Systematic approaches to dissect biological processes in stem cells by image-based screening

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.

Automated collective motion analysis validates human keratinocyte stem cell cultures

Identification and quality assurance of stem cells cultured in heterogeneous cell populations are indispensable for successful stem cell therapy. Here we present an image-processing pipeline for automated identification and quality assessment of human keratinocyte stem cells. When cultivated under appropriate conditions, human epidermal keratinocyte stem cells give rise to colonies and exhibit higher locomotive capacity as well as significant proliferative potential. Image processing and kernel density estimation were used to automatically extract the area of keratinocyte colonies from phase-contrast images of cultures containing feeder cells. The DeepFlow algorithm was then used to calculate locomotion speed of the colony area by analyzing serial images. This image-processing pipeline successfully identified keratinocyte stem cell colonies by measuring cell locomotion speed, and also assessed the effect of oligotrophic culture conditions and chemical inhibitors on keratinocyte behavior. Therefore, this study provides automated procedures for image-based quality control of stem cell cultures and high-throughput screening of small molecules targeting stem cells.

High-Content Screening Approaches That Minimize Confounding Factors in RNAi, CRISPR, and Small Molecule Screening

Screening arrayed libraries of reagents, particularly small molecules began as a vehicle for drug discovery, but the in last few years it has become a cornerstone of biological investigation, joining RNAi and CRISPR as methods for elucidating functional relationships that could not be anticipated, and illustrating the mechanisms behind basic and disease biology, and therapeutic resistance. However, these approaches share some common challenges, especially with respect to specificity or selectivity of the reagents as they are scaled to large protein families or the genome. High-content screening (HCS) has emerged as an important complement to screening, mostly the result of a wide array of specific molecular events, such as protein kinase and transcription factor activation, morphological changes associated with stem cell differentiation or the epithelial-mesenchymal transition of cancer cells. Beyond the range of cellular events that can be screened by HCS, image-based screening introduces new processes for differentiating between specific and nonspecific effects on cells. This chapter introduces these complexities and discusses strategies available in image-based screening that can mitigate the challenges they can bring to screening.

Functional fingerprinting of human mesenchymal stem cells using high-throughput RNAi screening

Mesenchymal stem cells (MSCs) are promising candidates for cellular therapies ranging from tissue repair in regenerative medicine to immunomodulation in graft versus host disease after allogeneic transplantation or in autoimmune diseases. Nonetheless, progress has been hampered by their enormous phenotypic as well as functional heterogeneity and the lack of uniform standards and guidelines for quality control. In this study, we describe a method to perform cellular phenotyping by high-throughput RNA interference in primary human bone marrow MSCs. We have shown that despite heterogeneity of MSC populations, robust functional assays can be established that are suitable for high-throughput and high-content screening. We profiled primary human MSCs against human fibroblasts. Network analysis showed a kinome fingerprint that differs from human primary fibroblasts as well as fibroblast cell lines. In conclusion, this study shows that high-throughput screening in primary human MSCs can be reliably used for kinome fingerprinting.

Cell motion predicts human epidermal stemness

Keratinocyte stem cell colonies can be identified by analyzing cell motion, an emergent stem cell property.

Image-based identification of cultured stem cells and noninvasive evaluation of their proliferative capacity advance cell therapy and stem cell research. Here we demonstrate that human keratinocyte stem cells can be identified in situ by analyzing cell motion during their cultivation. Modeling experiments suggested that the clonal type of cultured human clonogenic keratinocytes can be efficiently determined by analysis of early cell movement. Image analysis experiments demonstrated that keratinocyte stem cells indeed display a unique rotational movement that can be identified as early as the two-cell stage colony. We also demonstrate that α6 integrin is required for both rotational and collective cell motion. Our experiments provide, for the first time, strong evidence that cell motion and epidermal stemness are linked. We conclude that early identification of human keratinocyte stem cells by image analysis of cell movement is a valid parameter for quality control of cultured keratinocytes for transplantation.

