ABSTRACT
Single-cell RNA sequencing (scRNA-seq) data provide new opportunities for many research directions in the field of biology, one of which is the identification of cell types. However, traditional cell identification methods are time-consuming, uneconomical, complex, and difficult to be applied to large data sets. Here, we propose a graph neural network with multiple auxiliary tasks (MATGNN) for cell classification. First, we construct the adjacency matrix between cells based on their gene expression data, which represents the interactions between cells. Next, a complete undirected graph between cells is obtained and it is fed into the graph neural network model, which is employed to aggregate the information of node's neighborhood. Then, we improve the robustness of the proposed model through three different auxiliary tasks. Specifically, the first auxiliary task balances the information in the adjacency matrix between cells. The second one captures inherent information about the interactions between cells of same type and the third one is responsible for mining the structural information from the undirected graph between cells. Those three auxiliary tasks enable the model to deeply dig into the structural information and link information of the cell graph. Finally, we conduct extensive experiments on the gold datasets and the results indicate that our models outperform the state-of-the-art methods for single cell classification. Compared with other state-of-the-art methods, our method achieves the highest accuracy on most datasets. In particular, our method improves the classification accuracy of datasets BaronMouse, Segerstolpe and BaronHuman by 0.5%, 1.2%$ and 0.7%, respectively. We prove the effectiveness of establishing adjacency matrix between cells in cell classification. Three auxiliary tasks show that we can mine more cellular properties from existing datasets.
- Elham Azizi, Ambrose J Carr, George Plitas, Andrew E Cornish, Catherine Konopacki, Sandhya Prabhakaran, Juozas Nainys, Kenmin Wu, Vaidotas Kiseliovas, Manu Setty, Kristy Choi, Rachel M Fromme, Phuong Dao, Peter T McKenney, Ruby C Wasti, Krishna Kadaveru, Linas Mazutis , Alexander Y Rudensky, and Dana Pe'er. 2018. Single-cell map of diverse immune phenotypes in the breast tumor microenvironment. Cell, 174(5):1293-1308. https://doi.org/10.1016/j.cell.2018.05.060Google ScholarCross Ref
- Darren A Cusanovich, Andrew J Hill, Delasa Aghamirzaie, Riza M Daza, Hannah A Pliner, Joel B Berletch, Galina N Filippova, Xingfan Huang, Lena Christiansen, William S DeWitt, Choli Lee, Samuel G Regalado, David F Read, Frank J Steemers, Christine M Disteche, Cole Trapnell, and Jay Shendure . 2018. A single-cell atlas of in vivo mammalian chromatin accessibility. Cell, 174(5):1309-1324. https://doi.org/10.1016/j.cell.2018.06.052Google ScholarCross Ref
- Mauro J Muraro , Gitanjali Dharmadhikari , Dominic Grün , Nathalie Groen , Tim Dielen , Erik Jansen , Leon van Gurp , Marten A Engelse , Francoise Carlotti , Eelco J P de Koning , and Alexander van Oudenaarden. Bolles. 2016. A single-cell transcriptome atlas of the human pancreas. Cell Syst, 3(4):385-394.e3. https://doi.org/10.1016/j.cels.2016.09.002Google ScholarCross Ref
- Tabula Muris Consortium. 2018. Single-cell transcriptomics of 20 mouse organs creates a Tabula Muris. Nature, 562(7727):367-372. https://doi.org/10.1038/s41586-018-0590-4Google ScholarCross Ref
- Jason D Buenrostro , M Ryan Corces , Caleb A Lareau , Beijing Wu , Alicia N Schep , Martin J Aryee , Ravindra Majeti , Howard Y Chang , and William J Greenleaf. 2018. Integrated single-cell analysis maps the continuous regulatory landscape of human hematopoietic differentiation. Cell, 173(6):1535-1548.e16. https://doi.org/10.1016/j.cell.2018.03.074Google ScholarCross Ref
- Alexandra-Chloé Villani, Rahul Satija, Gary Reynolds, Siranush Sarkizova, Karthik Shekhar, James Fletcher, Morgane Griesbeck , Andrew Butler , Shiwei Zheng , Suzan Lazo, Laura Jardine, David Dixon, Emily Stephenson, Emil Nilsson, Ida Grundberg, David McDonald, Andrew Filby, Weibo Li, Philip L De Jager, Orit Rozenblatt-Rosen, Andrew A Lane, Muzlifah Haniffa , Aviv Regev, and Nir Hacohen. 2017. Single-cell RNA-seq reveals new types of human blood dendritic cells, monocytes, and progenitors. Science, 356(6335):eaah4573. https://doi.org/10.1126/science.aah4573Google ScholarCross Ref
