相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Biology
Zilong Hou et al.
Summary: Protein-protein interactions (PPIs) play a crucial role in cellular pathways and processes, but accurate identification of PPI binding sites is challenging. The proposed EDLM-based method, EDLMPPI, addresses these challenges by utilizing an ensemble deep learning model. Evaluation results demonstrate that EDLMPPI outperforms state-of-the-art techniques in terms of average precision on widely-used benchmark datasets. Additionally, the method provides new insights into protein binding site identification and characterization mechanisms.
COMMUNICATIONS BIOLOGY
(2023)
Article
Biophysics
Kurtis D. Ottman et al.
BIOPHYSICAL JOURNAL
(2023)
Article
Biochemical Research Methods
Xi-Liang Zhu et al.
Summary: With the advancement of single-cell measurement techniques, it is becoming increasingly evident that cells exhibit individual differences, and the distribution of protein expression can vary across cells. Determining the subcellular locations of proteins in single cells is crucial for understanding protein function and related diseases. Currently, research on single-cell protein location is in its early stages, and most studies and databases do not provide annotations at the cell level. In this study, a deep-learning-based pipeline was developed using large-scale immunofluorescence images and image-level subcellular locations to accurately recognize protein localizations in single cells.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Shaozhuang Ye et al.
Summary: Multimodal medical image fusion is highly significant in disease diagnosis and treatment. Traditional methods and deep learning methods have limitations. To address these issues, we propose an unsupervised multimodal medical image fusion method based on foveated differentiable architecture search (F-DARTS). The method introduces the foveation operator and a distinctive unsupervised loss function. Experimental results demonstrate that the proposed method outperforms traditional methods and deep learning methods in visual effect and objective evaluation.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Biophysics
Xiaocen Duan et al.
Summary: This study presents a data-driven 3D cellular force microscopy (CFM) approach using deep neural networks to reconstruct the force fields of individual cells directly from volumetric images. The method improves computational efficiency and exhibits good generalization ability and robustness. The ability to quantitatively characterize mechanical interactions between cells and extracellular matrices is of great importance in biomechanics and mechanobiology research.
BIOPHYSICAL JOURNAL
(2022)
Article
Biochemical Research Methods
Huangqingbo Sun et al.
Summary: This study introduces improved approaches for learning cell organelle models using Generative Adversarial Networks. Novel criteria are also developed to evaluate the similarity between synthetic and real cell images. These methods allow the inference of relationships between different organelles and capture object-level properties of cell images.
Article
Cell Biology
Xiao Fu et al.
EXPERIMENTAL CELL RESEARCH
(2022)
Review
Oncology
Amelie Echle et al.
Summary: Clinical workflows in oncology rely on molecular biomarkers for prediction and prognosis. Deep learning technology can extract biomarkers directly from routine histology images, potentially enhancing clinical decision-making, but require rigorous external validation in clinical settings.
BRITISH JOURNAL OF CANCER
(2021)
Article
Cell Biology
Adam R. Fenton et al.
Summary: Mitochondria form networks that are continually remodeled and adapted to carry out their cellular function. This remodeling is achieved through changes in morphology, number, and distribution, which are dependent on fission, fusion, shape transition, and transport/tethering along the cytoskeleton. Over the past few years, many mechanisms regulating these processes have been uncovered, showing precise and context-dependent regulation within the cell.
CURRENT OPINION IN CELL BIOLOGY
(2021)
Article
Multidisciplinary Sciences
Larissa Heinrich et al.
Summary: FIB-SEM combined with deep-learning-based segmentation is used to produce 3D reconstructions of cells with annotated organelle classes. The automatic reconstruction method enables detailed understanding of cellular organization and spatial interactions, with potential applications in correlative studies. An open data repository, 'OpenOrganelle', has been created to share data and models for further scientific exploration.
Article
Cell Biology
YoungJu Jo et al.
Summary: Jo et al. develop a broadly applicable deep-learning approach to predict fluorescence (FL) based on label-free refractive index (RI) measurements, 'RI2FL' (RI to FL). The trained model can be used across cell types without retraining.
NATURE CELL BIOLOGY
(2021)
Article
Biochemical Research Methods
Yanming Zhu et al.
Summary: This study proposed a novel NAS-based solution for deep learning-based live cell segmentation in time-lapse microscopy images. By jointly searching non-repeatable micro architectures to construct the macro network and defining a specific search space suitable for the task, as well as exploring temporal information in cell sequences, the method demonstrated more competitive performance, showing more consistent top performance across all datasets in the experiments.
Review
Cell Biology
Gautam Dey et al.
Summary: The defining feature of eukaryotic cells, the nucleus, is bounded by a double envelope with nuclear pores critical for separating the genome from the cytoplasm. Eukaryotes have evolved various strategies to remodel the nuclear compartment boundary during mitosis, from disassembling and reassembling the nucleus in daughter cells to maintaining an intact boundary throughout division. This review discusses common features of the division process, topological challenges, and the selective pressures that may drive the evolution of distinct modes of division.
CURRENT OPINION IN CELL BIOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Arif Ahmed Sekh et al.
Summary: To solve the problem of segmenting very small subcellular structures, the study uses a physics-based simulation approach to train neural networks and introduces a simulation-supervision method supported by physics-based GT. This approach addresses the issue of lacking ground truth data and improves the accuracy and speed of subcellular segmentation.
NATURE MACHINE INTELLIGENCE
(2021)
Article
Plant Sciences
Jiying Li et al.
Summary: The study introduces a deep-learning framework, DeepLearnMOR, which can classify and identify abnormalities in organelle morphology with over 97% accuracy using transfer learning and a convolutional neural network on a large dataset of confocal microscopy images from Arabidopsis plants with abnormal energy organelle division.
Review
Biochemical Research Methods
Yinan Shen et al.
BRIEFINGS IN BIOINFORMATICS
(2020)
Review
Cell & Tissue Engineering
Markus Grosch et al.
Article
Engineering, Biomedical
Flavio H. D. Araujo et al.
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
(2019)
Review
Pathology
Shidan Wang et al.
AMERICAN JOURNAL OF PATHOLOGY
(2019)
Review
Computer Science, Artificial Intelligence
Yesmina Jaafra et al.
IMAGE AND VISION COMPUTING
(2019)
Article
Biochemical Research Methods
Thorsten Falk et al.
Review
Biochemistry & Molecular Biology
Lorena Nunez Villacis et al.
Article
Biochemistry & Molecular Biology
Eric M. Christiansen et al.
Article
Biochemical Research Methods
Chawin Ounkomol et al.
Article
Biochemical Research Methods
Yousef Al-Kofahi et al.
BMC BIOINFORMATICS
(2018)
Review
Cell Biology
Marlieke L. M. Jongsma et al.
TRENDS IN CELL BIOLOGY
(2015)
Review
Biochemistry & Molecular Biology
Tara Teslaa et al.
Article
Biochemical Research Methods
Fernando Amat et al.
Article
Multidisciplinary Sciences
Jyrki Selinummi et al.
Review
Multidisciplinary Sciences
DJ Stephens et al.