Characterization of time-course morphological features for efficient prediction of osteogenic potential in human mesenchymal stem cells

Human bone marrow mesenchymal stem cells (hBMSCs) represents one of the most frequently applied cell sources for clinical bone regeneration. To achieve the greatest therapeutic effect, it is crucial to evaluate the osteogenic differentiation potential of the stem cells during their culture before the implantation. However, the practical evaluation of stem cell osteogenicity has been limited to invasive biological marker analysis that only enables assaying a single end-point. To innovate around invasive quality assessments in clinical cell therapy, we previously explored and demonstrated the positive predictive value of using time-course images taken during differentiation culture for hBMSC bone differentiation potential. This initial method establishes proof of concept for a morphology-based cell evaluation approach, but reveals a practical limitation when considering the need to handle large amounts of image data. In this report, we aimed to scale-down our proposed method into a more practical, efficient modeling scheme that can be more broadly implemented by physicians on the frontiers of clinical cell therapy. We investigated which morphological features are critical during the osteogenic differentiation period to assure the performance of prediction models with reduced burden on image acquisition. To our knowledge, this is the first detailed characterization that describes both the critical observation period and the critical number of time-points needed for morphological features to adequately model osteogenic potential. Our results revealed three important observations: (i) the morphological features from the first 3 days of differentiation are sufficiently informative to predict bone differentiation potential, both activities of alkaline phosphatase and calcium deposition, after 3 weeks of continuous culture; (ii) intervals of 48 h are sufficient for measuring critical morphological features; and (iii) morphological features are most accurately predictive when early morphological features from the first 3 days of differentiation are combined with later features (after 10 days of differentiation). Biotechnol. Bioeng. 2014;111: 1430–1439.

Cell-based fuzzy metrics enhance high-content screening (HCS) assay robustness

High-content screening (HCS) allows the exploration of complex cellular phenotypes by automated microscopy and is increasingly being adopted for small interfering RNA genomic screening and phenotypic drug discovery. We introduce a series of cell-based evaluation metrics that have been implemented and validated in a mono-parametric HCS for regulators of the membrane trafficking protein caveolin 1 (CAV1) and have also proved useful for the development of a multiparametric phenotypic HCS for regulators of cytoskeletal reorganization. Imaging metrics evaluate imaging quality such as staining and focus, whereas cell biology metrics are fuzzy logic-based evaluators describing complex biological parameters such as sparseness, confluency, and spreading. The evaluation metrics were implemented in a data-mining pipeline, which first filters out cells that do not pass a quality criterion based on imaging metrics and then uses cell biology metrics to stratify cell samples to allow further analysis of homogeneous cell populations. Use of these metrics significantly improved the robustness of the monoparametric assay tested, as revealed by an increase in Z' factor, Kolmogorov-Smirnov distance, and strict standard mean difference. Cell biology evaluation metrics were also implemented in a novel supervised learning classification method that combines them with phenotypic features in a statistical model that exceeded conventional classification methods, thus improving multiparametric phenotypic assay sensitivity.

Fluorescence-based high-throughput functional profiling of ligand-gated ion channels at the level of single cells

Ion channels are involved in many physiological processes and are attractive targets for therapeutic intervention. Their functional properties vary according to their subunit composition, which in turn varies in a developmental and tissue-specific manner and as a consequence of pathophysiological events. Understanding this diversity requires functional analysis of ion channel properties in large numbers of individual cells. Functional characterisation of ligand-gated channels involves quantitating agonist and drug dose-response relationships using electrophysiological or fluorescence-based techniques. Electrophysiology is limited by low throughput and high-throughput fluorescence-based functional evaluation generally does not enable the characterization of the functional properties of each individual cell. Here we describe a fluorescence-based assay that characterizes functional channel properties at single cell resolution in high throughput mode. It is based on progressive receptor activation and iterative fluorescence imaging and delivers >100 dose-responses in a single well of a 384-well plate, using α1-3 homomeric and αβ heteromeric glycine receptor (GlyR) chloride channels as a model system. We applied this assay with transiently transfected HEK293 cells co-expressing halide-sensitive yellow fluorescent protein and different GlyR subunit combinations. Glycine EC₅₀ values of different GlyR isoforms were highly correlated with published electrophysiological data and confirm previously reported pharmacological profiles for the GlyR inhibitors, picrotoxin, strychnine and lindane. We show that inter and intra well variability is low and that clustering of functional phenotypes permits identification of drugs with subunit-specific pharmacological profiles. As this method dramatically improves the efficiency with which ion channel populations can be characterized in the context of cellular heterogeneity, it should facilitate systems-level analysis of ion channel properties in health and disease and the discovery of therapeutics to reverse pathological alterations.

Editorial: "crossing boundaries: stem cells, materials, and mesoscopic sciences"

"Crossing Boundaries: Stem Cells, Materials, and Mesoscopic Sciences". This Special Issue, edited by Prof. Anthony Ho and Prof. Norio Nakatsuji, comprises review articles on the interdisciplinary study of stem cells and material science and is a celebration of the friendship and collaboration between Heidelberg University and Kyoto University in Germany and Japan, respectively.