Research Focus

My research centers on developing robust machine learning models that can generalize across different domains in the chemical space, with applications in drug discovery and computational chemistry.

Core Research Areas

🧬 Machine Learning for Drug Discovery

  • Development of ML models for bioactivity prediction
  • PROTAC design and ternary complex prediction
  • Molecular property prediction and ADMET modeling

🎯 Out-of-Distribution Generalization

  • Evaluation of ML model robustness on OOD data
  • Domain adaptation in chemical space
  • Transfer learning for molecular properties

⚗️ Computational Chemistry & Cheminformatics

  • Molecular modeling and simulation
  • Chemical space analysis and visualization
  • Structure-activity relationship modeling

🔄 Causal Learning & Systems Biology

  • Causal inference in biological systems
  • Dynamical systems analysis
  • Computational neuroscience applications

Current Projects

PhD Thesis: Domain Generalization in Chemical Space

University of Vienna | Comp3D Lab

Developing machine learning models that maintain performance when applied to molecules significantly different from training data. This work addresses a critical challenge in computational drug discovery.

Key Collaborations

  • University of Vienna: Comp3D laboratory research
  • International Partners: Cross-institutional research projects
  • Industry Connections: Applied research in pharmaceutical contexts

Research Impact

Recent Publications

  • 2025: Evaluating ML Models for Molecular Property Prediction (ChemRxiv)
  • 2024: Quantifying Task Hardness for Transfer Learning (J. Chem. Inf. Model.)
  • 2023: Bayesian Optimization for Ternary Complex Prediction (AI Life Sciences)

Research Tools & Software

  • Development of computational tools for drug discovery
  • Open-source contributions to cheminformatics community
  • Machine learning pipelines for molecular analysis

Future Directions

Emerging Research Areas

  • Multimodal Learning: Combining molecular and biological data
  • Explainable AI: Interpretable models for drug discovery
  • Federated Learning: Collaborative learning across institutions
  • Quantum-Classical Hybrid Methods: Next-generation computational approaches

Long-term Vision

Bridging the gap between computational predictions and experimental validation in drug discovery through robust, generalizable machine learning approaches.


*For detailed publications, see Publications For talks and presentations, see Talks*