Algorithmic advances in machine learning for single-cell expression analysis

Oller-Moreno, Sergio; Kloiber, Karin; Machart, Pierre; Bonn, Stefan

doi:10.1016/j.coisb.2021.02.002

Cited by 29 publications

(23 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methodologies cover a wide range of applications such as in silico data generation (e.g., cscGAN) (Marouf et al, 2020), data imputation (e.g., scIGANSs) (Xu et al, 2020) based on Generative Adversarial Networks (Goodfellow et al, 2014), data integration on unpaired datasets (e.g., totalVI) (Gayoso et al, 2021) or paired datasets (e.g., LIBRA) (Martinez- De-Morentin et al, 2021), among others. In summary, many of the methodologies associated with singlecell RNA-Seq analysis are using Machine Learning tools and new applications are appearing to refine many steps of the analysis framework described (Oller-Moreno et al, 2021).…”

Section: Lymphoid Cells In the Heartmentioning

confidence: 99%

Understanding the Adult Mammalian Heart at Single-Cell RNA-Seq Resolution

Marín-Sedeño

Morentin

Pérez‐Pomares

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

During the last decade, extensive efforts have been made to comprehend cardiac cell genetic and functional diversity. Such knowledge allows for the definition of the cardiac cellular interactome as a reasonable strategy to increase our understanding of the normal and pathologic heart. Previous experimental approaches including cell lineage tracing, flow cytometry, and bulk RNA-Seq have often tackled the analysis of cardiac cell diversity as based on the assumption that cell types can be identified by the expression of a single gene. More recently, however, the emergence of single-cell RNA-Seq technology has led us to explore the diversity of individual cells, enabling the cardiovascular research community to redefine cardiac cell subpopulations and identify relevant ones, and even novel cell types, through their cell-specific transcriptomic signatures in an unbiased manner. These findings are changing our understanding of cell composition and in consequence the identification of potential therapeutic targets for different cardiac diseases. In this review, we provide an overview of the continuously changing cardiac cellular landscape, traveling from the pre-single-cell RNA-Seq times to the single cell-RNA-Seq revolution, and discuss the utilities and limitations of this technology.

show abstract

Section: Lymphoid Cells In the Heartmentioning

confidence: 99%

Understanding the Adult Mammalian Heart at Single-Cell RNA-Seq Resolution

Marín-Sedeño

Morentin

Pérez‐Pomares

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

show abstract

“…Clustering is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups. Distance-based clustering [34,35], hierarchical clustering [36], community-based clustering [37,38], density-based clustering [39], soft clustering [40,41], and graph-based clustering [42] were widely applied to transcriptomic data analysis [43], pattern recognition [44], image processing [45] as well as heart failure [46] to reveal data internal characteristics.…”

Section: Unsupervised Learningmentioning

confidence: 99%

Review of applications and challenges of quantitative systems pharmacology modeling and machine learning for heart failure

Cheng

Qiu

Schmidt

et al. 2021

J Pharmacokinet Pharmacodyn

View full text Add to dashboard Cite

Quantitative systems pharmacology (QSP) is an important approach in pharmaceutical research and development that facilitates in silico generation of quantitative mechanistic hypotheses and enables in silico trials. As demonstrated by applications from numerous industry groups and interest from regulatory authorities, QSP is becoming an increasingly critical component in clinical drug development. With rapidly evolving computational tools and methods, QSP modeling has achieved important progress in pharmaceutical research and development, including for heart failure (HF). However, various challenges exist in the QSP modeling and clinical characterization of HF. Machine/deep learning (ML/DL) methods have had success in a wide variety of fields and disciplines. They provide data-driven approaches in HF diagnosis and modeling, and offer a novel strategy to inform QSP model development and calibration. The combination of ML/DL and QSP modeling becomes an emergent direction in the understanding of HF and clinical development new therapies. In this work, we review the current status and achievement in QSP and ML/DL for HF, and discuss remaining challenges and future perspectives in the field.

show abstract

“…Otherwise, scientists will not be able to ascertain BASs in broad populations, which would render BASs useless as the basis for a biodefense strategy. Scientists also need better models to eliminate nuisance technical variation that arises between different runs of the same single-modality 'omics experiment (i.e., batch effects) [107,108]. Assuming scientists can address these problems, the large volume, missingness, and high dimensionality of multi-omics data force researchers to make hard choices about how to extract and analyze pertinent information; these choices will influence their ability to uncover relevant BASs.…”

Section: As They Mature Multi-omics Approaches May Reveal More Bassmentioning

confidence: 99%

Beyond the List: Bioagent-Agnostic Signatures Could Enable a More Flexible and Resilient Biodefense Posture Than an Approach Based on Priority Agent Lists Alone

et al. 2021

View full text Add to dashboard Cite

As of 2021, the biothreat policy and research communities organize their efforts around lists of priority agents, which elides consideration of novel pathogens and biotoxins. For example, the Select Agents and Toxins list is composed of agents that historic biological warfare programs had weaponized or that have previously caused great harm during natural outbreaks. Similarly, lists of priority agents promulgated by the World Health Organization and the National Institute of Allergy and Infectious Diseases are composed of previously known pathogens and biotoxins. To fill this gap, we argue that the research/scientific and biodefense/biosecurity communities should categorize agents based on how they impact their hosts to augment current list-based paradigms. Specifically, we propose integrating the results of multi-omics studies to identify bioagent-agnostic signatures (BASs) of disease—namely, patterns of biomarkers that accurately and reproducibly predict the impacts of infection or intoxication without prior knowledge of the causative agent. Here, we highlight three pathways that investigators might exploit as sources of signals to construct BASs and their applicability to this framework. The research community will need to forge robust interdisciplinary teams to surmount substantial experimental, technical, and data analytic challenges that stand in the way of our long-term vision. However, if successful, our functionality-based BAS model could present a means to more effectively surveil for and treat known and novel agents alike.

show abstract

Algorithmic advances in machine learning for single-cell expression analysis

Cited by 29 publications

References 54 publications

Understanding the Adult Mammalian Heart at Single-Cell RNA-Seq Resolution

Understanding the Adult Mammalian Heart at Single-Cell RNA-Seq Resolution

Review of applications and challenges of quantitative systems pharmacology modeling and machine learning for heart failure

Beyond the List: Bioagent-Agnostic Signatures Could Enable a More Flexible and Resilient Biodefense Posture Than an Approach Based on Priority Agent Lists Alone

Contact Info

Product

Resources

About