4.2 Article

An introduction to representation learning for single-cell data analysis

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Fotomics: fourier transform-based omics imagification for deep learning-based cell-identity mapping using single-cell omics profiles

Seid Miad Zandavi et al.

Summary: This study proposes a method to transform high-dimensional molecular measurements into two-dimensional images, improving the representation and classification of biological samples using automated image recognition methods.

ARTIFICIAL INTELLIGENCE REVIEW (2023)

Letter Biotechnology & Applied Microbiology

A Python library for probabilistic analysis of single-cell omics data

Adam Gayoso et al.

NATURE BIOTECHNOLOGY (2022)

Article Biochemical Research Methods

Benchmarking atlas-level data integration in single-cell genomics

Malte D. Luecken et al.

Summary: This study benchmarked 68 method and preprocessing combinations on 85 batches of gene expression data, highlighting the importance of highly variable gene selection in improving method performance. When dealing with complex integration tasks, scANVI, Scanorama, scVI, and scGen consistently performed well, while the performance of single-cell ATAC-sequencing integration was strongly influenced by the choice of feature space.

NATURE METHODS (2022)

Article Multidisciplinary Sciences

C-type lectin receptor CLEC4A2 promotes tissue adaptation of macrophages and protects against atherosclerosis

Inhye Park et al.

Summary: CLEC4A2 is a distinguishing feature of vascular resident macrophages that have athero-protective properties. It promotes monocyte-to-macrophage differentiation and is critical for maintaining vascular homeostasis. CLEC4A2 deficiency leads to dysfunctional cholesterol metabolism and worsens the development of atherosclerosis.

NATURE COMMUNICATIONS (2022)

Article Biochemical Research Methods

Integration, exploration, and analysis of high-dimensional single-cell cytometry data using Spectre

Thomas Myles Ashhurst et al.

Summary: The Spectre R package enables comprehensive integration and analysis of high-dimensional cytometry data from different batches or experiments. It streamlines the analytical stages of raw data pre-processing, batch alignment, integration, clustering, visualization, and statistical analysis, making it suitable for bioinformaticians and laboratory scientists. Spectre's modular design allows for scalable analysis of very large datasets generated by flow cytometry, mass cytometry, or spectral cytometry.

CYTOMETRY PART A (2022)

Review Biochemistry & Molecular Biology

Computational Methods for Single-Cell Imaging and Omics Data Integration

Ebony Rose Watson et al.

Summary: Integrating single cell omics and imaging allows for a comprehensive understanding of the mechanisms driving tissue-level phenotypes. This review discusses the current technologies and methods for generating, processing, and analyzing single-cell omics and imaging data, and how they can be integrated to enhance our understanding of complex biological phenomena.

FRONTIERS IN MOLECULAR BIOSCIENCES (2022)

Article Oncology

The Spatial Landscape of Progression and Immunoediting in Primary Melanoma at Single-Cell Resolution

Ajit J. Nirmal et al.

Summary: This study investigates immune evasion and immunoediting in primary melanoma using high-plex imaging, 3D high-resolution microscopy, and spatially resolved microregion transcriptomics. The results show significant changes in cellular neighborhoods involving tumor, immune, and stromal cells during the progression of precursor states, melanoma in situ, and invasive tumor. Immunossuppression is already detectable in precursor regions, and a suppressive environment is formed along the tumor-stromal boundary during invasion, involving cytokine gradients, MHC-II expression, and PD1-PDL1-mediated cell contacts.

CANCER DISCOVERY (2022)

Article Biochemical Research Methods

Self-supervised deep learning encodes high-resolution features of protein subcellular localization

Hirofumi Kobayashi et al.

Summary: Cytoself is a self-supervised deep learning-based approach that accurately predicts and clusters protein localization from fluorescence images, providing insights into the diversity and complexity of cellular architecture.

NATURE METHODS (2022)

Article Biochemistry & Molecular Biology

Disentangling single-cell omics representation with a power spectral density-based feature extraction

Seid Miad Zandavi et al.

Summary: Emerging single-cell technologies provide high-resolution measurements of distinct cellular modalities, but the complexity and inaccuracies in single-cell sequencing measurements can hinder data analysis. This study presents a novel preprocessing method that reduces data complexity, enhances cell-type separation, and enables the identification of rare cells.

