Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods
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 se...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Biomedicines |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9059/11/11/3005 |
_version_ | 1797460047605792768 |
---|---|
author | Ekaterina Vedeneeva Vitaly Gursky Maria Samsonova Irina Neganova |
author_facet | Ekaterina Vedeneeva Vitaly Gursky Maria Samsonova Irina Neganova |
author_sort | Ekaterina Vedeneeva |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-09T16:59:57Z |
format | Article |
id | doaj.art-6faaeadf55a745d6a0e51e9a22963e0b |
institution | Directory Open Access Journal |
issn | 2227-9059 |
language | English |
last_indexed | 2024-03-09T16:59:57Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomedicines |
spelling | doaj.art-6faaeadf55a745d6a0e51e9a22963e0b2023-11-24T14:31:08ZengMDPI AGBiomedicines2227-90592023-11-011111300510.3390/biomedicines11113005Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning MethodsEkaterina Vedeneeva0Vitaly Gursky1Maria Samsonova2Irina Neganova3Department of Physics and Mechanics & Mathematical Biology and Bioinformatics Laboratory, Peter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaLaboratory of Molecular Medicine, Institute of Cytology, 194064 Saint Petersburg, RussiaDepartment of Physics and Mechanics & Mathematical Biology and Bioinformatics Laboratory, Peter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaLaboratory of Molecular Medicine, Institute of Cytology, 194064 Saint Petersburg, RussiaHuman 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.https://www.mdpi.com/2227-9059/11/11/3005human pluripotent stem cellshuman embryonic stem cellsmachine learningbest clonemorphological phenotype |
spellingShingle | Ekaterina Vedeneeva Vitaly Gursky Maria Samsonova Irina Neganova Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods Biomedicines human pluripotent stem cells human embryonic stem cells machine learning best clone morphological phenotype |
title | Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods |
title_full | Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods |
title_fullStr | Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods |
title_full_unstemmed | Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods |
title_short | Morphological Signal Processing for Phenotype Recognition of Human Pluripotent Stem Cells Using Machine Learning Methods |
title_sort | morphological signal processing for phenotype recognition of human pluripotent stem cells using machine learning methods |
topic | human pluripotent stem cells human embryonic stem cells machine learning best clone morphological phenotype |
url | https://www.mdpi.com/2227-9059/11/11/3005 |
work_keys_str_mv | AT ekaterinavedeneeva morphologicalsignalprocessingforphenotyperecognitionofhumanpluripotentstemcellsusingmachinelearningmethods AT vitalygursky morphologicalsignalprocessingforphenotyperecognitionofhumanpluripotentstemcellsusingmachinelearningmethods AT mariasamsonova morphologicalsignalprocessingforphenotyperecognitionofhumanpluripotentstemcellsusingmachinelearningmethods AT irinaneganova morphologicalsignalprocessingforphenotyperecognitionofhumanpluripotentstemcellsusingmachinelearningmethods |