Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks

doi:10.1186/s12859-021-04196-3

	Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks
	Zhang, Enze 3,4; Zhang, Boheng 2; Hu, Shaohan 1; Zhang, Fa 3,4; Liu, Zhiyong 3,4; Wan, Xiaohua 3,4
刊名	BMC BIOINFORMATICS
	2021-06-15
卷号	22 期号:SUPPL 3 页码:14
关键词	Protein pattern recognition DNNs Multi-class and multi-label Label imbalance High-throughput microscopy images
ISSN号	1471-2105
DOI	10.1186/s12859-021-04196-3
英文摘要	Background 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. Results In this paper, we first propose a novel customized architecture with adaptive concatenate pooling and "buffering" 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. Conclusion 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.
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences Grant[XDA19020400] ; National Key Research and Development Program of China[2017YFE0103900] ; National Key Research and Development Program of China[2017YFA0504702] ; National Key Research and Development Program of China[2017YFE0100500] ; Beijing Municipal Natural Science Foundation[L182053] ; NSFC[61672493] ; NSFC[61932018] ; NSFC[62072441] ; NSFC[U1611263] ; NSFC[U1611261]
WOS研究方向	Biochemistry & Molecular Biology ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology
语种	英语
出版者	BMC
WOS记录号	WOS:000661894600001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17673]
专题	中国科学院计算技术研究所
通讯作者	Wan, Xiaohua
作者单位	1.Tsinghua Univ, Sch Software, Beijing, Peoples R China 2.Tsinghua Univ, Dept Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Chinese Acad Sci, High Performance Comp Res Ctr, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Enze,Zhang, Boheng,Hu, Shaohan,et al. Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks[J]. BMC BIOINFORMATICS,2021,22(SUPPL 3):14.
APA	Zhang, Enze,Zhang, Boheng,Hu, Shaohan,Zhang, Fa,Liu, Zhiyong,&Wan, Xiaohua.(2021).Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks.BMC BIOINFORMATICS,22(SUPPL 3),14.
MLA	Zhang, Enze,et al."Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks".BMC BIOINFORMATICS 22.SUPPL 3(2021):14.