Researchers at the University of Navarra in Spain have developed an open-source software tool, RNACOREX, designed to identify gene regulation networks relevant to cancer survival analysis. The team behind the tool includes scientists from the Institute of Data Science and Artificial Intelligence (DATAI) and members of the Cancer Center Clínica Universidad de Navarra.
RNACOREX has been validated using data from thirteen different tumor types provided by The Cancer Genome Atlas (TCGA), an international consortium. The software analyzes thousands of molecules simultaneously, detecting key molecular interactions that may not be revealed through conventional analytical methods. By providing a detailed molecular "map," RNACOREX aims to improve researchers' understanding of tumors and help uncover mechanisms involved in tumor progression.
The software integrates information from international databases with actual gene-expression data to rank biologically significant interactions between microRNAs (miRNAs) and messenger RNA (mRNA). Using this approach, it builds complex regulatory networks that can serve as probabilistic models for further study.
According to Aitor Oviedo-Madrid, a researcher at DATAI's Digital Medicine Laboratory and first author of the published study in PLOS Computational Biology, "The software predicted patient survival with accuracy on par with sophisticated AI models, but with something many of those systems lack: clear, interpretable explanations of the molecular interactions behind the results."
Beyond mapping regulatory networks linked to clinical outcomes, RNACOREX identifies shared molecular patterns across various tumor types and highlights individual molecules that could be significant for biomedical research. These insights may inform future diagnostic or therapeutic strategies. As Oviedo-Madrid notes, "Our tool provides a reliable molecular 'map' that helps prioritize new biological targets, speeding up cancer research."
The program is available as open-source on GitHub and PyPI (Python Package Index), featuring automated database downloads for ease of use in laboratory settings. Funding for the project was partially provided by the Government of Navarra through its ANDIA 2021 program and by ERA PerMed JTC2022 PORTRAIT.
Armañanzas commented on RNACOREX's role within artificial intelligence applications in genomics: "As artificial intelligence in genomics accelerates, RNACOREX positions itself as an explainable, easy-to-interpret solution and an alternative to 'black-box' models, helping bring omics data into biomedical practice."
Future developments planned by the University of Navarra include expanding functionalities such as pathway analysis and additional interaction layers. These enhancements are intended to create more comprehensive models explaining how tumors grow and progress. This work reflects the university’s ongoing commitment to integrating biomedicine, artificial intelligence, and data science for advancing personalized cancer care.
