RESUMO
With the improvement of single-cell measurement techniques, there is a growing awareness that individual differences exist among cells, and protein expression distribution can vary across cells in the same tissue or cell line. Pinpointing the protein subcellular locations in single cells is crucial for mapping functional specificity of proteins and studying related diseases. Currently, research about single-cell protein location is still in its infancy, and most studies and databases do not annotate proteins at the cell level. For example, in the human protein atlas database, an immunofluorescence image stained for a particular protein shows multiple cells, but the subcellular location annotation is for the whole image, ignoring intercellular difference. In this study, we used large-scale immunofluorescence images and image-level subcellular locations to develop a deep-learning-based pipeline that could accurately recognize protein localizations in single cells. The pipeline consisted of two deep learning models, i.e. an image-based model and a cell-based model. The former used a multi-instance learning framework to comprehensively model protein distribution in multiple cells in each image, and could give both image-level and cell-level predictions. The latter firstly used clustering and heuristics algorithms to assign pseudo-labels of subcellular locations to the segmented cell images, and then used the pseudo-labels to train a classification model. Finally, the image-based model was fused with the cell-based model at the decision level to obtain the final ensemble model for single-cell prediction. Our experimental results showed that the ensemble model could achieve higher accuracy and robustness on independent test sets than state-of-the-art methods.
Assuntos
Aprendizado Profundo , Humanos , Proteínas/metabolismo , Algoritmos , Linhagem Celular , ImunofluorescênciaRESUMO
MOTIVATION: Knowledge of subcellular locations of proteins is of great significance for understanding their functions. The multi-label proteins that simultaneously reside in or move between more than one subcellular structure usually involve with complex cellular processes. Currently, the subcellular location annotations of proteins in most studies and databases are descriptive terms, which fail to capture the protein amount or fractions across different locations. This highly limits the understanding of complex spatial distribution and functional mechanism of multi-label proteins. Thus, quantitatively analyzing the multiplex location patterns of proteins is an urgent and challenging task. RESULTS: In this study, we developed a deep-learning-based pattern unmixing pipeline for protein subcellular localization (DULoc) to quantitatively estimate the fractions of proteins localizing in different subcellular compartments from immunofluorescence images. This model used a deep convolutional neural network to construct feature representations, and combined multiple nonlinear decomposing algorithms as the pattern unmixing method. Our experimental results showed that the DULoc can achieve over 0.93 correlation between estimated and true fractions on both real and synthetic datasets. In addition, we applied the DULoc method on the images in the human protein atlas database on a large scale, and showed that 70.52% of proteins can achieve consistent location orders with the database annotations. AVAILABILITY AND IMPLEMENTATION: The datasets and code are available at: https://github.com/PRBioimages/DULoc. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Assuntos
Aprendizado Profundo , Humanos , Algoritmos , Proteínas/química , Redes Neurais de Computação , ImunofluorescênciaRESUMO
Knowledge of protein expression in mammalian brains at regional and cellular levels can facilitate understanding of protein functions and associated diseases. As the mouse brain is a typical mammalian brain considering cell type and structure, several studies have been conducted to analyze protein expression in mouse brains. However, labeling protein expression using biotechnology is costly and time-consuming. Therefore, automated models that can accurately recognize protein expression are needed. Here, we constructed machine learning models to automatically annotate the protein expression intensity and cellular location in different mouse brain regions from immunofluorescence images. The brain regions and sub-regions were segmented through learning image features using an autoencoder and then performing K-means clustering and registration to align with the anatomical references. The protein expression intensities for those segmented structures were computed on the basis of the statistics of the image pixels, and patch-based weakly supervised methods and multi-instance learning were used to classify the cellular locations. Results demonstrated that the models achieved high accuracy in the expression intensity estimation, and the F1 score of the cellular location prediction was 74.5%. This work established an automated pipeline for analyzing mouse brain images and provided a foundation for further study of protein expression and functions.
