Reproduce “PGraphDTA: Improving Drug Target Interaction Prediction using Protein Language Models and Contact Maps” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Rakesh Bal, Yijia Xiao, Wei Wang
PGraphDTA replaces GraphDTA’s protein-sequence CNN with pretrained protein-language representations while retaining a graph representation of the drug. A second variant adds predicted protein contacts as structural context. On DAVIS, PGraphDTA with SeqVec achieves MSE 0.221 versus 0.271 for a reimplemented GraphDTA baseline. However, contact-map benefits are limited to some DAVIS variants and do not establish generalization or reduced costs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.