{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:52:55Z","timestamp":1740135175725,"version":"3.37.3"},"reference-count":12,"publisher":"Springer Science and Business Media LLC","issue":"S3","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"vor","delay-in-days":45,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["No. 2017YFE0103900 and 2017YFA0504702, 2017YFE0100500"],"award-info":[{"award-number":["No. 2017YFE0103900 and 2017YFA0504702, 2017YFE0100500"]}]},{"name":"the Strategic Priority Research Program of the Chinese Academy of Sciences Grant","award":["No. XDA19020400"],"award-info":[{"award-number":["No. XDA19020400"]}]},{"name":"the NSFC projects Grant","award":["61672493 and 62072441","U1611261","U1611263 and 61932018"],"award-info":[{"award-number":["61672493 and 62072441","U1611261","U1611263 and 61932018"]}]},{"name":"Natural Science Foundation of Beijing Municipality","award":["No. L182053"],"award-info":[{"award-number":["No. L182053"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,5]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Proteins are of extremely vital importance in the human body, and no movement or activity can be performed without proteins. Currently, microscopy imaging technologies developed rapidly are employed to observe proteins in various cells and tissues. In addition, due to the complex and crowded cellular environments as well as various types and sizes of proteins, a considerable number of protein images are generated every day and cannot be classified manually. Therefore, an automatic and accurate method should be designed to properly solve and analyse protein images with mixed patterns.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In this paper, we first propose a novel customized architecture with adaptive concatenate pooling and \u201cbuffering\u201d layers in the classifier part, which could make the networks more adaptive to training and testing datasets, and develop a novel hard sampler at the end of our network to effectively mine the samples from small classes. Furthermore, a new loss is presented to handle the label imbalance based on the effectiveness of samples. In addition, in our method, several novel and effective optimization strategies are adopted to solve the difficult training-time optimization problem and further increase the accuracy by post-processing.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our methods outperformed the SOTA method of multi-labelled protein classification on the HPA dataset, GapNet-PL, by above 2% in the F1 score. Therefore, experimental results based on the test set split from the Human Protein Atlas dataset show that our methods have good performance in automatically classifying multi-class and multi-labelled high-throughput microscopy protein images.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12859-021-04196-3","type":"journal-article","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T14:03:08Z","timestamp":1623765788000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks"],"prefix":"10.1186","volume":"22","author":[{"given":"Enze","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Boheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Shaohan","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Fa","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9340-878X","authenticated-orcid":false,"given":"Xiaohua","family":"Wan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,15]]},"reference":[{"unstructured":"The human protein atlas homepage. http:\/\/www.proteinatlas.org\/.","key":"4196_CR1"},{"doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V. Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Proceedings of the thirty-first AAAI conference on artificial intelligence (AAAI), p. 4278\u20134284; 2017.","key":"4196_CR2","DOI":"10.1609\/aaai.v31i1.11231"},{"doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), p. 770\u2013778; 2016.","key":"4196_CR3","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR), p. 2261\u20132269; 2017.","key":"4196_CR4","DOI":"10.1109\/CVPR.2017.243"},{"issue":"9","key":"4196_CR5","doi-asserted-by":"publisher","first-page":"998","DOI":"10.1177\/1087057116631284","volume":"21","author":"O D\u00fcrr","year":"2016","unstructured":"D\u00fcrr O, Sick B. Single-cell phenotype classification using deep convolutional neural networks. J Biomol Screen. 2016;21(9):998\u20131003.","journal-title":"J Biomol Screen"},{"issue":"12","key":"4196_CR6","doi-asserted-by":"publisher","first-page":"i52","DOI":"10.1093\/bioinformatics\/btw252","volume":"32","author":"OZ Kraus","year":"2016","unstructured":"Kraus OZ, Ba JL, Frey BJ. Classifying and segmenting microscopy images with deep multiple instance learning. Bioinformatics. 2016;32(12):i52\u20139.","journal-title":"Bioinformatics"},{"issue":"13","key":"4196_CR7","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1093\/bioinformatics\/btx069","volume":"33","author":"WJ Godinez","year":"2017","unstructured":"Godinez WJ, Hossain I, Lazic SE, Davies JW, Zhang X. A multi-scale convolutional neural network for phenotyping high-content cellular images. Bioinformatics. 2017;33(13):2010\u20139.","journal-title":"Bioinformatics"},{"unstructured":"Rumetshofer E, Hofmarcher M, R\u00f6hrl C, Hochreiter S, Klambauer G (2019) Human-level protein localization with convolutional neural networks. In: International conference on learning representations (ICLR); 2019.","key":"4196_CR8"},{"unstructured":"Human protein atlas image classification challenge homepage; 2018. https:\/\/www.kaggle.com\/c\/human-protein-atlas-image-classification.","key":"4196_CR9"},{"unstructured":"PyTorch 1.0 library HomePage. https:\/\/pytorch.org\/. 23 Feb 2019.","key":"4196_CR10"},{"doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. arXiv preprint; 2017.","key":"4196_CR11","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"crossref","unstructured":"Smith LN. Cyclical learning rates for training neural networks. In: 2017 IEEE winter conference on applications of computer vision (WACV), p. 464\u2013472; 2017.","key":"4196_CR12","DOI":"10.1109\/WACV.2017.58"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04196-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04196-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04196-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T05:49:35Z","timestamp":1672465775000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04196-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":12,"journal-issue":{"issue":"S3","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["4196"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04196-3","relation":{},"ISSN":["1471-2105"],"issn-type":[{"type":"electronic","value":"1471-2105"}],"subject":[],"published":{"date-parts":[[2021,5]]},"assertion":[{"value":"26 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"327"}}