- Dominic Grün, Anna Lyubimova, Lennart Kester, Kay Wiebrands, Onur Basak, Nobuo Sasaki, Hans Clevers, and Alexander van Oudenaarden. 2015. Single-cell messenger RNA sequencing reveals rare intestinal cell types. Nature, 525(7568):251-5. https://doi.org/10.1038/nature14966Google ScholarCross Ref
- Åsa Segerstolpe, Athanasia Palasantza, Pernilla Eliasson, Eva-Marie Andersson, Anne-Christine Andréasson, Xiaoyan Sun, Simone Picelli, Alan Sabirsh, Maryam Clausen, Magnus K Bjursell, David M Smith, Maria Kasper, Carina Ämmälä, and Rickard Sandberg. 2016. Single-cell transcriptome profling of human pancreatic islets in health and type 2 diabetes, Cell Metab, 24(4):593-607. https://doi.org/10.1016/j.cmet.2016.08.020Google ScholarCross Ref
- George Adam, Ladislav Rampášek, Zhaleh Safikhani, Petr Smirnov, Benjamin Haibe-Kains, and Anna Goldenberg. 2020. Machine learning approaches to drug response prediction: Challenges and recent progress. npj Precision Oncologyl, 4:19. https://doi.org/10.1038/s41698-020-0122-1Google ScholarCross Ref
- Britt Adamson, Thomas M Norman, Marco Jost, Min Y Cho, James K Nuñez, Yuwen Chen, Jacqueline E Villalta, Luke A Gilbert, Max A Horlbeck, Marco Y Hein, Ryan A Pak, Andrew N Gray, Carol A Gross, Atray Dixit , Oren Parnas, Aviv Regev, and Jonathan S Weissman. 2016. A multiplexed single-cell CRISPR screening platform enables systematic dissection of the unfolded protein response. Cell, 167(7):1867-1882.e21. https://doi.org/10.1016/j.cell.2016.11.048Google ScholarCross Ref
- Christopher T Fincher, Omri Wurtzel, Thom de Hoog, Kellie M Kravarik, and Peter W Reddien. 2018. Cell type transcriptome atlas for the planarian Schmid tea mediterranea. Science, 360(6391):eaaq1736. https://doi.org/10.1126/science.aaq1736Google ScholarCross Ref
- Mireya Plass, Jordi Solana, F Alexander Wolf, Salah Ayoub, Aristotelis Misios, Petar Glažar, Benedikt Obermayer, Fabian J Theis, Christine Kocks, and Nikolaus Rajewsky. 2018. Cell type atlas and lineage tree of a whole complex animal by single-cell transcriptomics. Science, 360(6391):eaaq1723. https://doi.org/10.1126/science.aaq1723Google ScholarCross Ref
- Jose Alquicira-Hernandez, Anuja Sathe, Hanlee P Ji, Quan Nguyen, and Joseph E Powell. 2019. scPred: accurate supervised method for cell-type classifcation from single-cell RNA-seq data. Science, 20(1):264. https://doi.org/10.1186/s13059-019-1862-5Google ScholarCross Ref
- Katerina Boufea, Sohan Seth, and Nizar N Batada. 2020. scID Uses Discriminant Analysis to Identify Transcriptionally Equivalent Cell Types across Single-Cell RNA-Seq Data with Batch Effect. iScience, 23(3):100914. https://doi.org/10.1016/j.isci.2020.100914Google ScholarCross Ref
- Yuval Lieberman, Lior Rokach, and Tal Shay. 2018. CaSTLe – Classifcation of single cells by transfer learning: harnessing the power of publicly available single cell RNA sequencing experiments to annotate new experiments. PLoS One, 13(10):e0205499. https://doi.org/10.1371/journal.pone.0205499Google ScholarCross Ref
- Dvir Aran, Agnieszka P Looney, Leqian Liu, Esther Wu, Valerie Fong, Austin Hsu, Suzanna Chak, Ram P Naikawadi, Paul J Wolters, Adam R Abate, Atul J Butte, and Mallar Bhattacharya. 2019. Reference-based analysis of lung single-cell sequencing reveals a transitional profbrotic macrophage. Nat Immunol, 20(2):163-172. https://doi.org/10.1038/s41590-018-0276-yGoogle ScholarCross Ref
- Vladimir Yu Kiselev, Andrew Yiu, and Martin Hemberg. 2018. scmap: projection of single-cell RNA-seq data across data sets. Nat Methods, 15(5):359-362. https://doi.org/10.1038/nmeth.4644Google ScholarCross Ref
- Ze Zhang, Danni Luo, Xue Zhong, Jin Huk Choi, Yuanqing Ma, Stacy Wang, Elena Mahrt, Wei Guo, Eric W Stawiski, Zora Modrusan, Somasekar Seshagiri, Payal Kapur, Gary C Hon, James Brugarolas, and Tao Wang. 2019. SCINA: semi-supervised analysis of single cells in silico. Genes, 10:531. https://doi.org/Google ScholarCross Ref
- Feiyang Ma and Matteo Pellegrini. 2020. ACTINN: automated identifcation of cell types in single cell RNA sequencing. Bioinformatics, 36(2):533-538. https://doi.org/Google ScholarCross Ref
- Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, and Chengqi Zhang, Philip S Yu. 2021. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst, 32(1):4-24. https://doi.org/10.1109/TNNLS.2020.2978386Google ScholarCross Ref
