Machine Learning in Stem Cells Research: Application for Biosafety and Bioefficacy Assessment

Abstract

The applicability of machine learning-based analysis in the field of biomedical field has been very beneficial in determining the biological mechanism and validation for a wide range of biological scenarios. This approach is also gaining momentum in variou s stem cells research activities, specifically for stem cells characterization and differentiation pattern. The adoption of similar computational approaches to study and assess biosafety and bioefficacy risks of stem cells for clinical application is the n ext progression. In particular where tumorigenicity has been one of the major concerns in stem cells therapy. There are many factors influencing tumorigenicity in stem cells which may be difficult to capture under conventional laboratory settings. In addition, given the possible multifactorial etiology of tumorigenicity, defining a onesize-fits-all strategy to test such risk in stem cells might not be feasible and may compromise stem cells safety and effectiveness in therapy. Given the increase in biological datasets (which is no longer limited to genomic data) and the advancement of health informatics powered by state-of-the-art machine learning algorithms, there exists a potential for practical application in biosafety and bioefficacy of stem cells therap y. Here, we identified relevant machine learning approaches and suggested protocols intended for stem cells research focusing on the possibility of its usage for stem cells biosafety and bioefficacy assessment. Ultimately, generating models that may assist healthcare professionals to make a better-informed decision in stem cell therapy.

Deep learning models for cancer stem cell detection: a brief review

“…Overall, large, high-quality datasets are required to effectively train different models with deep learning in different kinds of CSCs. Currently, data are limited in the relatively new field for stem cell research, ( 67 ).…”

Exploring the Current Trends of Artificial Intelligence in Stem Cell Therapy: A Systematic Review

“…One other important concern for stem cell therapy is biosafety and bioefficacy. Zaman et al [ 24 ] reviewed this aspect by taking advantage of machine learning, where the use of imaging data and analysis characterized morphological and phenotypic changes in stem cells by comparing data from cancer and stem cells under various conditions and environmental perturbations, as well as coupling it with deep learning algorithms like CNN, SVM, and Naïve Bayes, which could ensure biosafety and bioefficacy [ 24 ]. Table 3 below summarizes the algorithms used in studies chosen for this review.…”

Stem Cells and Cancer Stem Cells: The Jekyll and Hyde Scenario and Their Implications in Stem Cell Therapy

“…Emerging technologies such as the use of machine learning have been proposed as one of the approaches to assess the safety and efficacy of cell therapy [ 115 ]. However, it would require an advanced database to generate accurate prediction models for the assessment.…”

“…This has raised concerns, particularly with the ability of stem cells to promote cancer-like characteristics and progression in accordance to their niche microenvironment, which may be uncontrollable once it applied in vivo. In this regard, an online live-cell monitoring method was proposed to monitor cells for genetic modification and to process irregularities during the expansion phase [ 115 ]. Apart from that, there is also a need to ensure stem-cell potency—reliable metrics in the form of standardised potency assays utilising the biomarkers proposed by the International Society for Cellular Therapy (ISCT) to evaluate the therapeutic potential for a range of mesenchymal stem-cell products [ 114 ].…”