Project Abstract

Protein structure prediction has been a formidable task in computational biology with only large leaps in research in the past decade. This research endeavors to significantly impact the field by offering improved solutions for predicting protein structures with greater precision and efficiency. The unique proposition lies in the adaptation and refinement of the Eigenfold Diffusion model to specialise protein structure prediction compared to general purpose models. Employing a reduced focused dataset and iterative hyper-parameter tuning methods, the outcomes of this research deduced significant improvements in specialised protein prediction with competitve results.

Keywords: Machine learning, Diffusion Models, Protein Structure Prediction

 Conference Details

Session: Poster Session B at Poster Stand 94

Location: Sir Stanley Clarke Auditorium at Wednesday 8th 09:00 – 12:30

Markers: Yuanbo Wu, Mukesh Tiwary

Course: MSci Computer Science, 3rd Year

Future Plans: I’m continuing studies