- Tianyu Wang, Jun Bai, and Sheida Nabavi. 2021. Single-cell classification using graph convolutional networks. BMC Bioinformatics, 22(1):364. https://doi.org/Google ScholarCross Ref
- Damian Szklarczyk, Annika L Gable, David Lyon, Alexander Junge, Stefan Wyder, Jaime Huerta-Cepas, Milan Simonovic, Nadezhda T Doncheva, John H Morris, Peer Bork, Lars J Jensen, and Christian von Mering. 2019. STRING v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Res, 47(D1):D607-D613. https://doi.org/10.1093/nar/gky1131Google ScholarCross Ref
- Yuansong Zeng, Zhuoyi Wei, Zixiang Pan, Yutong Lu, and Yuedong Yang. 2022. A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification. Brief Bioinform, 23(2):bbab570. https://doi.org/10.1093/bib/bbab570Google ScholarCross Ref
- Krzysztof Polański, Matthew D Young, Zhichao Miao, Kerstin B Meyer, Sarah A Teichmann, and Jong-Eun Park. 2020. BBKNN: fast batch alignment of single cell transcriptomes. Bioinformatics, 36(3):964-965. https://doi.org/10.1093/bioinformatics/btz625Google ScholarCross Ref
- Vincent Mukwaya, Stephen Mann, and Hongjing Dou. 2021. Chemical communication at the synthetic cell/living cell interface. Commun Chem, 4(1):161. https://doi.org/10.1038/s42004-021-00597-wGoogle ScholarCross Ref
- Vladimir P Zhdanov. 2021. Proliferation of cells with aggregation and communication. Math Biosci, 301:32-36. https://doi.org/10.1016/j.mbs.2018.01.007Google ScholarCross Ref
- Dallas Foster, Brian Frost-LaPlante, Collin Victor, and Juan M Restrepo 2021. Gradient sensing via cell communication. Phys Rev E, 103(2-1):022405. https://doi.org/10.1103/PhysRevE.103.022405Google ScholarCross Ref
- Mauricio P. Pato. 2021. Disordered Random Walks. Brazilian Journal of Physics, 51:238-243. https://doi.org/Google ScholarCross Ref
- R. M. Phatarfod , T. P. Speed , A. M. Walker. 2016. A note on random walks. Journal of Applied Probability, 8(1):198-201. https://doi.org/Google ScholarCross Ref
- Yao Wu , Yu Song, Hong Huang, Fanghua Ye, Xing Xie, and Hai Jin. 2019. Enhancing Graph Neural Networks via auxiliary training for semi-supervised node classification. Knowledge-Based Systems, 220:106884. https://doi.org/Google ScholarCross Ref
- Tamim Abdelaal, Lieke Michielsen, Davy Cats, Dylan Hoogduin, Hailiang Mei, Marcel J T Reinders, and Ahmed Mahfouz. 2021. A comparison of automatic cell identification methods for single-cell RNA sequencing data. Genome Biology, 20(1):194. https://doi.org/10.1186/s13059-019-1795-zGoogle ScholarCross Ref
- Mohammadreza Heydarian, Thomas E. Doyle, and Reza Samavi . 2022. MLCM: Multi-Label Confusion Matrix. IEEE Access, 10:19083-19095. https://doi.org/Google Scholar
- Olivier Caelen. 2017. A Bayesian interpretation of the confusion matrix. Annals of Mathematics and Artificial Intelligence , 81:429-450. https://doi.org/Google ScholarDigital Library
- Kangwei Wang, Zhengwei Li, Zhu-Hong You, and Pengyong Han, Ru Nie. 2023. Adversarial dense graph convolutional networks for single-cell classification. Bioinformatics, 39(2):btad043. https://doi.org/10.1093/bioinformatics/btad043Google ScholarCross Ref
- Jacob C Kimmel, and David R Kelley. Semisupervised adversarial neural networks for single-cell classification. Genome Research, 31(10):1781-1793. https://doi.org/10.1101/gr.268581.120Google ScholarCross Ref
Recommendations
Accurate HEp-2 cell classification based on Sparse Coding of Superpixels
Proposing a new superpixel extraction method by adding the gradient information.Intelligently select the input patches based on proposed superpixel method.Proposing a technique for cell extraction from input masks of specimen images.Increasing the ...
Graph Neural Network for Cell Tracking in Microscopy Videos
Computer Vision – ECCV 2022AbstractWe present a novel graph neural network (GNN) approach for cell tracking in high-throughput microscopy videos. By modeling the entire time-lapse sequence as a direct graph where cell instances are represented by its nodes and their associations by ...
Pattern recognition and classification of two cancer cell lines by diffraction imaging at multiple pixel distances
Rapid and label-free imaging methods for accurate cell classification are highly desired for biology and clinical research. To improve consistency of classification performance, we have developed an approach of pattern analysis by gray level co-...
Comments