Assuntos
Encéfalo , Aprendizado de Máquina , Animais , Camundongos , Imunofluorescência , Processamento de Imagem Assistida por Computador , MamíferosRESUMO
Machine learning has been employed in recognizing protein localization at the subcellular level, which highly facilitates the protein function studies, especially for those multi-label proteins that localize in more than one organelle. However, existing works mostly study the qualitative classification of protein subcellular locations, ignoring fraction of one multi-label protein in different locations. Actually, about 50 % proteins are multi-label proteins, and the ignorance of quantitative information highly restricts the understanding of their spatial distribution and functional mechanism. One reason of the lack of quantitative study is the insufficiency of quantitative annotations. To address the data shortage problem, here we proposed a generative model, PLocGAN, which could generate cell images with conditional quantitative annotation of the fluorescence distribution. The model was a conditional generative adversarial network, in which the condition learning utilized partial label learning to overcome the lack of training labels and allowed training with only qualitative labels. Meanwhile, it used contrastive learning to enhance diversity of the generated images. We assessed the PLocGAN on four pixel-fused synthetic datasets and one real dataset, and demonstrated that the model could generate images with good fidelity and diversity, outperforming existing state-of-the-art generative methods. To verify the utility of PLocGAN in the quantitative prediction of protein subcellular locations, we replaced the training images with generated quantitative images and built prediction models, and found that they had a boosting effect on the quantitative estimation. This work demonstrates the effectiveness of deep generative models in bioimage analysis, and provides a new solution for quantitative subcellular proteomics.
Assuntos
Aprendizado Profundo , Humanos , Proteínas/metabolismo , Proteínas/química , Proteínas/análise , Processamento de Imagem Assistida por Computador/métodos , Microscopia de Fluorescência/métodos , Aprendizado de MáquinaRESUMO
PURPOSE: Computed tomography (CT) images can display internal organs of patients and are particularly suitable for preoperative surgical diagnoses. The increasing demands for computer-aided systems in recent years have facilitated the development of many automated algorithms, especially deep convolutional neural networks, to segment organs and tumors or identify diseases from CT images. However, performances of some systems are highly affected by the amount of training data, while the sizes of medical image data sets, especially three-dimensional (3D) data sets, are usually small. This condition limits the application of deep learning. METHODS: In this study, given a practical clinical data set that has 3D CT images of 20 patients with renal carcinoma, we designed a pipeline employing transfer learning to alleviate the detrimental effect of the small sample size. A dual-channel fine segmentation network (FS-Net) was constructed to segment kidney and tumor regions, with 210 publicly available 3D images from a competition employed during the training phase. We also built discriminative classifiers to classify the benign and malignant tumors based on the segmented regions, where both handcrafted and deep features were tested. RESULTS: Our experimental results showed that the Dice values of segmented kidney and tumor regions were 0.9662 and 0.7685, respectively, which were better than those of state-of-the-art methods. The classification model using radiomics features can classify most of the tumors correctly. CONCLUSIONS: The designed FS-Net was demonstrated to be more effective than simply fine-tuning on the practical small size data set given that the model can borrow knowledge from large auxiliary data without diluting the signal in primary data. For the small data set, radiomics features outperformed deep features in the classification of benign and malignant tumors. This work highlights the importance of architecture design in transfer learning, and the proposed pipeline is anticipated to provide a reference and inspiration for small data analysis.
