Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods

Abstract

Human pluripotent stem cells have the potential for unlimited proliferation and controlled differentiation into various somatic cells, making them a unique tool for regenerative and personalized medicine. Determining the best clone selection is a challenging problem in this field and requires new sensing instruments and methods able to automatically assess the state of a growing colony ('phenotype') and make decisions about its destiny. One possible solution for such label-free, non-invasive assessment is to make phase-contrast images and/or videos of growing stem cell colonies, process the morphological parameters ('morphological portrait', or signal), link this information to the colony phenotype, and initiate an automated protocol for the colony selection. As a step in implementing this strategy, we used machine learning methods to find an effective model for classifying the human pluripotent stem cell colonies of three lines according to their morphological phenotype ('good' or 'bad'), using morphological parameters from the previously published data as predictors. We found that the model using cellular morphological parameters as predictors and artificial neural networks as the classification method produced the best average accuracy of phenotype prediction (67%). When morphological parameters of colonies were used as predictors, logistic regression was the most effective classification method (75% average accuracy). Combining the morphological parameters of cells and colonies resulted in the most effective model, with a 99% average accuracy of phenotype prediction. Random forest was the most efficient classification method for the combined data. We applied feature selection methods and showed that different morphological parameters were important for phenotype recognition via either cellular or colonial parameters. Our results indicate a necessity for retaining both cellular and colonial morphological information for predicting the phenotype and provide an optimal choice for the machine learning method. The classification models reported in this study could be used as a basis for developing and/or improving automated solutions to control the quality of human pluripotent stem cells for medical purposes.

Keywords: best clone; human embryonic stem cells; human pluripotent stem cells; machine learning; morphological phenotype.

Figure 1

Schematic representation of a device designed for the automated best clone selection. Red arrows indicate the direction of information processing within the device.

Figure 2

Performance of classification models trained on the combined cellular and colonial data: (a) Box plots for the nested cross-validation accuracy. Orange lines show the median accuracy values, boxes represent the interval between the lower and upper quartiles, whiskers mark the minimum and maximum accuracy values, and circles are outliers; (b) ROC-curves. The dashed line represents a random classifier, which assigns phenotypes randomly. NB: naïve Bayes; KNN: k-nearest neighbors; LR: logistic regression; SVM: support vector machines; RF: random forest; NN: neural networks.

Figure 3

Mean SHAP values representing the importance of the morphological features in the best classification models based on (a) cell data, (b) colony data, and (c) combined data. Names of cellular parameters start with ‘Cell’, and names of colonial ones start with ‘Col’. A: Area; P: Perimeter; MA: Minor axis; FD: Feret’s diameter D; MFD: Minimal Feret’s diameter D; SF: Shape factor; AIS: Area of intercellular space (only for colonies).