Back

Global Pan-cancer serum miRNA classifier across 13 cancer types: Analysis of 46,349 clinical samples

Krishnamoorthy, P.; Parthasarathy, M.; Das, N.; S Raj, A.; Kumar, A.; Gupta, V.; Das, S.; Kumar, H.

2025-02-10 oncology
10.1101/2025.02.07.25321821 medRxiv
Show abstract

ABSTRACTLiquid biopsy offers the minimally-invasive way of early cancer diagnosis. MicroRNAs (miRNAs) are small non-coding RNAs that show promising diagnostic potential due to their stability and their dysregulation upon different physiological conditions. However, existing cancer classifiers often rely on cohort-based comparisons, limiting their clinical utility. Extensive analyses in this study present a pan-cancer miRNA-based single-sample classifier, trained on 16,190 samples, tested across 9 independent datasets, and further validated on 8 distinct disease cohorts. The classifier leverages miRNA expression signatures to classify cancer and non_cancer samples including healthy, other diseases with high sensitivity and specificity, enabling personalized predictions. The classifier identifies cancer by evaluating the relative expression patterns of specific miRNAs, capturing neoplasm-specific dysregulation patterns independent of cohort effects. This study highlights the potential of miRNAs in robust cancer classification, offering a minimally invasive, scalable, and clinically adaptable miRNA serum resource for early cancer detection across diverse populations and malignancies.

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.