Li C. Xue

The paper introduces a fast computational docking protocol for TCRpMHC-I complexes, achieving faster modeling and better model quality than existing tools.

IMMREP25 evaluates TCR:pMHC binding prediction for unseen peptides, showing improved performance with structural modeling but still below random guessing.

MHC-Diff predicts peptide-MHC structures with high accuracy and speed using a diffusion model, outperforming existing methods.

The paper updates PANDORA to predict bidirectional peptide conformations for MHC class II, achieving low RMSD values for reversed-bound peptides.

SwiftMHC rapidly predicts peptide-MHC binding and generates 3D structures, outperforming sequence-based methods in speed while maintaining accuracy.

PANDORA v2.0 benchmarks peptide-MHC II modeling software and improves its performance and usability for generating 3D pMHC-II structures.

This paper improves MHC-I binding peptide prediction generalizability using geometric deep learning, outperforming sequence-based methods without binding affinity data.

The paper introduces vanGOGH, a geometric deep learning method for protein structural alignment that matches state-of-the-art performance without training on natural homolog pairs.

MetaScore improves traditional protein-protein docking scoring functions using machine learning, outperforming existing methods in success and hit rates.

DeepRank-GNN uses graph neural networks to score protein-protein docking models, outperforming existing methods and improving speed and storage efficiency.

PANDORA is a fast pMHC structure modelling pipeline that uses anchor restraints to generate accurate models with high success rate and speed.

DeepRank uses 3D CNNs to mine protein-protein interfaces, achieving competitive or better performance in classification and docking model ranking.

The paper introduces iScore, a software tool that ranks protein-protein docking models using a random walk graph kernel and support vector machines, with MPI and GPU support for efficient computation.

The paper evaluates HADDOCK's performance in CAPRI rounds 38-45, showing it produces acceptable or better models for most targets using data-driven strategies.

iScore improves protein-protein docking model scoring by combining energy terms, graph representation, and evolutionary conservation, achieving top performance on benchmark datasets.

iSEE predicts binding affinity changes upon mutations using a random forest model with 31 features, achieving high performance on diverse datasets.