Predicting reprogramming-related gene expression from cell morphology in human induced pluripotent stem cells

Abstract

Purification is essential before differentiating human induced pluripotent stem cells (hiPSCs) into cells that fully express particular differentiation marker genes. High-quality iPSC clones are typically purified through gene expression profiling or visual inspection of the cell morphology; however, the relationship between the two methods remains unclear. We investigated the relationship between gene expression levels and morphology by analyzing live-cell phase-contrast images and mRNA profiles collected during the purification process. We employed this data and an unsupervised image feature extraction method to build a model that predicts gene expression levels from morphology. As a benchmark, we confirmed that the method can predict the gene expression levels from tissue images for cancer genes, performing as well as state-of-the-art methods. We then applied the method to iPSCs and identified two genes that are well-predicted from cell morphology. Although strong batch (or possibly donor) effects resulting from the reprogramming process preclude the ability to use the same model to predict across batches, prediction within a reprogramming batch is sufficiently robust to provide a practical approach for estimating expression levels of a few genes and monitoring the purification process.

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

“…The high classification accuracy of 98-99% that we have obtained approaches and sometimes exceeds the performance scores of previously reported classification models applied to pluripotent stem cells [11,12,[15][16][17][18][19][20][21][22][23][24]. Morphological parameters of cells and colonies used as predictors in our models are biologically interpretable but require methods for their extraction from the images prior to classification.…”

“…Other morphological characteristics, including morphological features of intracellular objects, have previously been considered and resulted in a classification accuracy of 80-89% [16,18]. Methods for automated feature extraction from images and videos of hPSCs with the subsequent application of supervised ML algorithms constitute another approach, with the reported classification accuracy values higher than 87% [19][20][21]24]. DL-based classification models applied directly to the images of hPSCs have been reported to perform at about 90% accuracy [12,23].…”

“…The first one comprises the phenotype classification models based on two-stage processing of the imaging data, in which biologically interpretable morphological features are first extracted from the hPSC images and then classification methods are applied with the extracted features as predictors [11,[15][16][17][18]. Studies from the second class apply DL methods (e.g., convolutional neural networks) directly to the colony images to infer the phenotype, or some less biologically interpretable features are automatically extracted using image processing methods followed by ML-based classification with these features as predictors [12,[19][20][21][22][23][24]. Despite the fact that the second approach often provides higher phenotype prediction accuracy, the first approach has an advantage in a clear biological interpretation of valuable morphological parameters found during this study, thus providing insights for possible new biological experiments.…”

Nanosensor Chemical Cytometry: Advances and Opportunities in Cellular Therapy and Precision Medicine

“…However, this information is mostly limited to the biophysical properties of single cell such as size, shape, volume, mass, or RI. The changes in the physical properties of cells can occur due to various reasons, such as changes in pH of the extracellular environment or fluctuations in the molecular expression levels within the single cell. − Therefore, for an accurate assessment of the live single cells, additional single cell information including proteomic or molecular attributes is critically required in addition to the biophysical attributes. To quantify the molecular information from individual therapeutic cells, it is essential to conduct chemical analyses tailored to the specific target analytes including substances secreted by cells, both internally and externally, such as reactive oxygen species (ROS), reactive nitrogen species (RNS), cytokines, or amino acids (AA) playing a critical role in cellular communications and metabolism.…”

High-volume, label-free imaging for quantifying single-cell dynamics in induced pluripotent stem cell colonies

“…The growth of pluripotent cells in multicellular colonies has posed challenges to quantitative imaging at the cellular level because of their close cell-cell contacts. Imaging at the colony level (7) or as groups of cells (8) in brightfield and fluorescence have led to knowledge about stem cell colony growth characteristics, gene expression, and classification at different stages of stem cell culture. Neural network-based algorithms have enabled greater discrimination of the characteristics of groups of iPSC and have been successfully used to predict differentiation (9) or distinguish between iPSC colonies, differentiated cells and dead cells from phase contrast images in an automated expansion culture setting (10)(11)(12).…”