Researchers from Marshall University and the University of Missouri have partnered to develop G2PDeep, an innovative web-based platform that uses advanced AI to analyze multiple types of biological data and more accurately predict complex health outcomes.
The team’s peer-reviewed article describing the technology was published this month in Biomolecules . G2PDeep integrates six major types of molecular data—gene expression, microRNA (miRNA) expression, protein expression, DNA methylation, single nucleotide polymorphisms (SNPs) and copy number variations (CNVs)—to produce highly accurate phenotypic predictions. This capability allows researchers and clinicians to better identify omics-based molecular markers that distinguish patient cohorts, improve risk assessment and advance personalized treatment strategies.
The platform has wide-reaching applications across biomedical science, including cancer, addiction, aging, obesity, kidney disease and other conditions that significantly impact populations across Appalachia and the Midwest. By bringing together diverse datasets in a single predictive model, G2PDeep helps uncover the biological mechanisms that drive disease susceptibility and treatment response. Likewise, when applied to agribiotech datasets, the platform can support plant breeders in developing predictive models for key phenotypic traits, enabling data-informed improvements in crop performance and resilience.
“This collaboration demonstrates the power of academic partnerships in accelerating breakthroughs that can transform patient care,” said Trupti Joshi, M.B.B.S., Ph.D., professor and senior associate dean for informatics and population analytics at the Marshall University Joan C. Edwards School of Medicine and corresponding author on the study. “G2PDeep equips researchers with an accessible, sophisticated tool to better understand and address the health challenges facing our communities.”
“Our collaboration with Dr. Joshi’s lab has been both long-term and productive,” said Dong Xu, Ph.D., bioinformatics professor in the department of electrical engineering and computer science at the University of Missouri-Columbia. “We focus on developing bioinformatics platforms, not just algorithms, that can be widely adopted by the research community. G2PDeep demonstrates how advanced AI methods can be translated into practical tools with broad scientific impact."
G2PDeep is available to researchers, clinicians and public health professionals seeking to leverage multiomics data to drive discovery and innovation. For more information, please visit https://g2pdeep.org . To access publication in its entirety, please visit doi.org/10.3390/biom15121673 .
Biomolecules
Data/statistical analysis
Not applicable
G2PDeep-v2: A Web-Based Deep-Learning Framework for Phenotype Prediction and Biomarker Discovery for All Organisms Using Multi-Omics Data
1-Dec-2025