NUCLEIC ACIDS RESEARCH (2022)

Editorial Material Multidisciplinary Sciences

Diagonal integration of multimodal single-cell data: potential pitfalls and paths forward

Yang Xu et al.

Summary: Diagonal integration of multimodal single-cell data is a trending topic, but bridging gaps is essential to enable novel biological discoveries using diagonal methods.

NATURE COMMUNICATIONS (2022)

Review Oncology

Mapping Phenotypic Plasticity upon the Cancer Cell State Landscape Using Manifold Learning

Daniel B. Burkhardt et al.

Summary: Phenotypic plasticity refers to the ability of cancer cells to undergo dynamic non-genetic changes in cell state, which amplifies cancer heterogeneity and promotes metastasis and therapy evasion. With the advancement of technologies to record molecular mechanisms at single-cell resolution, manifold learning techniques can effectively model cell state dynamics, resembling our understanding of the cell state landscape. State-gating therapies targeting phenotypic plasticity are anticipated to limit cancer heterogeneity, metastasis, and therapy resistance.

CANCER DISCOVERY (2022)

Article Multidisciplinary Sciences

A strategy to quantify myofibroblast activation on a continuous spectrum

Alexander Hillsley et al.

Summary: The study developed a strategy based on microscopy imaging and machine learning methods to quantify the activation of myofibroblasts. The results demonstrated the existence of a continuous spectrum of myofibroblast activation and provided an imaging-based strategy to determine the position of a cell on that spectrum.

SCIENTIFIC REPORTS (2022)

Article Biochemical Research Methods

scSemiGAN: a single-cell semi-supervised annotation and dimensionality reduction framework based on generative adversarial network

Zhongyuan Xu et al.

Summary: The article proposes a single-cell semi-supervised cell-type annotation and dimensionality reduction framework based on a generative adversarial network, called scSemiGAN, which is capable of performing deep latent representation learning and cell-type label prediction simultaneously. scSemiGAN achieves competitive or superior performance in multiple downstream tasks including cell-type annotation, latent representation visualization, confounding factor removal, and enrichment analysis.

BIOINFORMATICS (2022)

Article Computer Science, Artificial Intelligence

Simultaneous dimensionality reduction and integration for single-cell ATAC-seq data using deep learning

Wolfgang Kopp et al.

Summary: Advancements in single-cell technologies have allowed for the study of chromatin accessibility at a more detailed level, but the complexity and heterogeneity of the data pose challenges for computational analysis. To address this, a dedicated computational approach using a variational auto-encoder has been developed, enabling both dimensionality reduction and batch correction for single-cell ATAC-seq data.

NATURE MACHINE INTELLIGENCE (2022)

Article Biotechnology & Applied Microbiology

Benchmarking clustering algorithms on estimating the number of cell types from single-cell RNA-sequencing data

Lijia Yu et al.

Summary: This study systematically benchmarks a range of clustering algorithms for single-cell RNA-seq data and summarizes the strengths and weaknesses of each method. The authors evaluate the performance of the algorithms using a large number of datasets and provide a multi-aspect recommendation to users.

GENOME BIOLOGY (2022)

Review Biotechnology & Applied Microbiology

Statistics or biology: the zero-inflation controversy about scRNA-seq data

Ruochen Jiang et al.

Summary: Researchers have differing views on the interpretation of zeros in single-cell RNA-seq data, with some considering them as biological signals while others see them as missing data; factors contributing to biological and non-biological zeros were discussed, as well as their impact on data analysis; emphasis was placed on the importance of transparent analysis.

GENOME BIOLOGY (2022)

Article Multidisciplinary Sciences

Multi-domain translation between single-cell imaging and sequencing data using autoencoders

Karren Dai Yang et al.

Summary: The authors use autoencoders to learn a probabilistic coupling and map different data modalities to a shared latent space, presenting an approach for integrating vastly different modalities. The integration of imaging and transcriptomics is still an open challenge, but this method provides a framework for diverse applications in biomedical discovery.

NATURE COMMUNICATIONS (2021)

Article Biochemistry & Molecular Biology

Semisupervised adversarial neural networks for single-cell classification

Jacob C. Kimmel et al.

