Accurately predicting patient risk and identifying survival biomarkers are two important tasks in survival analysis. For the emerging high-throughput gene expression data, random survival forest (RSF) is attracting more and more attention as it not only shows excellent performance on survival prediction problems with high-dimensional variables, but also is capable of identifying important variables according to variable importance automatically calculated within the algorithm. However, RSF still suffers from some problems such as limited predictive accuracy on independent datasets and limited biological interpretation of survival biomarkers. In this study, we integrated gene interaction information into a Reweighted RSF model (RRSF) to improve predictive accuracy and identify biologically meaningful survival markers. We applied RRSF to the prediction of patients with glioblastoma multiforme (GBM) and esophageal squamous cell carcinoma (ESCC). With a reconstructed global pathway network and an mRNA-lncRNA co-expression network as the prior gene interaction information, RRSF showed better overall predictive performance than RSF on three GBM and two ESCC datasets. In addition, RRSF identified a two-gene and three-lncRNA signature, which showed robust prognostic values and had high biological relevance to the development of GBM and ESCC, respectively.
Pubmed ID: 30181543 RIS Download
Publication data is provided by the National Library of Medicine ® and PubMed ®. Data is retrieved from PubMed ® on a weekly schedule. For terms and conditions see the National Library of Medicine Terms and Conditions.
Curated data set from a study that investigated 77 primary high-grade astrocytomas and 23 matched recurrences so that changes in gene expression related to both survival and disease progression can be identified. Samples in the study include WHO grade III and IV astrocytomas with a wide range of survival times.
View all literature mentionsHuman and mouse genome annotation project which aims to identify all gene features in the human genome using computational analysis, manual annotation, and experimental validation.
View all literature mentionsIntegrated database resource consisting of 16 main databases, broadly categorized into systems information, genomic information, and chemical information. In particular, gene catalogs in completely sequenced genomes are linked to higher-level systemic functions of cell, organism, and ecosystem. Analysis tools are also available. KEGG may be used as reference knowledge base for biological interpretation of large-scale datasets generated by sequencing and other high-throughput experimental technologies.
View all literature mentions