A Crucial Angiogenesis-Associated Gene MEOX2 Could Be a Promising Biomarker Candidate for Breast Cancer

Inference of differential gene regulatory networks using boosted differential trees

Summary

Diseases can be caused by molecular perturbations that induce specific changes in regulatory interactions and their coordinated expression, also referred to as network rewiring. However, the detection of complex changes in regulatory connections remains a challenging task and would benefit from the development of novel nonparametric approaches. We develop a new ensemble method called BoostDiff (boosted differential regression trees) to infer a differential network discriminating between two conditions. BoostDiff builds an adaptively boosted (AdaBoost) ensemble of differential trees with respect to a target condition. To build the differential trees, we propose differential variance improvement as a novel splitting criterion. Variable importance measures derived from the resulting models are used to reflect changes in gene expression predictability and to build the output differential networks. BoostDiff outperforms existing differential network methods on simulated data evaluated in four different complexity settings. We then demonstrate the power of our approach when applied to real transcriptomics data in COVID-19, Crohn's disease, breast cancer, prostate adenocarcinoma, and stress response in Bacillus subtilis. BoostDiff identifies context-specific networks that are enriched with genes of known disease-relevant pathways and complements standard differential expression analyses.

Availability and implementation

BoostDiff is available at https://github.com/scibiome/boostdiff_inference.

Low expression of MEOX2 is associated with poor survival in patients with breast cancer

Aim: To investigate associations of MEOX2 expression with clinicopathological features and survival of breast cancer patients. Materials & methods: We used a breast cancer tissue microarray for immunohistochemistry. Associations between MEOX2 expression and clinicopathological features were analyzed using the χ-square test. Survival analysis was determined using a Kaplan-Meier curve. Multivariate Cox regression was used to determine associations of MEOX2 expression with overall survival. Results: We found that 74.1% of patients (100/135) had expression of MEOX2 at varying levels. MEOX2 was associated with histological grade and negatively correlated with Ki67 expression. Lower MEOX2 expression was significantly associated with decreased overall survival (p = 0.0011). Conclusion: MEOX2 expression could be a novel diagnostic and prognostic biomarker of breast cancer.