TCox: Correlation-Based Regularization Applied to Colorectal Cancer Survival Data

被引:3
|
作者
Peixoto, Carolina [1 ]
Lopes, Marta B. [2 ,3 ]
Martins, Marta [4 ]
Costa, Luis [4 ,5 ]
Vinga, Susana [1 ]
机构
[1] Univ Lisbon, Inst Super Tecn, INESC ID, Rua Alves Redol 9, P-1000029 Lisbon, Portugal
[2] UNL, FCT, NOVA Lab Comp Sci & Informat NOVA LINCS, P-2829516 Caparica, Portugal
[3] UNL, FCT, Ctr Matemat & Aplicacoes CMA, P-2829516 Caparica, Portugal
[4] Univ Lisbon, Fac Med, Inst Med Mol Joao Lobo Antunes, Ave Prof Egas Moniz, P-1649028 Lisbon, Portugal
[5] Ctr Hosp Lisboa Norte, Hosp Santa, Oncol Div, P-1649028 Lisbon, Portugal
关键词
regularized optimization; Cox regression; survival analysis; TCGA data; RNA-seq data; SELECTION; PACKAGE; MODELS; PATHS; TOOL;
D O I
10.3390/biomedicines8110488
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Colorectal cancer (CRC) is one of the leading causes of mortality and morbidity in the world. Being a heterogeneous disease, cancer therapy and prognosis represent a significant challenge to medical care. The molecular information improves the accuracy with which patients are classified and treated since similar pathologies may show different clinical outcomes and other responses to treatment. However, the high dimensionality of gene expression data makes the selection of novel genes a problematic task. We propose TCox, a novel penalization function for Cox models, which promotes the selection of genes that have distinct correlation patterns in normal vs. tumor tissues. We compare TCox to other regularized survival models, Elastic Net, HubCox, and OrphanCox. Gene expression and clinical data of CRC and normal (TCGA) patients are used for model evaluation. Each model is tested 100 times. Within a specific run, eighteen of the features selected by TCox are also selected by the other survival regression models tested, therefore undoubtedly being crucial players in the survival of colorectal cancer patients. Moreover, the TCox model exclusively selects genes able to categorize patients into significant risk groups. Our work demonstrates the ability of the proposed weighted regularizer TCox to disclose novel molecular drivers in CRC survival by accounting for correlation-based network information from both tumor and normal tissue. The results presented support the relevance of network information for biomarker identification in high-dimensional gene expression data and foster new directions for the development of network-based feature selection methods in precision oncology.
引用
收藏
页码:1 / 16
页数:16
相关论文
共 50 条
  • [1] Twiner: correlation-based regularization for identifying common cancer gene signatures
    Marta B. Lopes
    Sandra Casimiro
    Susana Vinga
    [J]. BMC Bioinformatics, 20
  • [2] Twiner: correlation-based regularization for identifying common cancer gene signatures
    Lopes, Marta B.
    Casimiro, Sandra
    Vinga, Susana
    [J]. BMC BIOINFORMATICS, 2019, 20 (1)
  • [3] Visualization of correlation-based environmental data
    Dzemyda, G
    [J]. ENVIRONMETRICS, 2004, 15 (08) : 827 - 836
  • [4] Correlation-based interpolation of NSCAT wind data
    Polito, PS
    Liu, WT
    Tang, WQ
    [J]. JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY, 2000, 17 (08) : 1128 - 1138
  • [5] Correlation-based search for time series data
    Ibrahim, Ibrahim A.
    Albarrak, Abdullah M.
    [J]. INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2020, 62 (02) : 158 - 174
  • [6] Correlation-Based Analytics of Time Series Data
    Ahsan, Ramoza
    Neamtu, Rodica
    Bashir, Muzammil
    Rundensteiner, Elke A.
    Sarkozy, Gabor
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2020, : 4482 - 4491
  • [7] Correlation-based embedding of pairwise score data
    Strickert, Marc
    Bunte, Kerstin
    Schleif, Frank-Michael
    Huellermeier, Eyke
    [J]. NEUROCOMPUTING, 2014, 141 : 97 - 109
  • [8] Correlation-based search for time series data
    Ibrahim, Ibrahim A.
    Albarrak, Abdullah M.
    [J]. International Journal of Computer Applications in Technology, 2020, 62 (02): : 158 - 174
  • [9] Correlation-based data broadcasting in wireless networks
    Cai, KK
    Lin, HZ
    Chen, C
    [J]. DATABASE: ENTERPRISE, SKILLS AND INNOVATION, PROCEEDINGS, 2005, 3567 : 111 - 119
  • [10] Dimensionality problem in the visualization of correlation-based data
    Dzemyda, Gintautas
    Kurasova, Olga
    [J]. ADAPTIVE AND NATURAL COMPUTING ALGORITHMS, PT 2, 2007, 4432 : 544 - +