2022
DOI: 10.3390/ph15050562
|View full text |Cite
|
Sign up to set email alerts
|

Induced Pluripotent Stem Cell-Based Drug Screening by Use of Artificial Intelligence

Abstract: Induced pluripotent stem cells (iPSCs) are terminally differentiated somatic cells that differentiate into various cell types. iPSCs are expected to be used for disease modeling and for developing novel treatments because differentiated cells from iPSCs can recapitulate the cellular pathology of patients with genetic mutations. However, a barrier to using iPSCs for comprehensive drug screening is the difficulty of evaluating their pathophysiology. Recently, the accuracy of image analysis has dramatically impro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
12
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(12 citation statements)
references
References 109 publications
0
12
0
Order By: Relevance
“…For instance, DL was utilized to directly analyze the 3D image stacks of hiPSC‐derived mammary gland organoids without converting them into 2D projections or specifying individual cell types 112 . DL‐Based Senescence Scoring by Morphology (Deep‐SeSMo) is a CNN‐based model that uses phase‐contrast microscopy images without molecular labels to generate senescence probability on iPSCs in large numbers 113,114 …”
Section: Ai‐enabled Analysis For Hpsc‐derived Organoidsmentioning
confidence: 99%
See 1 more Smart Citation
“…For instance, DL was utilized to directly analyze the 3D image stacks of hiPSC‐derived mammary gland organoids without converting them into 2D projections or specifying individual cell types 112 . DL‐Based Senescence Scoring by Morphology (Deep‐SeSMo) is a CNN‐based model that uses phase‐contrast microscopy images without molecular labels to generate senescence probability on iPSCs in large numbers 113,114 …”
Section: Ai‐enabled Analysis For Hpsc‐derived Organoidsmentioning
confidence: 99%
“…112 DL-Based Senescence Scoring by Morphology (Deep-SeSMo) is a CNN-based model that uses phase-contrast microscopy images without molecular labels to generate senescence probability on iPSCs in large numbers. 113,114 DL methods have been utilized in studies focused on cardiotoxicity to quantify drug-induced structural changes in hiPSC-CMs. DL models trained with both brightfield and fluorescent images of hiPSC-CMs have demonstrated their ability to detect cellular changes resulting in the loss of cardiac function.…”
Section: Image Analysis Using Deep Learning Techniquesmentioning
confidence: 99%
“…Moreover, protocols must be developed to reliably evaluate the effect of test compounds on hiPSC-based drug-screening platforms. Important advancements are being reported in cell culture processes that are based on the use of robotics to achieve an automated reprogramming, maintenance and differentiation of hiPSCs, and that are contributing to the creation of large and reliable repositories of hiPSC lines [ 139 , 140 ]; equally important are the improvements in image analysis techniques and artificial intelligence technologies that enable the processing of large amounts of datasets, cell identification and the elucidation of a cell’s pathological state based on its morphology [ 141 , 142 , 143 , 144 ]. New computational prediction models are being generated, such as those described by Zhang et al (2020) [ 145 ] and Huang et al (2021) [ 146 ] to predict drug-induced ototoxicity, thus contributing to drug design optimization.…”
Section: Hipsc-based Drug Screening Systemsmentioning
confidence: 99%
“…Somatic cells, a favorable alternative for research, reprogrammed into induced pluripotent stem cells (iPSCs) by transfecting four transcription factors (Sox2, Oct3/4, Klf4, and c-Myc), have the ability to differentiate into three germ layers with each type of organ tissue [ 5 ]. Recently, iPSCs have been applied in various medication study fields, including tissue engineering of cell regeneration [ 6 , 7 ], disease models [ 8 , 9 , 10 ], and drug screening [ 11 , 12 , 13 , 14 , 15 ]. However, drug screening studies have focused on toxicity or clinical side effects, not on the pharmacological mechanism [ 16 , 17 , 18 , 19 ].…”
Section: Introductionmentioning
confidence: 99%