Towards future directions in data-integrative supervised prediction of human aging-related genes

MOTIVATION: Identification of human genes involved in the aging process is critical due to the incidence of many diseases with age. A state-of-the-art approach for this purpose infers a weighted dynamic aging-specific subnetwork by mapping gene expression (GE) levels at different ages onto the protein–protein interaction network (PPIN). Then, it analyzes this subnetwork in a supervised manner by training a predictive model to learn how network topologies of known aging- versus non-aging-related genes change across ages. Finally, it uses the trained model to predict novel aging-related gene candidates. However, the best current subnetwork resulting from this approach still yields suboptimal prediction accuracy. This could be because it was inferred using outdated GE and PPIN data. Here, we evaluate whether analyzing a weighted dynamic aging-specific subnetwork inferred from newer GE and PPIN data improves prediction accuracy upon analyzing the best current subnetwork inferred from outdated data. RESULTS: Unexpectedly, we find that not to be the case. To understand this, we perform aging-related pathway and Gene Ontology term enrichment analyses. We find that the suboptimal prediction accuracy, regardless of which GE or PPIN data is used, may be caused by the current knowledge about which genes are aging-related being incomplete, or by the current methods for inferring or analyzing an aging-specific subnetwork being unable to capture all of the aging-related knowledge. These findings can potentially guide future directions towards improving supervised prediction of aging-related genes via -omics data integration. AVAILABILITY AND IMPLEMENTATION: All data and code are available at zenodo, DOI: 10.5281/zenodo.6995045. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics Advances online.