Biology subjects

Yamada, T. G.

Publications and source records attributed to Yamada, T. G..

3 recordsLinked to original sources

bioRxiv2018

Predicting the future direction of cell movement with convolutional neural networks

Image-based deep learning systems, such as convolutional neural networks (CNNs), have recently been applied to cell classification, producing impressive results; however, application of CNNs has been confined to classification of the current cell state from the image. Here, we focused on cell movement where current and/or past cell shape can influence the future cell fate. We demonstrate that CNNs prospectively predicted the future direction of cell movement with high accuracy from a single image patch of a cell at a certain time. Furthermore, by visualizing the image features that were learned by the CNNs, we could identify morphological features, e.g., the protrusions and trailing edge that have been experimentally reported to determine the direction of cell movement. Our results indicate that CNNs have the potential to predict the future cell fate from current cell shape, and can be used to automatically identify those morphological features that influence future cell fate.

systems biology↗

bioRxiv2018

Transcriptome analysis of Pv11 cells infers the mechanism of desiccation tolerance and recovery

The larvae of the African midge, Polypedilum vanderplanki, can enter an ametabolic state called anhydrobiosis to conquer fatal desiccation stress. The Pv11 cell line, derived from embryos of the midge, shows desiccation tolerance by pretreatment with trehalose before desiccation; they can resume proliferation after rehydration. To address the underlying molecular mechanisms, we desiccated Pv11 cells after pretreatment with the medium containing trehalose and induced proliferation by rehydration. We collected the cells at each before and after desiccation and rehydration step and performed CAGE-seq of mRNA of those cells. By analysing differentially expressed genes (DEGs) among the results of CAGE-seq, we detected 384 DEGs after trehalose treatment and 14 DEGs after rehydration. Hierarchical clustering of the identified DEGs indicated that rehydration returns their expression pattern to that in the control culture state. DEGs involved in various stress responses, detoxification of harmful chemicals, and regulation of oxidoreduction were upregulated by trehalose treatment. DEGs for rehydration supported that DNA repair is one of the potential mechanisms involves recovery. This study provided initial insight into the molecular mechanisms underlying the extreme desiccation tolerance of Pv11 cells with a potential for proliferation following rehydration.

genomics↗

bioRxiv2018

Development of Convolutional Neural Network Based Instance Segmentation Algorithm to Acquire Quantitative Criteria of Mouse Development

In embryology, analytical approaches such as segmentation are applied to acquiring quantitative criteria from time-series three-dimensional microscopic images. When used to segment cells or intracellular organelles, several current machine learning techniques outperform traditional image processing algorithms. However segmentation algorithms still have unsolved problems, especially in bioimage processing. The most critical issue is that the existing algorithms can perform only semantic segmentation, which distin-guishes whether a pixel is within an object (for example, nucleus) or not. In this study, we implemented a novel segmentation algorithm, based on deep learning, which segments each nucleus and adds different labels to the detected objects. This segmentation algorithm is called instance segmentation. Our instance segmentation algorithm, implemented as a neural network, which we named QCA Net, substantially out-performed 3D U-Net, which is the best semantic segmentation algorithm that uses deep learning. Using QCA Net, we quantified the nuclear number, volume, surface area, and center of gravity coordinates during the development of mouse embryos. In particular, QCA Net distinguished nuclei of embryonic cells from those of polar bodies formed in meiosis. We consider that QCA Net can greatly contribute to bioimage segmentation in embryology by generating quantitative criteria from segmented images.

systems biology↗