Source:Artificial Intelligence in Medicine
Author(s): Lei Chen, Yu-Hang Zhang, Guohui Lu, Tao Huang, Yu-Dong Cai
BackgroundCancer is a disease that involves abnormal cell growth and can invade or metastasize to other tissues. It is known that several factors are related to its initiation, proliferation, and invasiveness. Recently, it has been reported that long non-coding RNAs (lncRNAs) can participate in specific functional pathways and further regulate the biological function of cancer cells. Studies on lncRNAs are therefore helpful for uncovering the underlying mechanisms of cancer biological processes.MethodsWe investigated cancer-related lncRNAs using gene ontology (GO) terms and KEGG pathway enrichment scores of neighboring genes that are co-expressed with the lncRNAs by extracting important GO terms and KEGG pathways that can help us identify cancer-related lncRNAs. The enrichment theory of GO terms and KEGG pathways was adopted to encode each lncRNA. Then, feature selection methods were employed to analyze these features and obtain the key GO terms and KEGG pathways.ResultsThe analysis indicated that the extracted GO terms and KEGG pathways are closely related to several cancer associated processes, such as hormone associated pathways, energy associated pathways, and ribosome associated pathways. And they can accurately predict cancer-related lncRNAs.ConclusionsThis study provided novel insight of how lncRNAs may affect tumorigenesis and which pathways may play important roles during it. These results could help understanding the biological mechanisms of lncRNAs and treating cancer.
http://ift.tt/2l1Bhvo
Δεν υπάρχουν σχόλια:
Δημοσίευση σχολίου