scholarly journals Data-driven comparison of multiple high-dimensional single-cell expression profiles

2021 ◽  
Author(s):  
Daigo Okada ◽  
Jian Hao Cheng ◽  
Cheng Zheng ◽  
Ryo Yamada
Keyword(s):  
Machine Learning ◽  
Single Cell ◽  
Expression Profiles ◽  
Data Driven ◽  
Gene Set Analysis ◽  
High Dimensional ◽  
Biological Method ◽  
Gene Set ◽  
Cell Expression ◽  
And Control

AbstractComparing multiple single-cell expression datasets such as cytometry and scRNA-seq data between case and control donors provides information to elucidate the mechanisms of disease. We propose a completely data-driven computational biological method for this task. This overcomes the challenges of conventional cellular subset-based comparisons and facilitates further analyses such as machine learning and gene set analysis of single-cell expression datasets.

Insights into therapeutic targets and biomarkers using integrated multi-‘omics’ approaches for dilated and ischemic cardiomyopathies

2021 ◽  
Author(s):  
Austė Kanapeckaitė ◽  
Neringa Burokienė
Keyword(s):  
Machine Learning ◽  
Single Cell ◽  
Learning Algorithm ◽  
Expression Profiles ◽  
Therapeutic Targets ◽  
Development Stage ◽  
Biological Data ◽  
Specific Gene ◽  
Tissue Remodelling ◽  
Pharmacological Management

Abstract At present, heart failure (HF) treatment only targets the symptoms based on the left ventricle dysfunction severity; however, the lack of systemic ‘omics’ studies and available biological data to uncover the heterogeneous underlying mechanisms signifies the need to shift the analytical paradigm towards network-centric and data mining approaches. This study, for the first time, aimed to investigate how bulk and single cell RNA-sequencing as well as the proteomics analysis of the human heart tissue can be integrated to uncover HF-specific networks and potential therapeutic targets or biomarkers. We also aimed to address the issue of dealing with a limited number of samples and to show how appropriate statistical models, enrichment with other datasets as well as machine learning-guided analysis can aid in such cases. Furthermore, we elucidated specific gene expression profiles using transcriptomic and mined data from public databases. This was achieved using the two-step machine learning algorithm to predict the likelihood of the therapeutic target or biomarker tractability based on a novel scoring system, which has also been introduced in this study. The described methodology could be very useful for the target or biomarker selection and evaluation during the pre-clinical therapeutics development stage as well as disease progression monitoring. In addition, the present study sheds new light into the complex aetiology of HF, differentiating between subtle changes in dilated cardiomyopathies (DCs) and ischemic cardiomyopathies (ICs) on the single cell, proteome and whole transcriptome level, demonstrating that HF might be dependent on the involvement of not only the cardiomyocytes but also on other cell populations. Identified tissue remodelling and inflammatory processes can be beneficial when selecting targeted pharmacological management for DCs or ICs, respectively.

scholarly journals Single-Cell Expression Landscape of SARS-CoV-2 Receptor ACE2 and Host Proteases in Normal and Malignant Lung Tissues from Pulmonary Adenocarcinoma Patients

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1250
Author(s):  
Guangchun Han ◽  
Ansam Sinjab ◽  
Kieko Hara ◽  
Warapen Treekitkarnmongkol ◽  
Patrick Brennan ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Single Cell ◽  
Cancer Patients ◽  
Expression Profiles ◽  
Lung Cells ◽  
Alveolar Type ◽  
Specific Expression ◽  
Lung Cancer Patients ◽  
Normal Tissues ◽  
Cell Expression

