PhD Scientific Days 2026

Poster Session 3.H - Pharmaceutical Sciences and Health Technologies

miRNAtarget: a Network-based Solution and Benchmarking Framework for Predicting Transcriptome-wide Concerted Regulatory Effects of microRNAs

Előadó neve

Váczy-Földi, Máté, MSc

Neptune code

XA6S0Q

Előadó munkahelye

Department of Pharmacology and Pharmacotherapy, Semmelweis University

Előadó telefonszáma

+36 20 504 7462

Előadó e-mail címe

vaczy.foldi.mate@semmelweis.hu

Az előadás címe

miRNAtarget: a Network-based Solution and Benchmarking Framework for Predicting Transcriptome-wide Concerted Regulatory Effects of microRNAs

Szerző(k) neve és munkahelye

Máté Váczy-Földi^1,2,3, Bettina Benczik^1,2,3, Zsolt Papp^1,2, Olivér Balogh^1,2, Barnabás Váradi^1,2, Dóra Bihary^1,2, Zoltán Bereczki^1,2, András Makkos^1,2,3, Anikó Görbe^1,2,3,4, Péter Bencsik^3,4, Péter Ferdinandy^1,2,3, Bence Ágg^1,2,3

1: Department of Pharmacology and Pharmacotherapy, Semmelweis University, Hungary
2: Center for Pharmacology and Drug Research & Development, Semmelweis University, Hungary
3: Pharmahungary Group, Hungary
4: Department of Pharmacology and Pharmacotherapy, University of Szeged, Hungary

Bemutatás módja

Poszter

Szekció

Poster Session 3.H - Pharmaceutical Sciences and Health Technologies

Language of the presentation

English

Preferred session

Pharmaceutical Sciences and Health Technologies

Összefoglaló szövege

Introduction
The development of small RNA therapeutics has grown explosively over the past decade, which necessitates the accurate prediction of their effects to ensure therapeutic efficacy and avoid off-target toxicity. This prediction task poses an even greater challenge for the combinatorial effects of multiple microRNAs.
Aims
To address this problem, we aimed to create a robust evaluation framework and a comprehensive benchmarking dataset for prediction tools, and to demonstrate their applicability through a comparative performance analysis of our network topology-based model, miRNAtarget™.
Methods
A ground truth benchmark dataset of differential gene expression profiles was constructed by applying a uniform bioinformatics pipeline to paired small RNA- and bulk mRNA-sequencing data from five human and mouse studies in the Gene Expression Omnibus (GEO). This dataset was then utilized within a rigorous validation framework to perform a comparative performance analysis. The predictive accuracy of the complete, multi-source miRNAtarget™ model was evaluated against its own single-source variants, which rely exclusively on individual databases (TargetScan, miRDB, miRTarBase), and a random classifier.
Result
Our analysis revealed that predictive performance of miRNAtarget is dependent on the evaluation metric. When evaluating by the magnitude of predicted effect (top ten percent by absolute value of change), the single-source miRNAtarget variant relying on miRDB was the top performer (6/17 comparisons). However, when evaluating by directional accuracy (top ten percent of most up- and downregulated predictions), the TargetScan-based variant was better (8/17 comparisons).
Conclusion
We have defined the task of predicting the combinatorial transcriptomic effects of microRNAs and provided the first unified framework and public dataset to address it. This work establishes a necessary benchmark for the rigorous and reproducible comparison of future prediction algorithms.
Funding
Project no. RRF-2.3.1-21-2022-00003 has been implemented with the support provided by the European Union. Supported by the 2024-2.1.2-EKÖP-KDP New National Excellence Program of the Ministry for Culture and Innovation from the source of the National Research, Development and Innovation Fund. This study has been supported by a Semmelweis 250+ Excellence Fellowship.

University

Semmelweis University

Supervisor

Dr. Bence Ágg, MD PhD

Publication of my abstract

I do not give consent to the publication of my abstract on the website of the congress.

phd.section.field

in doctoral studies before complex exam (PhD)

Kind

Szabad

Status

elfogadva

Accepted presentation method

poszter

Előadás fájl jóváhagyás

nem rendelkezett róla

Előadó

9071

Start

13:42

End

13:45