Summary: scNym is a semi-supervised adversarial neural network that can transfer cell identity annotations between different experiments by learning rich representations of cell identities from both labeled and unlabeled datasets. It shows superior performance in transferring annotations across experiments and can synthesize information from multiple datasets to improve accuracy. Additionally, scNym models are well calibrated, interpretable, and can be enhanced with saliency methods.

GENOME RESEARCH (2021)

Article Multidisciplinary Sciences

Single-cell epigenomics reveals mechanisms of human cortical development

Ryan S. Ziffra et al.

Summary: During mammalian development, differences in chromatin state play a crucial role in cell fate specification and defining cell identity in the developing brain. Through studying chromatin accessibility patterns, it was found that cerebral organoids recapitulate most cell-type-specific enhancer accessibility patterns but lack some open chromatin regions found in vivo. Systematic comparison of chromatin accessibility across brain regions revealed unexpected diversity among neural progenitor cells and highlighted the role of retinoic acid signaling in neuronal lineage specification in the prefrontal cortex.

NATURE (2021)

Article Genetics & Heredity

ArchR is a scalable software package for integrative single-cell chromatin accessibility analysis

Jeffrey M. Granja et al.

Summary: ArchR is a software suite for single-cell chromatin accessibility analysis in R, allowing fast and comprehensive analysis and processing of single-cell chromatin accessibility data, providing multiple analysis functions, and capable of handling large amounts of single-cell data in a short period of time.

NATURE GENETICS (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)

Review Biochemistry & Molecular Biology

From imaging a single cell to implementing precision medicine: an exciting new era

Loukia G. Karacosta

Summary: In the age of high-throughput, single-cell biology, single-cell imaging has shown significant advancements both technologically and in translational applications. The synchronous progress of imaging and computational biology has opened up opportunities for merging the two, providing tools for observing, understanding, and predicting cellular and tissue phenotypes and behaviors. The use of multiplexed single-cell imaging and machine learning algorithms enables patient stratification and predictive diagnostics of clinical specimens. By harnessing computational tools and systems biology approaches, the exciting applications and future implementation of single-cell imaging in precision medicine can be further strengthened.

EMERGING TOPICS IN LIFE SCIENCES (2021)

Article Genetics & Heredity

A Comparison for Dimensionality Reduction Methods of Single-Cell RNA-seq Data

Ruizhi Xiang et al.

Summary: The study compared the performance of different dimensionality reduction methods in scRNA-seq data analysis. t-SNE showed the best accuracy and computing cost, while UMAP demonstrated high stability and preserved the cohesion and separation of cell populations.

FRONTIERS IN GENETICS (2021)

Review Biochemical Research Methods

Supervised application of internal validation measures to benchmark dimensionality reduction methods in scRNA-seq data

Forrest C. Koch et al.

Summary: The study conducted a comprehensive benchmark of dimensionality reduction methods in scRNA-seq data, evaluating the performance of over 25000 low-dimensional embeddings across 33 methods and 55 datasets using IVMs. The findings suggest that hyperparameter optimization with IVMs can lead to near-optimal clustering results.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemistry & Molecular Biology

Representation learning applications in biological sequence analysis

Hitoshi Iuchi et al.

Summary: Representation learning in biological sequence analysis is a critical method for converting biological sequences into vectors for function and structure estimation. By treating biological sequences as sentences and applying natural language processing techniques, we can better analyze and utilize large amounts of sequencing data.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2021)

Article Mathematical & Computational Biology

Penalized Latent Dirichlet Allocation Model in Single-Cell RNA Sequencing

Xiaotian Wu et al.

Summary: Single-cell RNA sequencing quantifies gene expression variation at individual cell level, and the penalized Latent Dirichlet Allocation (pLDA) model is developed to reduce the data dimension and extract robust and interpretable biological information from scRNA-seq data. The pLDA model considers genes as words, cells as documents, and latent biological functions as topics, showing improved performances in cell-type classification and providing interpretable topics with biological functions.

STATISTICS IN BIOSCIENCES (2021)

Article Biochemistry & Molecular Biology

Dimension Reduction and Clustering Models for Single-Cell RNA Sequencing Data: A Comparative Study

Chao Feng et al.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2020)

Review Urology & Nephrology

Tools for the analysis of high-dimensional single-cell RNA sequencing data

Yan Wu et al.

