Predicting Gastric Cancer Molecular Subtypes from Gene Expression Data

Proceedings

Marta Moreno¹  Pedro G Ferreira¹  Abel Sousa²  Marta Melé³  Rui Oliveira⁴ 

[1] Department of Computer Science, Faculty of Sciences, University of Porto, 4169-007 Porto, Portugal;Ipatimup—Institute of Molecular Pathology and Immunology of the University of Porto, 4200-465 Porto, Portugal;Life Sciences Department, Barcelona Supercomputing Center, Barcelona, 08034 Catalonia, Spain;University of Minho and INESC TEC, 4200-465 Porto, Portugal;

关键词: gene expression;    gastric cancer;    disease classification;    machine learning;   

DOI  :  10.3390/proceedings2020054059

来源: DOAJ

【 摘 要 】

Stomach cancer is a complex disease and one of the leading causes of cancer mortality in the world. With the view to improve patient diagnosis and prognosis, it has been stratified into four molecular subtypes. In this work, we compare the results of multiple machine learning algorithms for the prediction of stomach cancer molecular subtypes from gene expression data. Moreover, we show the importance of decorrelating clinical and technical covariates.

【 授权许可】

Unknown