This repository contains code for the manuscript: (https://doi.org/10.64898/2026.06.23.734064)
"Stability-driven multi-omics integration for reproducible latent structure in thyroid cancer"
Abstract
High-dimensional multi-omics data integration offers novel opportunities to characterize complex biological systems. Even though sampling variability frequently compromises findings, particularly in small cohorts, the reproducibility and generalizability of the derived latent structures are insufficiently evaluated. We propose a Stability-driven framework for multi-omics integration that combines sparse generalized canonical correlation analysis with repeated cross-validation, out-of-sample projection, and systematic evaluation of both component-level and feature-level stability. We apply this framework to untargeted metabolomic and Olink targeted inflammation proteomic profiles in a thyroid cancer case–control cohort (n = 162). Our Stability-driven integration identified reproducible metabolomic and proteomic latent components that showed consistent out-of-sample disease associations and tracked temporally structured changes relative to time to diagnosis. The proposed framework provides a generalizable strategy for identifying reproducible latent structures that improve the robustness of biological inference in multi-omics studies.
This project implements a stability-driven framework for multi-omics data integration using sparse generalized canonical correlation analysis (SGCCA), combined with:
- repeated cross-validation
- Integration of metabolomics and proteomics data using a repeated CV framework
- out-of-sample (OOF) inference
- Separation of model fitting and inference using cross-fitted latent scores
- component-level stability assessment
- Stability evaluation of latent components derived from SGCCA
- feature-level stability evaluation
- Stability evaluation of feature contributions
Each folder contains the codes for one analysis block of the paper:
1_sgcca_repeat_CV:2_component_stability_evaluation:3_oos_association_evaluation:4_feature_stability_evaluation:
data: dataset simulated for metabolomics and proteomics
The original omics data used in this study are not publicly available due to participant privacy restrictions, but may be accessed upon reasonable request through the BioMe Biobank.
Code is released under the MIT License.
To cite the work and for a more complete description of the methods and analyses: https://doi.org/10.64898/2026.06.23.734064