The novel coronavirus SARS-CoV-2 is the causative agent of the COVID-19 pandemic. Severely symptomatic COVID-19 is associated with lung inflammation, pneumonia, and respiratory failure, thereby raising concerns of elevated risk of COVID-19-associated mortality among lung cancer patients. Angiotensin-converting enzyme 2 (ACE2) is the major receptor for SARS-CoV-2 entry into lung cells. The single-cell expression landscape of ACE2 and other SARS-CoV-2-related genes in pulmonary tissues of lung cancer patients remains unknown. We sought to delineate single-cell expression profiles of ACE2 and other SARS-CoV-2-related genes in pulmonary tissues of lung adenocarcinoma (LUAD) patients. We examined the expression levels and cellular distribution of ACE2 and SARS-CoV-2-priming proteases TMPRSS2 and TMPRSS4 in 5 LUADs and 14 matched normal tissues by single-cell RNA-sequencing (scRNA-seq) analysis. scRNA-seq of 186,916 cells revealed epithelial-specific expression of ACE2, TMPRSS2, and TMPRSS4. Analysis of 70,030 LUAD- and normal-derived epithelial cells showed that ACE2 levels were highest in normal alveolar type 2 (AT2) cells and that TMPRSS2 was expressed in 65% of normal AT2 cells. Conversely, the expression of TMPRSS4 was highest and most frequently detected (75%) in lung cells with malignant features. ACE2-positive cells co-expressed genes implicated in lung pathobiology, including COPD-associated HHIP, and the scavengers CD36 and DMBT1. Notably, the viral scavenger DMBT1 was significantly positively correlated with ACE2 expression in AT2 cells. We describe normal and tumor lung epithelial populations that express SARS-CoV-2 receptor and proteases, as well as major host defense genes, thus comprising potential treatment targets for COVID-19 particularly among lung cancer patients.

Applications of Data-Driven Modelling and Machine Learning in Control of Water Resources

2011 ◽  
pp. 197-217 ◽  
Author(s):  
D. P. Solomatine
Keyword(s):  
Machine Learning ◽  
Water Resources ◽  
Computational Intelligence ◽  
Flood Control ◽  
Water Levels ◽  
Data Driven ◽  
Real Time Control ◽  
Modeling And Control ◽  
Physically Based ◽  
And Control

Traditionally, management and control of water resources is based on behavior-driven or physically based models based on equations describing the behavior of water bodies. Since recently models built on the basis of large amounts of collected data are gaining popularity. This modeling approach we will call data-driven modeling; it borrows methods from various areas related to computational intelligence—machine learning, data mining, soft computing, etc. The chapter gives an overview of successful applications of several data-driven techniques in the problems of water resources management and control. The list of such applications includes: using decision trees in classifying flood conditions and water levels in the coastal zone depending on the hydrometeorological data, using artificial neural networks (ANN) and fuzzy rule-based systems for building controllers for real-time control of water resources, using ANNs and M5 model trees in flood control, using chaos theory in predicting water levels for ship guidance, etc. Conclusions are drawn on the applicability of the mentioned methods and the future role of computational intelligence in modeling and control of water resources.

scholarly journals Machine Learning of Hematopoietic Stem Cell Divisions from Paired Daughter Cell Expression Profiles Reveals Effects of Aging on Self-Renewal

Cell Systems ◽  
2020 ◽  
Vol 11 (6) ◽  
pp. 640-652.e5 ◽  
Author(s):  
Fumio Arai ◽  
Patrick S. Stumpf ◽  
Yoshiko M. Ikushima ◽  
Kentaro Hosokawa ◽  
Aline Roch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Stem Cell ◽  
Daughter Cell ◽  
Expression Profiles ◽  
Self Renewal ◽  
Hematopoietic Stem ◽  
Cell Divisions ◽  
Stem Cell Divisions ◽  
Effects Of Aging ◽  
Cell Expression

Single-cell expression profiles of melanoma

Science ◽  
2016 ◽  
Vol 352 (6282) ◽  
pp. 183-185
Author(s):  
L. M. Zahn
Keyword(s):  
Single Cell ◽  
Expression Profiles ◽  
Cell Expression

scholarly journals Machine learning of stem cell identities from single-cell expression data via regulatory network archetypes