Assuntos
Neoplasias Renais , Redes Neurais de Computação , Humanos , Processamento de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Neoplasias Renais/diagnóstico por imagem , Aprendizado de Máquina , Tomografia Computadorizada por Raios X/métodosRESUMO
PURPOSE: Myocardial ischemia/reperfusion injury (IRI) induces cardiomyocytes death and leads to loss of cardiac function. Circular RNAs (circRNA) have gain increasing interests in modulating myocardial IRI. In this study, we aim to investigate the role and exact mechanism of circTLK1 in the pathogenesis of myocardial IRI. METHODS: Myocardial IRI was developed in mice with measuring hemodynamic parameters and the activity of serum myocardial enzymes to evaluate cardiac function. HE and TTC staining were performed to assess infarct area. Expression patterns of circTLK1 and miR-214 were investigated using qRT-PCR assay. Gene expression of circTLK1, miR-214 or RIPK was altered by transfecting with their overexpression or knockdown vectors. The apoptosis of cardimyocytes was assessed by TUNEL staining and Caspase-3 activity analysis. Apoptosis-related markers Bcl-2, Bax, and caspase3, as well as TNF-α signals were determined by western blotting. The interactions of circTLK1/miR-214 and miR-214/RIPK1 were verified using luciferase reporter assay. RNA immunoprecipitation (RIP) was subjected to further definite the direct binding of circTLK1/miR-214. The regulatory network of circTLK1/miR-214/RIPK1 was further validated in vivo. RESULTS: circTLK1 was an up-regulated circRNA found in a myocardial IRI mouse model. Mice with silencing circTLK1 significantly alleviated the impaired cardiac function indexes and decreased infarct area, thus attenuating the pathogenesis of myocardial IRI. Knockdown of circTLK1 dramatically decreased cardiomyocytes apoptosis, which was determined by apoptosis-related proteins. miR-214 was identified as a downstream effector to reverse circTLK1-mediated damage effects in myocardial IRI. miR-214 could directly target RIPK1 via binding to its' 3'-UTR. Overexpression of RIPK1 led to impaired cardiac function indexes, increased infarct area, and cell apoptosis, which abolished the protective effects of miR-214. The TNF signaling pathway was demonstrated to be involved in the circTLK1/miR-214/RIPK1 regulatory network in myocardial IRI. CONCLUSION: Taken together, our study revealed an up-regulated circRNA, circTLK1, could exacerbate myocardial IRI via targeting miR-214/RIPK1-mediated TNF signaling pathway, which may provide therapeutic targets for treatment.
Assuntos
MicroRNAs , Traumatismo por Reperfusão Miocárdica , Traumatismo por Reperfusão , Animais , Apoptose , Modelos Animais de Doenças , Camundongos , MicroRNAs/genética , Traumatismo por Reperfusão Miocárdica/genética , Miócitos Cardíacos , RNA Circular , Proteína Serina-Treonina Quinases de Interação com Receptores , Traumatismo por Reperfusão/genética , Transdução de SinaisRESUMO
BACKGROUND: Myocardial infarction (MI) is a common cardiovascular disease caused by myocardial ischemia. Also, microRNA (miRNA) participates in the pathophysiology of many cardiovascular diseases, which can affect stem cell transplantation in the treatment of MI. In this study, our aim is to explore effect of miR-26b on inflammatory response and myocardial remodeling through the MAPK pathway by targeting PTGS2 in mice with MI. METHODS: Microarray data analysis was conducted to screen MI-related differentially expressed gens (DEGs). Relationship between miR-26b and PTGS2 was testified. Cardiac function, inflammatory reaction, infarct size, and myocardial fibrosis were observed. The miR-26b expression and mRNA and protein levels of, PTGS2, ERK, JNK and p38 and Bcl-2/Bax were examined. The effect of miR-26b on cell apoptosis was also analyzed. RESULTS: MiR-26b was predicted to target PTGS2 further to mediate the MAPK pathway, thus affecting MI. MiR-26b negatively targeted PTGS2. MI mice showed decreased cardiac function, as well as increased inflammatory reaction, myocardial injury, area of fibrosis and myocardial cell apoptosis. After injection of miR-26b agomir or NS-398 (PTGS2 inhibitor), inflammatory response of MI mice was attenuated and myocardial remodeling induced by MI was alleviated. CONCLUSION: These findings indicate that miR-26b inhibits PTGS2 to activate the MAPK pathway, so as to reduce inflammatory response and improve myocardial remodeling in mice with MI.