Award type：Award from Japanese society, conference, symposium, etc. 

Award type：Award from Japanese society, conference, symposium, etc. 

Language：English   Publisher：Dmm Disease Models and Mechanisms  

Spinal and bulbar muscular atrophy (SBMA) is a neuromuscular disorder caused by CAG trinucleotide expansion in the androgen receptor (AR) gene. To improve the quality of in vitro cell-based assays for the evaluation of potential drug candidates for SBMA, we developed a morphology-based phenotypic analysis for a muscle cell model of SBMA that involves multiparametric morphological profiling to quantitatively assess the therapeutic effects of drugs on muscle cell phenotype. The analysis was validated using dihydrotestosterone and pioglitazone, which have been shown to exacerbate and ameliorate the pathophysiology of SBMA, respectively. Gene expression analysis revealed activation of the JNK pathway in the SBMA cells compared to the control cells. Phenotypic analysis revealed the effect of naratriptan, a JNK inhibitor, on the phenotypic changes of SBMA cells, and the results were confirmed by LDH assays. We then trained a predictive machine learning model to classify the drug responses, and it successfully discriminated between pioglitazone-type and naratriptan-type morphological profiles based on their morphological characteristics. Our morphology-based phenotypic analysis provides a noninvasive and efficient screening method to accelerate the development of therapeutics for SBMA.

DOI： 10.1242/dmm.052220

Open Access

Web of Science

Scopus

PubMed

Language：English   Publisher：Communications Biology  

In regenerative medicine, mesenchymal stem cells (MSCs) constitute a promising therapeutic route for many diseases. The current quality-by-design guidelines do not clearly define a framework for MSC production. Here, we suggest and experimentally validate a model-based method to determine design spaces (DSs) for MSC cultivation. A kinetic model used in previous work was employed; part of the experimental data was used to re-estimate the maximum specific growth rate in the kinetic model and then calculate the prediction intervals of this parameter. Subsequently, regions of seeding density and harvesting time where both the upper and lower limits of growth predictions met the acceptable number of cells and confluency with given risk levels were defined as DSs. Finally, the established DS was validated with the remaining data; it allowed better predictions of the cell numbers and confluency under specific cultivation conditions and improved the overall robustness of MSC cultivation processes. (Figure presented.)

DOI： 10.1038/s42003-025-08063-2

Open Access

Web of Science

Scopus

PubMed

Language：English   Publisher：Journal of Bioscience and Bioengineering  

Advances in regenerative medicine highlighted the need for label-free cell image analysis to replace conventional microscopic observation for non-invasive cell quality evaluation. Image-based evaluation provides an efficient, quantitative, and automated approach to cell analysis, but segmentation remains a critical and challenging step. In this study, we investigated how training dataset design influenced the robustness of U-Net models for cell segmentation, focusing on challenges posed by limited data availability in cell culture. Using 2592 image pairs from four cell types representing key morphological categories, we constructed 42 investigation patterns to evaluate the effects of dataset size, dataset content, and morphological diversity on model performance. Our results showed that robust segmentation models could be developed with approximately 10 raw images captured using a 4× objective lens, a much smaller dataset than typically assumed. The dataset content was found to be crucial: training dataset images that captured commonly observed cell patterns yielded more robust models compared to those capturing rare or irregular cell patterns, which often impaired model performance with large deviations. Additionally, including both spindle and round cell morphologies in the training datasets improved model robustness when tested across all four cell types, while datasets restricted to a single morphology type could not achieve robust models. These findings highlight the importance of curating datasets that capture representative yet diverse cell morphologies. By addressing critical questions about dataset design, this study provides actionable guidance for the effective use of deep learning-based cell segmentation models in manufacturing and research applications.

DOI： 10.1016/j.jbiosc.2025.01.004

Web of Science

Scopus

PubMed

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： https://doi.org/10.3390/app12031622

Open Access

Language：Japanese   Publisher：公益社団法人 日本生物工学会  

DOI： 10.34565/seibutsukogaku.103.3_125

CiNii Research

Language：Japanese   Publisher：一般社団法人 人工知能学会  

DOI： 10.11517/jjsai.40.2_141

CiNii Research

Event date： 2024.3

Presentation type：Poster presentation  

Event date： 2024.3

Presentation type：Poster presentation  

Event date： 2023.10

Presentation type：Oral presentation (general)  

Event date： 2023.9

Presentation type：Oral presentation (general)  

Event date： 2023.6

Language：Japanese   Presentation type：Poster presentation