New software sheds light on cancer’s hidden genetic networks

Researchers at the University of Navarra have developed RNACOREX, open-source software capable of identifying Genetics regulatory networks Genetics applications in cancer survival analysis. The tool, created by scientists at the Institute of data Science data Artificial Intelligence (DATAI)and members of Clínica Universidad de Navarra Cancer Center, has been validated with data thirteen types of tumors from the international consortium The Cancer Genome Atlas (TCGA).

Published in PLOS Computational Biology, RNACOREX analyzes thousands of molecules simultaneously to detect key interactions that often remain undetected using conventional analytical approaches. The tool provides researchers with an interpretable molecular “map” that improves the understanding of tumors and opens new venues forrevealing the mechanisms that drive tumor progression.

Decoding Cancer’s Hidden Genetic Structure

Inside our cells, different types of molecules — such as microRNAs (miRNAs) and messenger RNA (mRNA )— communicate through highly complex regulatory networks. When these connections break down, cancers and other diseases can emerge

“Understanding the architecture of these networks is crucial for detecting, studying, and classifying different tumor types. However, reliably identifying these networks is a challenge due to the vast amount of available data, the presence of many false signals,and the lack of accessible and precise tools capable of distinguishing which molecular interactions are truly associated with each disease,” says Rubén Armañanzas, head of the  Digital Medicine Laboratory at DATAI  and one of the study’s lead authors.

RNACOREX addresses this problem by combining information from international databases with real gene-expression data analysis to rank the most biologically relevant miRNA–mRNA interactions. Using this information, it derives increasingly complex regulatory networks that could also serve as powerful probabilistic models.

Better interpretation and prediction

To assess its performance, researchers evaluated RNACOREX on thirteen cancer types — from breast and colon to lung, stomach, melanoma, and head and neck — using data from The Cancer Genome Atlas (TCGA) consortium. “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”, adds Aitor Oviedo-Madrid, a researcher at the Digital Medicine Laboratory of DATAI and first author of the study.

RNACOREX not only identifies regulatory networks associated with clinical outcomes, but also uncovers molecular patterns shared across tumor types and highlights individual molecules of particular biomedical interest. These findings open the door to new hypotheses about the mechanisms that regulate tumor growth and suggest valuable clues for future diagnostic or therapeutic targets. “Our tool provides a reliable molecular ‘map’ that helps prioritize new biological targets, speeding up cancer research”, he concludes.

An evolving open-source tool

RNACOREX is an open-source program available on GitHub  and PyPI (Python Package Index),  and includes automated database downloads to streamline its use inlaboratories and research centers. The project has been partially funded by theGovernment of Navarra (ANDIA 2021 program) and the ERA PerMed JTC2022PORTRAIT.

“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,” says Armañanzas.

The University of Navarra is already developing new functionalities — includingpathway analysis and additional interaction layers — to develop models that betterexplain the mechanisms driving tumor growth and progression. These advances reflectthe institution’s commitment to interdisciplinary research that integrates biomedicine,AI, and data science to improve understanding and management of cancer throughpersonalized and precision medicine.