Description
In recent years, the rapid development of high-throughput technologies has led to many types of omics data. Various methods have been proposed to instill biological insights from each data type. However, with the advancement of deep learning, researchers started integrating diverse data types using neural networks to answer clinically relevant questions more accurately. Moreover, some methods have shown that supervised methods can provide better accuracy and interpretability. On the other hand, long non-coding RNAs have proven to play a significant role in cancer biomarker prediction. In this study, we conducted an analysis that utilizes the International Cancer Genome Consortium (ICGC) datasets for four types of cancer and identifies new biomarkers by providing a list of relevant genes, which achieved 82% accuracy.
