Hüseyin Tunç

The paper introduces MolCodon, a codon-based molecular language that provides high-fidelity, interpretable, and alignment-compatible sequence representations for small molecules, outperforming existing methods in various tasks.

DRGSCROLL improves docking simulations by optimizing ligand pose and receptor side-chain flexibility using a genetic algorithm, showing better performance in energy and docking scores compared to existing methods.

This study uses NeuralPlexer to identify FDA-approved BCL2 inhibitors through in silico analysis, finding candidates like Lathyrol and Fadrozole with potent inhibitory interactions.

This paper develops DIF-based MD-ANN models to predict HIV-1 RTI resistance using genotypic data, showing improved performance over IF-based models in single-drug benchmarks.