Research
Design. Make. Test. Learn.
I build integrated discovery workflows that connect AI and machine learning, computational molecular design, peptide chemistry, and experimental evaluation.
Discovery pathway
A continuous experimental loop
Each stage sharpens the next question. Select a stage to see its role in the workflow.
Algorithms and molecular evidence help define testable chemical possibilities.
Orbitide antimalarials
Malaria continues to demand therapeutic candidates with new chemical structures and mechanisms. My doctoral research investigates orbitides, head-to-tail cyclic peptides that provide a compact framework for systematic medicinal-chemistry optimization.
I synthesize and evaluate orbitides to determine how amino-acid sequence, stereochemistry, aromatic substitution, ring size, and backbone modification influence antiplasmodial activity. The program also examines mammalian-cell selectivity, plasma and protease stability, and preferred solution conformations.
Core questions
Which structural features govern activity against drug-resistant Plasmodium falciparum? Can conformational control improve potency, selectivity, and stability? Which analogues justify broader strain profiling and mechanistic investigation?
Computational design
Computation is most valuable when it sharpens experimental decisions. I integrate artificial intelligence and machine learning with molecular docking, virtual screening, structure prediction, conformational sampling, and molecular dynamics to prioritize molecules, interpret observations, and design the next experiment.
My toolkit includes AI-enabled peptide-design workflows, Glide, AutoDock Vina, MOE, GROMACS, Desmond, MODELLER, PyMOL, VMD, and Python-based automation. The platform spans peptides, small molecules, protein-ligand interactions, and protein-protein interfaces.