2017 ◽  
Author(s):  
Patrick S Stumpf ◽  
Ben D MacArthur
Keyword(s):  
Machine Learning ◽  
Stem Cells ◽  
Stem Cell ◽  
Single Cell ◽  
Regulatory Network ◽  
Cell Biology ◽  
Embryonic Stem ◽  
Network Activity ◽  
Expression Data ◽  
Cell Expression

AbstractThe molecular regulatory network underlying stem cell pluripotency has been intensively studied, and we now have a reliable ensemble model for the ‘average’ pluripotent cell. However, evidence of significant cell-to-cell variability suggests that the activity of this network varies within individual stem cells, leading to differential processing of environmental signals and variability in cell fates. Here, we adapt a method originally designed for face recognition to infer regulatory network patterns within individual cells from single-cell expression data. Using this method we identify three distinct network configurations in cultured mouse embryonic stem cells – corresponding to naïve and formative pluripotent states and an early primitive endoderm state – and associate these configurations with particular combinations of regulatory network activity archetypes that govern different aspects of the cell’s response to environmental stimuli, cell cycle status and core information processing circuitry. These results show how variability in cell identities arise naturally from alterations in underlying regulatory network dynamics and demonstrate how methods from machine learning may be used to better understand single cell biology, and the collective dynamics of cell communities.

scholarly journals SPRING: a kinetic interface for visualizing high dimensional single-cell expression data

2016 ◽  
Author(s):  
Caleb Weinreb ◽  
Samuel Wolock ◽  
Allon Klein
Keyword(s):  
Gene Expression ◽  
Single Cell ◽  
Nearest Neighbor ◽  
High Dimensional ◽  
K Nearest Neighbor ◽  
Link Type ◽  
Cell Gene Expression ◽  
Graph Layouts ◽  
Cell Expression ◽  
Cell Data

MotivationSingle-cell gene expression profiling technologies can map the cell states in a tissue or organism. As these technologies become more common, there is a need for computational tools to explore the data they produce. In particular, existing data visualization approaches are imperfect for studying continuous gene expression topologies.ResultsForce-directed layouts of k-nearest-neighbor graphs can visualize continuous gene expression topologies in a manner that preserves high-dimensional relationships and allows manually exploration of different stable two-dimensional representations of the same data. We implemented an interactive web-tool to visualize single-cell data using force-directed graph layouts, called SPRING. SPRING reveals more detailed biological relationships than existing approaches when applied to branching gene expression trajectories from hematopoietic progenitor cells. Visualizations from SPRING are also more reproducible than those of stochastic visualization methods such as tSNE, a state-of-the-art tool.Availabilityhttps://kleintools.hms.harvard.edu/tools/spring.html,https://github.com/AllonKleinLab/SPRING/[email protected], [email protected]

scholarly journals Single-cell transcriptomic catalog of mouse cortical development

2017 ◽  
Author(s):  
Lipin Loo ◽  
Jeremy M. Simon ◽  
Eric S. McCoy ◽  
Jesse K. Niehaus ◽  
Mark J. Zylka
Keyword(s):  
Cerebral Cortex ◽  
Single Cell ◽  
Neurological Disease ◽  
Expression Profiles ◽  
Cortical Development ◽  
Brain Diseases ◽  
Mouse Cerebral Cortex ◽  
Transcriptomics Data ◽  
Disease Associated Genes ◽  
Cell Expression

We generated a single-cell transcriptomic catalog of the developing mouse cerebral cortex that includes numerous classes of neurons, progenitors, and glia, their proliferation, migration, and activation states, and their relatedness within and across timepoints. Cell expression profiles stratified neurological disease-associated genes into distinct subtypes. Complex neurodevelopmental processes can be reconstructed with single-cell transcriptomics data, permitting a deeper understanding of cortical development and the cellular origins of brain diseases.

Sign in / Sign up

Export Citation Format

Share Document