Exploring Pathway-Based Group Lasso for Cancer Survival Analysis: A Special Case of Multi-Task Learning

被引:2
作者
Malenova, Gabriela [1 ]
Rowson, Daniel [1 ]
Boeva, Valentina [1 ,2 ,3 ]
机构
[1] Swiss Fed Inst Technol, Inst Machine Learning, Dept Comp Sci, Zurich, Switzerland
[2] Swiss Inst Bioinformat SIB, Zurich, Switzerland
[3] Univ Paris, CNRS, INSERM, Institut Cochin,UMRS 1016,UMR 8104,U1016, Paris, France
关键词
survival analysis; Cox model; cancer; lasso; group lasso; multi-task; signalling pathways; VARIABLE SELECTION; REGRESSION;
D O I
10.3389/fgene.2021.771301
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
Motivation: The Cox proportional hazard models are widely used in the study of cancer survival. However, these models often meet challenges such as the large number of features and small sample sizes of cancer data sets. While this issue can be partially solved by applying regularization techniques such as lasso, the models still suffer from unsatisfactory predictive power and low stability.Methods: Here, we investigated two methods to improve survival models. Firstly, we leveraged the biological knowledge that groups of genes act together in pathways and regularized both at the group and gene level using latent group lasso penalty term. Secondly, we designed and applied a multi-task learning penalty that allowed us leveraging the relationship between survival models for different cancers.Results: We observed modest improvements over the simple lasso model with the inclusion of latent group lasso penalty for six of the 16 cancer types tested. The addition of a multi-task penalty, which penalized coefficients in pairs of cancers from diverging too greatly, significantly improved accuracy for a single cancer, lung squamous cell carcinoma, while having minimal effect on other cancer types.Conclusion: While the use of pathway information and multi-tasking shows some promise, these methods do not provide a substantial improvement when compared with standard methods.
引用
收藏
页数:10
相关论文
共 36 条
[1]  
[Anonymous], 2011, Tech. Rep.
[2]   Gene Ontology: tool for the unification of biology [J].
Ashburner, M ;
Ball, CA ;
Blake, JA ;
Botstein, D ;
Butler, H ;
Cherry, JM ;
Davis, AP ;
Dolinski, K ;
Dwight, SS ;
Eppig, JT ;
Harris, MA ;
Hill, DP ;
Issel-Tarver, L ;
Kasarskis, A ;
Lewis, S ;
Matese, JC ;
Richardson, JE ;
Ringwald, M ;
Rubin, GM ;
Sherlock, G .
NATURE GENETICS, 2000, 25 (01) :25-29
[3]  
COX DR, 1972, J R STAT SOC B, V34, P187
[4]  
Dereli Onur, 2019, INT C MACH LEARN, P1576
[5]  
Evgeniou T, 2005, J MACH LEARN RES, V6, P615
[6]   The Reactome Pathway Knowledgebase [J].
Fabregat, Antonio ;
Jupe, Steven ;
Matthews, Lisa ;
Sidiropoulos, Konstantinos ;
Gillespie, Marc ;
Garapati, Phani ;
Haw, Robin ;
Jassal, Bijay ;
Korninger, Florian ;
May, Bruce ;
Milacic, Marija ;
Roca, Corina Duenas ;
Rothfels, Karen ;
Sevilla, Cristoffer ;
Shamovsky, Veronica ;
Shorser, Solomon ;
Varusai, Thawfeek ;
Viteri, Guilherme ;
Weiser, Joel ;
Wu, Guanming ;
Stein, Lincoln ;
Hermjakob, Henning ;
D'Eustachio, Peter .
NUCLEIC ACIDS RESEARCH, 2018, 46 (D1) :D649-D655
[7]   A pathway-based classification of human breast cancer [J].
Gatza, Michael L. ;
Lucas, Joseph E. ;
Barry, William T. ;
Kim, Jong Wook ;
Wang, Quanli ;
Crawford, Matthew D. ;
Datto, Michael B. ;
Kelley, Michael ;
Mathey-Prevot, Bernard ;
Potti, Anil ;
Nevins, Joseph R. .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2010, 107 (15) :6994-6999
[8]  
Gornitz N., 2011, P ADV NEUR INF PROC, P2690
[9]   Large-scale benchmark study of survival prediction methods using multi-omics data [J].
Herrmann, Moritz ;
Probst, Philipp ;
Hornung, Roman ;
Jurinovic, Vindi ;
Boulesteix, Anne-Laure .
BRIEFINGS IN BIOINFORMATICS, 2021, 22 (03)
[10]   Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations [J].
Huang, Zhi ;
Johnson, Travis S. ;
Han, Zhi ;
Helm, Bryan ;
Cao, Sha ;
Zhang, Chi ;
Salama, Paul ;
Rizkalla, Maher ;
Yu, Christina Y. ;
Cheng, Jun ;
Xiang, Shunian ;
Zhan, Xiaohui ;
Zhang, Jie ;
Huang, Kun .
BMC MEDICAL GENOMICS, 2020, 13 (Suppl 5)