NATURE REVIEWS NEPHROLOGY (2020)

Review Biochemistry & Molecular Biology

Single-cell multiomics: technologies and data analysis methods

Jeongwoo Lee et al.

EXPERIMENTAL AND MOLECULAR MEDICINE (2020)

Article Multidisciplinary Sciences

Label-free detection of rare circulating tumor cells by image analysis and machine learning

Shen Wang et al.

SCIENTIFIC REPORTS (2020)

Editorial Material Multidisciplinary Sciences

Single cell transcriptomics comes of age

Sarah Aldridge et al.

NATURE COMMUNICATIONS (2020)

Article Computer Science, Artificial Intelligence

On hyperparameter optimization of machine learning algorithms: Theory and practice

Li Yang et al.

NEUROCOMPUTING (2020)

Article Biotechnology & Applied Microbiology

Benchmarking principal component analysis for large-scale single-cell RNA-sequencing

Koki Tsuyuzaki et al.

GENOME BIOLOGY (2020)

Article Genetics & Heredity

ComBat-seq: batch effect adjustment for RNA-seq count data

Yuqing Zhang et al.

NAR GENOMICS AND BIOINFORMATICS (2020)

Article Biotechnology & Applied Microbiology

A comparison of single-cell trajectory inference methods

Wouter Saelens et al.

NATURE BIOTECHNOLOGY (2019)

Article Biochemical Research Methods

cisTopic: cis-regulatory topic modeling on single-cell ATAC-seq data

Carmen Bravo Gonzalez-Blas et al.

NATURE METHODS (2019)

Review Engineering, Biomedical

Integrating imaging and omics data: A review

Laura Antonelli et al.

BIOMEDICAL SIGNAL PROCESSING AND CONTROL (2019)

Article Multidisciplinary Sciences

Structure-preserving visualisation of high dimensional single-cell datasets

Benjamin Szubert et al.

SCIENTIFIC REPORTS (2019)

Review Biochemical Research Methods

Beyond bulk: a review of single cell transcriptomics methodologies and applications

Ashwinikumar Kulkarni et al.

CURRENT OPINION IN BIOTECHNOLOGY (2019)

Article Biotechnology & Applied Microbiology

Massively parallel single-cell chromatin landscapes of human immune cell development and intratumoral T cell exhaustion

Ansuman T. Satpathy et al.

NATURE BIOTECHNOLOGY (2019)

Editorial Material Biochemical Research Methods

A dream of single-cell proteomics

Vivien Marx

NATURE METHODS (2019)

Article Biochemical Research Methods

Data denoising with transfer learning in single-cell transcriptomics

Jingshu Wang et al.

NATURE METHODS (2019)

Article Biochemical Research Methods

Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting

Alex X. Lu et al.

PLOS COMPUTATIONAL BIOLOGY (2019)

Article Biochemical Research Methods

Exploring single-cell data with deep multitasking neural networks

Matthew Amodio et al.

NATURE METHODS (2019)

Article Multidisciplinary Sciences

The art of using t-SNE for single-cell transcriptomics

Dmitry Kobak et al.

NATURE COMMUNICATIONS (2019)

Article Biotechnology & Applied Microbiology

Dimensionality reduction for visualizing single-cell data using UMAP

Etienne Becht et al.

NATURE BIOTECHNOLOGY (2019)

Article Multidisciplinary Sciences

Semisoft clustering of single-cell data

Lingxue Zhu et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

Article Biotechnology & Applied Microbiology

Visualizing structure and transitions in high-dimensional biological data

Kevin R. Moon et al.

NATURE BIOTECHNOLOGY (2019)

Article Multidisciplinary Sciences

Single-cell RNA-seq denoising using a deep count autoencoder

Goekcen Eraslan et al.

NATURE COMMUNICATIONS (2019)

Review Chemistry, Analytical

Advances in mass spectrometry based single-cell metabolomics

Kyle D. Duncan et al.

ANALYST (2019)

Article Biotechnology & Applied Microbiology

scPred: accurate supervised method for cell-type classification from single-cell RNA-seq data

Jose Alquicira-Hernandez et al.

GENOME BIOLOGY (2019)

Article Biotechnology & Applied Microbiology

Accuracy, robustness and scalability of dimensionality reduction methods for single-cell RNA-seq analysis

Shiquan Sun et al.

