{"type":"ScholarlyArticle","title":"Toward Convex Manifolds: A Geometric Perspective for Deep Graph Clustering of Single-cell RNA-seq Data","authors":[{"name":"Nairouz Mrabah","slug":"nairouz-mrabah","given":"Nairouz","family":"Mrabah","affiliation":"University of Quebec at Montreal , Montreal , Quebec , Canada"},{"name":"Mohamed Mahmoud Amar","slug":"mohamed-mahmoud-amar","given":"Mohamed Mahmoud","family":"Amar","affiliation":"University of Quebec at Montreal , Montreal , Quebec , Canada"},{"name":"Mohamed Bouguessa","slug":"mohamed-bouguessa","given":"Mohamed","family":"Bouguessa","affiliation":"University of Quebec at Montreal , Montreal , Quebec , Canada"},{"name":"Abdoulaye Banire Diallo","slug":"abdoulaye-banire-diallo","given":"Abdoulaye Banire","family":"Diallo","affiliation":"University of Quebec at Montreal , Montreal , Quebec , Canada"}],"abstract":"The deep clustering paradigm has shown great potential for discovering complex patterns that can reveal cell heterogeneity in single-cell RNA sequencing data. This paradigm involves two training phases: pretraining based on a pretext task and fine-tuning using pseudo-labels. Although current models yield promising results, they overlook the geometric distortions that regularly occur during the training process. More precisely, the transition between the two phases results in a coarse flattening of the latent structures, which can deteriorate the clustering performance. In this context, existing methods perform euclidean-based embedding clustering without ensuring the flatness and convexity of the latent manifolds. To address this problem, we incorporate two mechanisms. First, we introduce an overclustering loss to flatten the local curves. Second, we propose an adversarial mechanism to adjust the global geometric configuration. The second mechanism gradually transforms the latent structures into convex ones. Empirical results on a variety of gene expression datasets show that our model outperforms state-of-the-art methods.","doi":"10.24963/ijcai.2023/540","url":"https://ijcai.org/proceedings/2023/540","pdf":"https://ijcai.org/proceedings/2023/0540.pdf","markdown":"https://ijcai.org/proceedings/2023/540.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/540","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":540,"pages":{"first":4855,"last":4863},"keywords":["Machine Learning: ML: Clustering","Multidisciplinary Topics and Applications: MDA: Bioinformatics","Machine Learning: ML: Unsupervised learning"],"videos":[],"references":[{"position":1,"raw":"[Boyd et al., 2004] Stephen Boyd, Stephen P Boyd, and Lieven Vandenberghe. Convex optimization. Cambridge university press, 2004.","title":"Convex optimization","authors":"Stephen Boyd, Stephen P Boyd, Lieven Vandenberghe","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brady et al., 2017] Samuel W Brady, Jasmine A McQuerry, Yi Qiao, Stephen R Piccolo, Gajendra Shrestha, David F Jenkins, Ryan M Layer, Brent S Pedersen, Ryan H Miller, Amanda Esch, et al. Combating subclonal evolution of resistant cancer phenotypes. Nature communications, 8(1):1-15, 2017.","title":"Combating subclonal evolution of resistant cancer phenotypes","authors":"Jasmine A Samuel W Brady, Yi Mcquerry, Qiao, Gajendra Stephen R Piccolo, David F Shrestha, Ryan M Jenkins, Layer, Ryan H Brent S Pedersen, Amanda Miller, Esch","year":"2017","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2020] Liang Chen, Weinan Wang, Yuyao Zhai, and Minghua Deng. Deep soft k-means clustering with self-training for single-cell rna sequence data. NAR ge- nomics and bioinformatics, 2(2):lqaa039, 2020.","title":"Deep soft k-means clustering with self-training for single-cell rna sequence data","authors":"Liang Chen, Weinan Wang, Yuyao Zhai, Minghua Deng","year":"2020","venue":"NAR genomics and bioinformatics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Eraslan et al., 2019] Gökcen Eraslan, Lukas M Simon, Maria Mircea, Nikola S Mueller, and Fabian J Theis. Single-cell rna-seq denoising using a deep count autoen- coder. Nature communications, 10(1):1-14, 2019.","title":"Single-cell rna-seq denoising using a deep count autoencoder","authors":"Eraslan","year":"2019","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ester et al., 1996] Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In KDD, volume 96, pages 226-231, 1996.","title":"A density-based algorithm for discovering clusters in large spatial databases with noise","authors":"Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu","year":"1996","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gan et al., 2022] Yanglan Gan, Xingyu Huang, Guobing Zou, Shuigeng Zhou, and Jihong Guan. Deep structural clustering for single-cell rna-seq data jointly through au- toencoder and graph neural network. Briefings in Bioin- formatics, 23(2):bbac018, 2022.","title":"Deep