🎓 Thesis Defense Completed
Undergraduate Thesis DefenseThesis Defense 🎉
I successfully defended my undergraduate thesis on March 18, 2025.
Extended Abstract
ResLysEmbed: A ResNet-Based Framework for Succinylated Lysine Residue Prediction Using Sequence and Language Model Embeddings
Souvik Ghosh, Department of CSE, BUET
1905073@ugrad.cse.buet.ac.bd
M Saifur Rahman, Department of CSE, BUET
mrahman@cse.buet.ac.bd
Abstract
Lysine (K) succinylation is a post-translational modification that can severely influence various cellular activities and has been linked to several diseases by recent research.
In this study, we propose a novel ResNet-based architecture, ResLysEmbed, for lysine succinylation site prediction that uses word embeddings along with per-residue embeddings from a protein language model. Furthermore, we applied SHAP (SHapley Additive exPlanations) analysis to interpret how much each residue within the 33-length window around the target site contributes to succinylation prediction.