GENOME BIOLOGY (2019)

Article Biochemistry & Molecular Biology

Recovering Gene Interactions from Single-Cell Data Using Data Diffusion

David van Dijk et al.

Article Neurosciences

Single cell transcriptomics in neuroscience: cell classification and beyond

Bosiljka Tasic

CURRENT OPINION IN NEUROBIOLOGY (2018)

Article Multidisciplinary Sciences

Interpretable dimensionality reduction of single cell transcriptome data with deep generative models

Jiarui Ding et al.

NATURE COMMUNICATIONS (2018)

Article Biochemical Research Methods

Robust classification of single-cell transcriptome data by nonnegative matrix factorization

Chunxuan Shao et al.

BIOINFORMATICS (2017)

Article Multidisciplinary Sciences

Single-cell RNA-seq enables comprehensive tumour and immune cell profiling in primary breast cancer

Woosung Chung et al.

NATURE COMMUNICATIONS (2017)

Article Biology

The Human Cell Atlas

Aviv Regev et al.

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 Immunology

Mass cytometry: blessed with the curse of dimensionality

Evan W. Newell et al.

NATURE IMMUNOLOGY (2016)

Article Biotechnology & Applied Microbiology

SLICER: inferring branched, nonlinear cellular trajectories from single cell RNA-seq data

Joshua D. Welch et al.

GENOME BIOLOGY (2016)

Article Biochemical Research Methods

Diffusion maps for high-dimensional single-cell analysis of differentiation data

Laleh Haghverdi et al.

BIOINFORMATICS (2015)

Article Biotechnology & Applied Microbiology

Spatial reconstruction of single-cell gene expression data

Rahul Satija et al.

NATURE BIOTECHNOLOGY (2015)

Article Biochemical Research Methods

CIDRE: an illumination-correction method for optical microscopy

Kevin Smith et al.

NATURE METHODS (2015)

Article Biotechnology & Applied Microbiology

ZIFA: Dimensionality reduction for zero-inflated single-cell gene expression analysis

Emma Pierson et al.

GENOME BIOLOGY (2015)

Article Biotechnology & Applied Microbiology

The dynamics and regulators of cell fate decisions are revealed by pseudotemporal ordering of single cells

Cole Trapnell et al.

NATURE BIOTECHNOLOGY (2014)

Review Immunology

Single-cell technologies for monitoring immune systems

Pratip K. Chattopadhyay et al.

NATURE IMMUNOLOGY (2014)

Article Computer Science, Artificial Intelligence

Nonnegative Matrix Factorization: A Comprehensive Review

Yu-Xiong Wang et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2013)

Article Biochemical Research Methods

Comparison of Methods for Image-Based Profiling of Cellular Morphological Responses to Small-Molecule Treatment

Vebjorn Ljosa et al.

JOURNAL OF BIOMOLECULAR SCREENING (2013)

Review Computer Science, Hardware & Architecture

A Few Useful Things to Know About Machine Learning

Pedro Domingos

COMMUNICATIONS OF THE ACM (2012)

Article Computer Science, Artificial Intelligence

Understanding the phase contrast optics to restore artifact-free microscopy images for segmentation

Zhaozheng Yin et al.

MEDICAL IMAGE ANALYSIS (2012)

Article Biochemistry & Molecular Biology

Cellular Heterogeneity: Do Differences Make a Difference?

Steven J. Altschuler et al.

Review Oncology

Systems microscopy: An emerging strategy for the life sciences

John G. Lock et al.

EXPERIMENTAL CELL RESEARCH (2010)

Article Biotechnology & Applied Microbiology

CellProfiler: image analysis software for identifying and quantifying cell phenotypes

Anne E. Carpenter et al.

GENOME BIOLOGY (2006)

Article Computer Science, Artificial Intelligence

Laplacian eigenmaps for dimensionality reduction and data representation

M Belkin et al.

NEURAL COMPUTATION (2003)

Article Multidisciplinary Sciences

Nonlinear dimensionality reduction by locally linear embedding

ST Roweis et al.

SCIENCE (2000)

Article Multidisciplinary Sciences

A global geometric framework for nonlinear dimensionality reduction

JB Tenenbaum et al.

SCIENCE (2000)