiome data and preserves non-zero distributions of taxa abundances.

GENOME BIOLOGY (2021)

Article Biotechnology & Applied Microbiology

A generalization of t-SNE and UMAP to single-cell multimodal omics

Van Hoan Do et al.

Summary: In this study, j-SNE and j-UMAP are introduced as natural generalizations for joint visualization of multimodal omics data, producing unified embeddings that agree better with known cell types and harmonize RNA and protein velocity landscapes across eight datasets.

GENOME BIOLOGY (2021)

Editorial Material Biochemical Research Methods

Single-cell multimodal omics: the power of many

Chenxu Zhu et al.

NATURE METHODS (2020)

Review Biotechnology & Applied Microbiology

Integrative Methods and Practical Challenges for Single-Cell Multi-omics

Anjun Ma et al.

TRENDS IN BIOTECHNOLOGY (2020)

Article Biochemical Research Methods

Unsupervised topological alignment for single-cell multi-omics integration

Kai Cao et al.

BIOINFORMATICS (2020)

Article Biochemistry & Molecular Biology

scIGANs: single-cell RNA-seq imputation using generative adversarial networks

Yungang Xu et al.

NUCLEIC ACIDS RESEARCH (2020)

Article Biochemical Research Methods

SCIM: universal single-cell matching with unpaired feature sets

Stefan G. Stark et al.

BIOINFORMATICS (2020)

Article Multidisciplinary Sciences

Benchmarking of cell type deconvolution pipelines for transcriptomics data

Francisco Avila Cobos et al.

NATURE COMMUNICATIONS (2020)

Article Biotechnology & Applied Microbiology

MOFA plus : a statistical framework for comprehensive integration of multi-modal single-cell data

Ricard Argelaguet et al.

GENOME BIOLOGY (2020)

Review Endocrinology & Metabolism

Integrated omics: tools, advances and future approaches

Biswapriya B. Misra et al.

JOURNAL OF MOLECULAR ENDOCRINOLOGY (2019)

Review Biochemical Research Methods

Methods to study RNA-protein interactions

Muthukumar Ramanathan et al.

NATURE METHODS (2019)

Review Genetics & Heredity

Integrative single-cell analysis

Tim Stuart et al.

NATURE REVIEWS GENETICS (2019)

Article Biochemistry & Molecular Biology

Comprehensive Integration of Single-Cell Data

Tim Stuart et al.

Article Biochemistry & Molecular Biology

Single-Cell Multi-omic Integration Compares and Contrasts Features of Brain Cell Identity

Joshua D. Welch et al.

Article Biochemical Research Methods

Fast, sensitive and accurate integration of single-cell data with Harmony

Ilya Korsunsky et al.

NATURE METHODS (2019)

Article Biotechnology & Applied Microbiology

Dimensionality reduction for visualizing single-cell data using UMAP

Etienne Becht et al.

NATURE BIOTECHNOLOGY (2019)

Article Biotechnology & Applied Microbiology

Assessment of computational methods for the analysis of single-cell ATAC-seq data

Huidong Chen et al.

GENOME BIOLOGY (2019)

Article Biotechnology & Applied Microbiology

Integrative single-cell analysis of transcriptional and epigenetic states in the human adult brain

Blue B. Lake et al.

NATURE BIOTECHNOLOGY (2018)

Article Biochemical Research Methods

DrImpute: imputing dropout events in single cell RNA sequencing data

Wuming Gong et al.

BMC BIOINFORMATICS (2018)

Article Biochemistry & Molecular Biology

Recovering Gene Interactions from Single-Cell Data Using Data Diffusion

David van Dijk et al.

Article Biotechnology & Applied Microbiology

Highly scalable generation of DNA methylation profiles in single cells

Ryan M. Mulqueen et al.

NATURE BIOTECHNOLOGY (2018)

Article Biotechnology & Applied Microbiology

Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors

Laleh Haghverdi et al.

NATURE BIOTECHNOLOGY (2018)

Article Biotechnology & Applied Microbiology

Integrating single-cell transcriptomic data across different conditions, technologies, and species

Andrew Butler et al.

NATURE BIOTECHNOLOGY (2018)

Article Biochemical Research Methods

SAVER: gene expression recovery for single-cell RNA sequencing

Mo Huang et al.

NATURE METHODS (2018)

Article Multidisciplinary Sciences

Single-cell profiling of the developing mouse brain and spinal cord with split-pool barcoding

Alexander B. Rosenberg et al.

SCIENCE (2018)

Article Multidisciplinary Sciences

An accurate and robust imputation method scImpute for single-cell RNA-seq data

Wei Vivian Li et al.

NATURE COMMUNICATIONS (2018)

Article Biochemistry & Molecular Biology

A Single-Cell Atlas of In Vivo Mammalian Chromatin Accessibility

Darren A. Cusanovich et al.

Article Biochemical Research Methods

Simultaneous epitope and transcriptome measurement in single cells

Marlon Stoeckius et al.

NATURE METHODS (2017)

Article Multidisciplinary Sciences

Massively parallel digital transcriptional profiling of single cells

Grace X. Y. Zheng et al.

NATURE COMMUNICATIONS (2017)

Article Biotechnology & Applied Microbiology

MATCHER: manifold alignment reveals correspondence between single cell transcriptome and epigenome dynamics

Joshua D. Welch et al.

GENOME BIOLOGY (2017)

Article Biochemistry & Molecular Biology

A Single-Cell Transcriptome Atlas of the Human Pancreas

Mauro J. Muraro et al.

CELL SYSTEMS (2016)

Review Biotechnology & Applied Microbiology

Design and computational analysis of single-cell RNA-sequencing experiments

Rhonda Bacher et al.

GENOME BIOLOGY (2016)

Article Multidisciplinary Sciences

Reducing the dimensionality of data with neural networks

G. E. Hinton et al.

SCIENCE (2006)