structural clustering for single-cell rna-seq data jointly through autoencoder and graph neural network","authors":"Gan","year":"2022","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huang et al., 2018] Mo Huang, Jingshu Wang, Eduardo Torre, Hannah Dueck, Sydney Shaffer, Roberto Bonasio, John I Murray, Arjun Raj, Mingyao Li, and Nancy R Zhang. Saver: gene expression recovery for single-cell rna sequencing. Nature methods, 15(7):539-542, 2018.","title":"Saver: gene expression recovery for single-cell rna sequencing","authors":"Mo Huang, Jingshu Wang, Eduardo Torre, Hannah Dueck, Sydney Shaffer, Roberto Bonasio, John I Murray, Arjun Raj, Mingyao Li, Nancy R Zhang","year":"2018","venue":"Nature methods","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Johnson, 1967] Stephen C Johnson. Hierarchical clustering schemes. Psychometrika, 32(3):241-254, 1967.","title":"Hierarchical clustering schemes","authors":"Johnson Stephen","year":"1967","venue":"Psychometrika","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Variational graph auto-encoders. In NeurIPS workshop, volume 32, pages 1-3, 2016.","title":"Variational graph auto-encoders","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":"NeurIPS workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lin et al., 2017] Peijie Lin, Michael Troup, and Joshua WK Ho. Cidr: Ultrafast and accurate clustering through im- putation for single-cell rna-seq data. Genome biology, 18(1):1-11, 2017.","title":"Cidr: Ultrafast and accurate clustering through imputation for single-cell rna-seq data","authors":"Lin","year":"2017","venue":"Genome biology","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Luo et al., 2021] Zixiang Luo, Chenyu Xu, Zhen Zhang, and Wenfei Jin. A topology-preserving dimensionality re- duction method for single-cell rna-seq data using graph au- toencoder. Scientific reports, 11(1):1-8, 2021.","title":"A topology-preserving dimensionality reduction method for single-cell rna-seq data using graph autoencoder","authors":"Luo","year":"2021","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mrabah et al., 2022] Nairouz Mrabah, Mohamed Bouguessa, and Riadh Ksantini. Escaping feature twist: A variational graph auto-encoder for node clustering. In IJCAI, pages 3351-3357, 2022.","title":"Nairouz Mrabah, Mohamed Bouguessa, and Riadh Ksantini. Escaping feature twist: A variational graph auto-encoder for node clustering","authors":"Mrabah","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ocasio et al., 2019] Jennifer Karin Ocasio, Benjamin Bab- cock, Daniel Malawsky, Seth J Weir, Lipin Loo, Jeremy M Simon, Mark J Zylka, Duhyeong Hwang, Taylor Dismuke, Marina Sokolsky, et al. scrna-seq in medulloblastoma shows cellular heterogeneity and lineage expansion sup- port resistance to shh inhibitor therapy. Nature communi- cations, 10(1):1-17, 2019.","title":"scrna-seq in medulloblastoma shows cellular heterogeneity and lineage expansion support resistance to shh inhibitor therapy","authors":"Karin Jennifer, Benjamin Ocasio, Daniel Babcock, Seth J Malawsky, Lipin Weir, Jeremy M Loo, Mark J Simon, Duhyeong Zylka, Taylor Hwang, Marina Dismuke, Sokolsky","year":"2019","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Park and Zhao, 2018] Seyoung Park and Hongyu Zhao. Spectral clustering based on learning similarity matrix. Bioinformatics, 34(12):2069-2076, 2018.","title":"Seyoung Park and Hongyu Zhao. Spectral clustering based on learning similarity matrix","authors":"Zhao Park","year":"2018","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Saviano et al., 2020] Antonio Saviano, Neil C Henderson, and Thomas F Baumert. Single-cell genomics and spatial transcriptomics: Discovery of novel cell states and cellular interactions in liver physiology and disease biology. Jour- nal of hepatology, 73(5):1219-1230, 2020.","title":"Single-cell genomics and spatial transcriptomics: Discovery of novel cell states and cellular interactions in liver physiology and disease biology","authors":"Antonio Saviano, Neil C Henderson, Thomas F Baumert","year":"2020","venue":"Journal of hepatology","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shalek et al., 2014] Alex K Shalek, Rahul Satija, Joe Shuga, John J Trombetta, Dave Gennert, Diana Lu, Peilin Chen, Rona S Gertner, Jellert T Gaublomme, Nir Yosef, et al. Single-cell rna-seq reveals dynamic paracrine control of cellular variation. Nature, 510(7505):363-369, 2014.","title":"Single-cell rna-seq reveals dynamic paracrine control of cellular variation","authors":"Alex K Shalek, Rahul Satija, Joe Shuga, John J Trombetta, Dave Gennert, Diana Lu, Peilin Chen, Rona S Gertner, T Jellert, Nir Gaublomme, Yosef","year":"2014","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tian et al., 2019] Tian Tian, Ji Wan, Qi Song, and Zhi Wei. Clustering single-cell rna-seq data with a