Similarity network fusion based on local scaling affinity construction

Konferenz: BIBE 2018 - International Conference on Biological Information and Biomedical Engineering
06.06.2018 - 08.06.2018 in Shanghai, China

Tagungsband: BIBE 2018

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Duan, Xin; Wang, Kejun (College of Automation, Harbin Engineering University, Harbin, China)

Integrating the diverse types of genome-wide data can provide us a deeper understanding of the biological process. Multi-omics data integration methods are needed to deal with the increasing information from various data layers. Based on the widely used method - Similarity Network Fusion(SNF), however, suffering the trivial parameters setting, we present Ls-SNF which employs the local scaling method to construct the affinity matrix. To demonstrate the effectiveness, we applied Ls-SNF to colon cancer and lung cancer subtyping. Compared with the similarity network fusion(SNF) and affinity network fusion (ANF), our approach can eliminate the scaling problem and needs less parameters while producing better clustering performance.