Machine Learning of Stem Cell Identities From Single-Cell Expression Data via Regulatory Network Archetypes

Deep learning models will shape the future of stem cell research

Our ability to understand and control stem cell biology is being augmented by developments on two fronts, our ability to collect more data describing cell state and our capability to comprehend these data using deep learning models. Here we consider the impact deep learning will have in the future of stem cell research. We explore the importance of generating data suitable for these methods, the requirement for close collaboration between experimental and computational researchers, and the challenges we face to do this fairly and effectively. Achieving this will ensure that the resulting deep learning models are biologically meaningful and computationally tractable.

A comprehensive survey of regulatory network inference methods using single cell RNA sequencing data

Gene regulatory network is a complicated set of interactions between genetic materials, which dictates how cells develop in living organisms and react to their surrounding environment. Robust comprehension of these interactions would help explain how cells function as well as predict their reactions to external factors. This knowledge can benefit both developmental biology and clinical research such as drug development or epidemiology research. Recently, the rapid advance of single-cell sequencing technologies, which pushed the limit of transcriptomic profiling to the individual cell level, opens up an entirely new area for regulatory network research. To exploit this new abundant source of data and take advantage of data in single-cell resolution, a number of computational methods have been proposed to uncover the interactions hidden by the averaging process in standard bulk sequencing. In this article, we review 15 such network inference methods developed for single-cell data. We discuss their underlying assumptions, inference techniques, usability, and pros and cons. In an extensive analysis using simulation, we also assess the methods' performance, sensitivity to dropout and time complexity. The main objective of this survey is to assist not only life scientists in selecting suitable methods for their data and analysis purposes but also computational scientists in developing new methods by highlighting outstanding challenges in the field that remain to be addressed in the future development.

Epithelial-Mesenchymal Transition Drives Three-Dimensional Morphogenesis in Mammalian Early Development

From fertilization to onset of gastrulation, a mammalian embryo goes through several rounds of cellular morphogenesis resembling phenomena of epithelial-mesenchymal transition (EMT) and mesenchymal-epithelial transition (MET), collectively referred to as EMTs. How these EMT events play a role in shaping the three-dimensional (3-D) architecture of the developing embryo is not well-understood. In this review, we present a model in which cellular morphogenesis, represented primarily by dynamic changes in its epithelialization status, is the driving force of embryonic 3-D organization. This is achieved through the integration of three key components of mammalian early development, the pluripotency regulation, morphogenetic signaling, and biomechanical force anisotropy. Although cells in an early embryo do not exhibit full mesenchymal characteristics, our model underscores the importance of investigating molecular regulation of epithelial cell polarity and partial EMT/MET in understanding mammalian early development.

The Importance of Computational Modeling in Stem Cell Research

The generation of large amounts of omics data is increasingly enabling not only the processing and analysis of large data sets but also the development of computational models in the field of stem cell research. Although computational models have been proposed in recent decades, we believe that the stem cell community is not fully aware of the potentiality of computational modeling in guiding their experimental research. In this regard, we discuss how single-cell technologies provide the right framework for computational modeling at different scales of biological organization in order to address challenges in the stem cell field and to guide experimentalists in the design of new strategies for stem cell therapies and treatment of congenital disorders.

A novel machine learning based approach for iPS progenitor cell identification

Identification of induced pluripotent stem (iPS) progenitor cells, the iPS forming cells in early stage of reprogramming, could provide valuable information for studying the origin and underlying mechanism of iPS cells. However, it is very difficult to identify experimentally since there are no biomarkers known for early progenitor cells, and only about 6 days after reprogramming initiation, iPS cells can be experimentally determined via fluorescent probes. What is more, the ratio of progenitor cells during early reprograming period is below 5%, which is too low to capture experimentally in the early stage. In this paper, we propose a novel computational approach for the identification of iPS progenitor cells based on machine learning and microscopic image analysis. Firstly, we record the reprogramming process using a live cell imaging system after 48 hours of infection with retroviruses expressing Oct4, Sox2 and Klf4, later iPS progenitor cells and normal murine embryonic fibroblasts (MEFs) within 3 to 5 days after infection are labeled by retrospectively tracing the time-lapse microscopic image. We then calculate 11 types of cell morphological and motion features such as area, speed, etc., and select best time windows for modeling and perform feature selection. Finally, a prediction model using XGBoost is built based on the selected six types of features and best time windows. Our model allows several missing values/frames in the sample datasets, thus it is applicable to a wide range of scenarios. Cross-validation, holdout validation and independent test experiments show that the minimum precision is above 52%, that is, the ratio of predicted progenitor cells within 3 to 5 days after viral infection is above 52%. The results also confirm that the morphology and motion pattern of iPS progenitor cells is different from that of normal MEFs, which helps with the machine learning methods for iPS progenitor cell identification.

Identification of induced pluripotent stem (iPS) progenitor cells could provide valuable information for studying the origin and underlying mechanism of iPS cells. However, it is very difficult to identify experimentally since there are no biomarkers known for early progenitor cells, and only after about 6 days of induction, iPS cells can be experimentally determined via fluorescent probes. What is more, the percentage of the progenitor cells during the early induction period is below 5%, too low to capture experimentally in early stage. In this work, we proposed an approach for the identification of iPS progenitor cells, the iPS forming cells, based on machine learning and microscopic image analysis. The aim is to help biologists to enrich iPS progenitor cells during the early stage of induction, which allows experimentalists to select iPS progenitor cells with much higher probability, and furthermore to study the biomarkers which trigger the reprogramming process.

Modeling Mammalian Commitment to the Neural Lineage Using Embryos and Embryonic Stem Cells

Early mammalian embryogenesis relies on a large range of cellular and molecular mechanisms to guide cell fate. In this highly complex interacting system, molecular circuitry tightly controls emergent properties, including cell differentiation, proliferation, morphology, migration, and communication. These molecular circuits include those responsible for the control of gene and protein expression, as well as metabolism and epigenetics. Due to the complexity of this circuitry and the relative inaccessibility of the mammalian embryo in utero, mammalian neural commitment remains one of the most challenging and poorly understood areas of developmental biology. In order to generate the nervous system, the embryo first produces two pluripotent populations, the inner cell mass and then the primitive ectoderm. The latter is the cellular substrate for gastrulation from which the three multipotent germ layers form. The germ layer definitive ectoderm, in turn, is the substrate for multipotent neurectoderm (neural plate and neural tube) formation, representing the first morphological signs of nervous system development. Subsequent patterning of the neural tube is then responsible for the formation of most of the central and peripheral nervous systems. While a large number of studies have assessed how a competent neurectoderm produces mature neural cells, less is known about the molecular signatures of definitive ectoderm and neurectoderm and the key molecular mechanisms driving their formation. Using pluripotent stem cells as a model, we will discuss the current understanding of how the pluripotent inner cell mass transitions to pluripotent primitive ectoderm and sequentially to the multipotent definitive ectoderm and neurectoderm. We will focus on the integration of cell signaling, gene activation, and epigenetic control that govern these developmental steps, and provide insight into the novel growth factor-like role that specific amino acids, such as L-proline, play in this process.