New Open-Source Tool RNACOREX Maps Gene Regulation Networks to Predict Cancer Survival

RNACOREX Emerges as Explainable Alternative to AI Models in Cancer Research

Researchers at the University of Navarra in Spain have introduced RNACOREX, an open-source software platform designed to identify gene regulation networks with direct applications in cancer survival analysis. 1

1

Developed by scientists at the Institute of Data Science and Artificial Intelligence (DATAI) in collaboration with members of the Cancer Center Clínica Universidad de Navarra, this tool addresses a critical gap in genomics research by offering interpretable insights into how tumors function at the molecular level.

Published in PLOS Computational Biology, RNACOREX can analyze thousands of biological molecules simultaneously, detecting important molecular interactions that conventional analytical approaches frequently overlook. 2

2

The software has been validated using data from thirteen different tumor types provided by The Cancer Genome Atlas (TCGA), including breast, colon, lung, stomach, melanoma, and head and neck tumors.

Decoding Complex Molecular Communication in Cancer

Inside human cells, different types of molecules such as microRNAs (miRNAs) and messenger RNA (mRNA) communicate through highly complex regulatory networks. When these networks fail to function properly, cancer and other diseases can develop. "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. 1

1

RNACOREX overcomes these obstacles by integrating curated information from international biological databases with real-world gene expression data to rank the most biologically meaningful miRNA-mRNA interactions. From this foundation, the software builds progressively more complex regulatory networks that can also function as probabilistic models for studying disease behavior.

Predicting Patient Survival With Transparent Insights

The research team applied RNACOREX to data from thirteen different cancers to evaluate its performance. "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," says Aitor Oviedo-Madrid, a researcher at the Digital Medicine Laboratory of DATAI and first author of the study. 2

2

Beyond survival prediction, RNACOREX identifies regulatory networks linked to clinical outcomes, detects molecular patterns shared across multiple tumor types, and spotlights individual molecules with strong biomedical relevance. These capabilities may help researchers generate new hypotheses about tumor progression while pointing toward promising potential diagnostic markers or potential treatment targets. "Our tool provides a reliable molecular 'map' that helps prioritize new biological targets, speeding up cancer research," Oviedo-Madrid adds. 1

1

Open Access Advances Biomedicine and Data Science Integration

RNACOREX is freely available as an open-source program on GitHub and PyPI (Python Package Index), including automated tools for downloading databases to streamline integration into laboratory workflows. The project has received partial funding from the Government of Navarra (ANDIA 2021 program) and the ERA PerMed JTC2022 PORTRAIT. 1

1

"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. 2

2

The University of Navarra team is already working on expanding the software's capabilities, with planned additions including pathway analysis and new layers of molecular interaction data. These efforts aim to create models that more fully explain the biological mechanisms behind tumor growth and progression, reflecting the institution's commitment to interdisciplinary research that combines biomedicine, artificial intelligence, and data science to advance personalized and precision cancer medicine.