DISCIPLE (Data analytIcS intelligenCe In PharmacoLogical sciEnces) – Research Group on Data Analytics Intelligence in Pharmacological Sciences
Publication List
[1] A.-M. Cucos, Z. Gáll, and L. B. Iantovics. “Multi-Label Classification of Adverse Drug Reactions Using a Hybrid Approach Integrating Support Vector Machine, Random Forest and Extreme Gradient Boosting.”, Pharmaceuticals, 2026.
[2] R. B. Marqas, Z. Simó, A. Mousa, F. Özyurt, and L. B. Iantovics, “Advancing drug–drug interaction prediction with biomimetic improvements: Leveraging the latest artificial intelligence techniques to guide researchers in the field,” Biomimetics, vol. 11, no. 1, Art. no. 39, 2026.
[3] A. Biró, G. Kolumbán, and L. B. Iantovics, “Risk-calibrated polypharmacy graph learning for uncertainty-aware drug combination optimization,” in Proc. 30th IEEE Int. Conf. Intelligent Engineering Systems (INES), 2026, pp. 53–58.
[4] I.-F. Gheorghita, V.-I. Bocanet, and L. B. Iantovics, “Fine-tuning BiomedBERT with LoRA and pseudo-labeling for accurate drug–drug interactions classification,” Applied Sciences, vol. 15, no. 15, Art. no. 8653, 2025.
[5] F.-I. Gheorghita, V.-I. Bocanet, and L. B. Iantovics, “Machine learning-based drug-drug interaction prediction: A critical review of models, limitations, and data challenges,” Frontiers in Pharmacology, vol. 16, Art. no. 1632775, 2025.
[6] F.-I. Gheorghita, V.-I. Bocanet, and L. B. Iantovics, “Graph–vector hybrid model for predicting synergistic drug-drug interactions toward clinical decision support integration,” in Proc. 29th Int. Conf. Knowledge-Based and Intelligent Information & Engineering Systems (KES 2025), Procedia Computer Science, vol. 270, pp. 4563–4572, 2025.
[7] A.-M. Cucos and L. B. Iantovics, “Machine learning-based adverse drug reaction prediction: Model comparisons, feature optimization and generative AI challenges,” in Proc. 29th Int. Conf. Knowledge-Based and Intelligent Information & Engineering Systems (KES 2025), Procedia Computer Science, vol. 270, pp. 1139–1148, 2025.
[8] F.-I. Gheorghita, D.-O. Pop, and L. B. Iantovics, “Molecular feature-based prediction of drug-drug interactions using graph neural networks,” in Proc. 18th Int. Conf. Interdisciplinarity in Engineering (Inter-Eng 2024), pp. 23–40, 2024.
Members
Prof. dr. abil. László Barna Iantovics – Scientific leader
Research focus: Data analytics intelligence in health sciences.
Attila Biro – Scientific responsable + senior researcher
Research focus: AI-enabled digital transformation and MedTech innovation at the intersection of computer science, clinical applications, and applied mathematics. He conducts advanced postdoctoral research at UMFST G.E. Palade of Târgu Mureș, developing data-driven architectures and mathematical modeling techniques to engineer AI solutions that deliver measurable, real-world impact across international healthcare markets.
Domains of Interest
- Digital Health
- Applied Mathematics & Data Science
- Executive AI Leadership
Ana-Maria Cucos – PhD candidate · Researcher
Research focus: Adverse Drug Reaction prediction using molecular fingerprints and descriptors with machine learning methods, including Random Forest, Gradient Boosted Trees, and neural network architectures.
Domains of interest
- Pharmaceutical AI
- Cheminformatics
- Machine Learning
Asist. Zsuzsa Simó – PhD candidate · Researcher
Research focus: Interpretable machine learning for imbalanced datasets, with applications including hyperparameter tuning for DDI prediction and adaptive kernel techniques.
Domains of interest
- Interpretable ML
- Healthcare data
- DDI prediction
Flaviu-Ioan Gheorghita – PhD candidate · Researcher
Research focus. Drug-drug interaction prediction using BiomedBERT with LoRA fine-tuning, graph neural networks, and graph-vector hybrid models for clinical decision support integration.
Recent publications. Applied Sciences (2025), Frontiers in Pharmacology (2025).
Domains of interest
- Pharmaceutical AI
- Graph Neural Networks
- Clinical Decision Support