Sergio Vela Moreno

This study compares 16S rRNA gene sequencing and meta-transcriptomic analyses of endometrial microbiota, finding weak correlation in low-biomass environments and highlighting the value of RNA-based functional insights.

This paper develops explainable machine learning models to predict relapse timing in endometrial cancer using preoperative data, finding high performance with F1 scores up to 0.895.

The paper investigates endometrial polyps using bulk and single-cell RNA sequencing, identifying aberrant stromal-to-epithelial transitions and altered differentiation trajectories.

OncoProExp is a web application for cancer proteomics and phosphoproteomics analysis, offering tools for data exploration, biomarker discovery, and risk stratification using machine learning.