model-based deep learning approach. Nature Machine Intelligence, 1(4):191-198, 2019.","title":"Clustering single-cell rna-seq data with a model-based deep learning approach","authors":"Tian Tian, Ji Wan, Qi Song, Zhi Wei","year":"2019","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tian et al., 2021] Tian Tian, Jie Zhang, Xiang Lin, Zhi Wei, and Hakon Hakonarson. Model-based deep embedding for constrained clustering analysis of single cell rna-seq data. Nature communications, 12(1):1-12, 2021.","title":"Model-based deep embedding for constrained clustering analysis of single cell rna-seq data","authors":"Tian Tian, Jie Zhang, Xiang Lin, Zhi Wei, Hakon Hakonarson","year":"2021","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tirosh et al., 2016] Itay Tirosh, Benjamin Izar, Sanjay M Prakadan, Marc H Wadsworth, Daniel Treacy, John J Trombetta, Asaf Rotem, Christopher Rodman, Christine Lian, George Murphy, et al. Dissecting the multicellular ecosystem of metastatic melanoma by single-cell rna-seq. Science, 352(6282):189-196, 2016.","title":"Dissecting the multicellular ecosystem of metastatic melanoma by single-cell rna-seq","authors":"Itay Tirosh, Benjamin Izar, Marc H Sanjay M Prakadan, Daniel Wadsworth, John J Treacy, Asaf Trombetta, Christopher Rotem, Christine Rodman, George Lian, Murphy","year":"2016","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Treutlein et al., 2014] Barbara Treutlein, Doug G Brown- field, Angela R Wu, Norma F Neff, Gary L Mantalas, F Hernan Espinoza, Tushar J Desai, Mark A Krasnow, and Stephen R Quake. Reconstructing lineage hierarchies of the distal lung epithelium using single-cell rna-seq. Na- ture, 509(7500):371-375, 2014.","title":"Reconstructing lineage hierarchies of the distal lung epithelium using single-cell rna-seq","authors":"Barbara Treutlein, Doug G Brownfield, Angela R Wu, Norma F Neff, Gary L Mantalas, F Hernan Espinoza, Tushar J Desai, Mark A Krasnow, Stephen R Quake","year":"2014","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[van Dijk et al., 2017] David van Dijk, Juozas Nainys, Roshan Sharma, Pooja Kaithail, Ambrose J Carr, Kevin R Moon, Linas Mazutis, Guy Wolf, Smita Krishnaswamy, and Dana Pe'er. Magic: A diffusion-based imputation method reveals gene-gene interactions in single-cell rna- sequencing data. BioRxiv, page 111591, 2017.","title":"Magic: A diffusion-based imputation method reveals gene-gene interactions in single-cell rnasequencing data","authors":"Juozas David Van Dijk, Roshan Nainys, Pooja Sharma, Ambrose J Kaithail, Kevin R Carr, Linas Moon, Guy Mazutis, Smita Wolf, Dana Krishnaswamy, ' Pe, Er","year":"2017","venue":"BioRxiv","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2017] Bo Wang, Junjie Zhu, Emma Pierson, Daniele Ramazzotti, and Serafim Batzoglou. Visualization and analysis of single-cell rna-seq data by kernel-based similarity learning. Nature methods, 14(4):414-416, 2017.","title":"Visualization and analysis of single-cell rna-seq data by kernel-based similarity learning","authors":"Bo Wang, Junjie Zhu, Emma Pierson, Daniele Ramazzotti, Serafim Batzoglou","year":"2017","venue":"Nature methods","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2021] Juexin Wang, Anjun Ma, Yuzhou Chang, Jianting Gong, Yuexu Jiang, Ren Qi, Cankun Wang, Hongjun Fu, Qin Ma, and Dong Xu. scgnn is a novel graph neural network framework for single-cell rna-seq analyses. Nature communications, 12(1):1-11, 2021.","title":"scgnn is a novel graph neural network framework for single-cell rna-seq analyses","authors":"Wang","year":"2021","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xie et al., 2016] Junyuan Xie, Ross Girshick, and Ali Farhadi. Unsupervised deep embedding for clustering analysis. In ICML, pages 478-487, 2016.","title":"Unsupervised deep embedding for clustering analysis","authors":"Junyuan Xie, Ross Girshick, Ali Farhadi","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yu et al., 2021] Bin Yu, Chen Chen, Ren Qi, Ruiqing Zheng, Patrick J Skillman-Lawrence, Xiaolin Wang, An- jun Ma, and Haiming Gu. scgmai: a gaussian mixture model for clustering single-cell rna-seq data based on deep autoencoder. Briefings in Bioinformatics, 22(4):316, 2021.","title":"scgmai: a gaussian mixture model for clustering single-cell rna-seq data based on deep autoencoder","authors":"Bin Yu, Chen Chen, Ren Qi, Ruiqing Zheng, Patrick J Skillman-Lawrence, Xiaolin Wang, Anjun Ma, Haiming Gu","year":"2021","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yu et al., 2022] Zhuohan Yu, Yifu Lu, Yunhe Wang, Fan Tang, Ka-Chun Wong, and Xiangtao Li. Zinb-based graph embedding autoencoder for single-cell rna-seq interpreta- tions. AAAI, 36(4):4671-4679, 2022.","title":"Zinb-based graph embedding autoencoder for single-cell rna-seq interpretations","authors":"Yu","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}