Biology subjects

Morikura, T.

Publications and source records attributed to Morikura, T..

5 recordsLinked to original sources

bioRxiv2025

Autofluorescence-based Label-free Cell Counting Method in Suspension Culture with Microcarriers

To advance the industrialization of cultured meat and regenerative medicine, scalable and efficient cell culture techniques are essential. Among these, the suspension culture method using microcarriers has emerged as a promising approach for the large-scale cell culture technique. However, monitoring cell growth on the microcarriers remains challenging, particularly in developing cell counting techniques that can be seamlessly integrated into bioprocess workflows without cell detachment, fluorescence labeling and any parameter tuning in the analysis algorithm. In this study, we proposed a versatile image analysis-based cell counting method by using cellular autofluorescence without any parameter tuning. The proposed method estimates the number of cells by applying spatiotemporal averaging to the autofluorescence signals in the microscopic images. Using numerical and cell culture experiments, we demonstrated that the proposed method can estimates the number of cells accurately. This technique, which harnesses the ubiquitous autofluorescence inherent in living cells, offers a cost-effective and practical solution applicable to a broad range of fields requiring high-throughput cell quantification.

systems biology↗

bioRxiv2025

Mixing features of transcription factors and genes enables accurate prediction of gene regulation relationships for unknown transcription factors

Identifying regulatory relationships between transcription factors (TFs) and genes is essential to understand diverse biological phenomena related to gene expression. Recently, deep learning-based models to predict TFs that bind to genes from nucleotide sequences of the target genes have been developed, yet these models are trained to predict known TFs only. In this study we developed a deep learning model, GReNIMJA (Gene Regulatory Network Inference by Mixing and Jointing features of Amino acid and nucleotide sequences), to predict gene regulation even by unknown TFs. Our model is designed to mix the features of the TF amino acid sequences and nucleotide sequences of the target genes using a 2D LSTM architecture and to perform binary classification with the aim of determining the presence or absence of a regulatory relationship. The accuracy of our model in predicting regulatory relationships was 84.4% for known TFs (higher than those of conventional models) and 68.5% for unknown TFs; the latter is an unsolved task for conventional deep learning-based models. We expect our model to advance identification of unknown gene regulatory networks and contribute to the understanding of diverse biological phenomena.

systems biology↗

bioRxiv2024

Label-free multiplex microscopic imaging by image-to-image translation overcoming the trade-off between pixel- and image-level similarity

Establishment of multiplex microscopic imaging without labeling is indispensable for understanding complex interactions of subcellular components. Toward the establishment of label-free multiplex microscopic imaging, image-to-image translation models that extract images of multiple subcellular components from bright-field images via nonlinear processing have attracted attention. However, the performance of conventional models is limited by a trade-off relationship between pixel- and image-level similarity, which degrades imaging performance. Here, we developed an image-to-image Wasserstein Schrodinger Bridge model to achieve high-performance image-to-image translation at the pixel level using Schrodinger Bridge while minimizing Wasserstein distance at the image level. Our model dramatically outperformed the conventional models at both levels simultaneously, reducing the mean squared error by 410-fold and improving the structural similarity index measure by 17.1-fold. Label-free multiplex microscopic imaging based on our model paves a way for the analysis of the interactions of subcellular components.

systems biology↗

bioRxiv2024

Deep learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy

Infertility is a global issue, with approximately 50% of cases attributed to defective spermatogenesis. For studies into spermatogenesis and spermatogenic dysfunction, evaluating the seminiferous tubule stage is essential. However, the current method of evaluation involves labor-intensive and time-consuming manual tasks such as staining, observation, and image analysis. Lack of reproducibility is also a problem owing to the subjective nature of visual evaluation by experts. In this study, we propose a deep learning-based method for automatically and objectively evaluating the seminiferous tubule stage. Our approach automatically predicts which of 12 seminiferous tubule stages is represented in bright-field microscopic images of mouse seminiferous tubules stained by hematoxylin-PAS. For training and validation of our model, we created a dataset of 1229 tissue images, each labeled with one of 12 distinct seminiferous tubule stages. The maximum prediction accuracy was 79.58% which rose to 98.33% with allowance for a prediction error of {+/-}1 stage. Remarkably, although the model was not explicitly trained on the patterns of transition between stages, it inferred characteristic structural patterns involved in the process of spermatogenesis. This method not only advances our understanding of spermatogenesis but also holds promise for improving the automated diagnosis of infertility.

systems biology↗

bioRxiv2024

Cell segmentation without annotation by unsupervised domain adaptation based on cooperative self-learning

Semantic cell segmentation from microscopic images is essential for the quantitative evaluation of cell morphology. Although supervised deep-learning-based models offer accurate segmentation, their performance degrades for unknown cell types. To address this problem, unsupervised domain adaptation methods based on adversarial training, self-training, or a combination of these approaches have been developed in recent years. These methods train the model using inference labels from the unknown domain as pseudo labels with reliability to resolve the discrepancy between the features of the unknown and known domains. However, conventional methods require a predefined threshold to calculate pseudo-labels reliability, leading to costly hyperparameter tuning. Here, we developed an unsupervised domain adaptation for semantic cell segmentation with cooperative self-learning (CULPICO: Cooperative Unsupervised Learning for PIxel-wise COloring) that does not require predefined threshold of the pseudo-labels reliability. The proposed method consists of two independent segmentation models and a mutual exchange mechanism of inference data. The models infer a label probability at each pixel and generate a pseudo-label as unsupervised learning. The pseudo-labels created by each model are mutually used as ground truth in the other model. Loss function is corrected by considering pixel-level discrepancies between the label probabilities inferred by the two models. The proposed method, despite being an unsupervised learning method, can segment efficiently the unknown cell types without labels with an accuracy comparable to supervised learning models. Our method, which could solve the performance degradation problem without constructing new datasets, is expected to accelerate life science by reducing the cost of extracting quantitative biological knowledge.

systems biology↗