Back

D-CoMEx: A Unified Approach to Identify Phenotype-specific miRNA Biomarkers Related to Diseases

Kakati, T.; Bhattacharyya, D. K.; Kalita, J. K.

2025-06-16 bioinformatics
10.1101/2025.06.10.658948 bioRxiv
Show abstract

Profiling of miRNAs is important to understand how they regulate biological pathways and contribute to diseases. With current technological advancements leading to capture of voluminous biological data, it is interesting and challenging to explore new methods that can discover disease-data associations and provide better insights into the underlying mechanisms of diseases. Such understanding may also help prevent severe pathogenesis of the disease and contribute to knowledge required for effective drug development. This paper proposes a unified approach, D-CoMEx, to mine miRNA biomarkers from dysregulated pathways associated with Parkinsons disease (PD) and Breast Cancer (BC). The approach integrates a co-expression network (CEN) module extraction technique with a differential analysis method to capture interactions between miRNAs and dysregulated pathways. Our method identifies more statistically and biologically significant dysregulated pathways compared to DCGL, MODA, and DiffCoEx. We present three evidence-backed recommendations supporting strong associations between miRNAs and dysregulated pathways, demonstrating that D-CoMEx extracts biologically relevant miRNA biomarkers linked to disease progression.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.