Cancer survival prediction by learning comprehensive deep feature representation for multiple types of genetic data

Cancer is one of the leading death causes around the world. Accurate prediction of its survival time is significant, which can help clinicians make appropriate therapeutic schemes. Cancer data can be characterized by varied molecular features, clinical behaviors and morphological appearances. Howeve...

Full description

Saved in:
Bibliographic Details
Published inBMC bioinformatics Vol. 24; no. 1; p. 267
Main Authors Hao, Yaru, Jing, Xiao-Yuan, Sun, Qixing
Format Journal Article
LanguageEnglish
Published England BioMed Central Ltd 28.06.2023
BioMed Central
BMC
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:Cancer is one of the leading death causes around the world. Accurate prediction of its survival time is significant, which can help clinicians make appropriate therapeutic schemes. Cancer data can be characterized by varied molecular features, clinical behaviors and morphological appearances. However, the cancer heterogeneity problem usually makes patient samples with different risks (i.e., short and long survival time) inseparable, thereby causing unsatisfactory prediction results. Clinical studies have shown that genetic data tends to contain more molecular biomarkers associated with cancer, and hence integrating multi-type genetic data may be a feasible way to deal with cancer heterogeneity. Although multi-type gene data have been used in the existing work, how to learn more effective features for cancer survival prediction has not been well studied. To this end, we propose a deep learning approach to reduce the negative impact of cancer heterogeneity and improve the cancer survival prediction effect. It represents each type of genetic data as the shared and specific features, which can capture the consensus and complementary information among all types of data. We collect mRNA expression, DNA methylation and microRNA expression data for four cancers to conduct experiments. Experimental results demonstrate that our approach substantially outperforms established integrative methods and is effective for cancer survival prediction. https://github.com/githyr/ComprehensiveSurvival .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1471-2105
1471-2105
DOI:10.1186/s12859-023-05392-z