Applying Machine Learning to Stem Cell Culture and Differentiation

Abstract

Machine learning techniques are increasingly becoming incorporated into biological research workflows in a variety of disciplines, most notably cancer research and drug discovery. Efforts in stem cell research comparatively lag behind. We detail key paradigms in machine learning, with a focus on equipping stem cell biologists with the understanding necessary to begin conceptualizing and designing machine learning workflows within their own domain of expertise. Supervised approaches in both regression and classification as well as unsupervised clustering techniques are all covered, with examples from across the biological sciences. High-throughput, high-content, multiplex assays for data acquisition are also discussed in the form of single-cell RNA sequencing and image-based approaches. Lastly, potential applications in stem cell biology, including the development of novel cell types, and improving model maturation are also discussed. Machine learning approaches applied in stem cell biology show promise in accelerating progress in developmental biology, drug screening, disease modeling, and personalized medicine.

Deep Learning Powered Identification of Differentiated Early Mesoderm Cells from Pluripotent Stem Cells

“…Using several CNN models, including Attention U-Net [ 10 ] with a DenseNet121 [ 11 ] backbone (for segmentation) and InceptionV3 (for classification) [ 12 ], we successfully segmented and classified the mesoderm cells and distinguished them from the non-mesoderm (endoderm and ectoderm) cells. Although there are a handful of stem cell morphology prediction studies using DL [ 13 , 14 , 15 ], to our knowledge, this is the first work with single cells that uses DL methods to capitalize on the cellular and nuclear morphological features in pixel space and identify the germ-layers with high accuracy. The use of DL makes the process accurate, fast, high throughput, and label free.…”

A literature review: machine learning-based stem cell investigation

“…Bioinformatics is a field of multidisciplinary that contains the application of computational techniques for analyzing and explaining many biological data which include genomics, proteogenomic, proteomic, and many-omic data ( 1 ). In the field of biology, machine learning (ML) algorithms can play a crucial role in handling and extracting patterns from the major and complex datasets generated in bioinformatics research ( 2 ). Different predictive models for various biological processes can be created using ML algorithms for predicting protein structure, function, or the likelihood of a genetic mutation causing disease.…”

Morphology-based deep learning approach for predicting adipogenic and osteogenic differentiation of human mesenchymal stem cells (hMSCs)

“…For example, MSCs morphology has been correlated with differentiation capacity ( Matsuoka et al, 2013 ; 2014 ; Lan et al, 2022a ) and passage number ( Lo Surdo and Bauer, 2012 ). Recent advancements in machine learning provide opportunities for predicting stem cell fate by utilizing large datasets of stem cell characteristics ( Fan et al, 2017 ; Ashraf et al, 2021 ; Zhu et al, 2021 ). Among these machine learning methods, deep learning techniques have emerged as powerful tools to predict and identify stem cell patterns and lineage relationships ( Kusumoto and Yuasa, 2019 ; Ren et al, 2021 ).…”