Bias in, bias out–AlphaFold-Multimer and the structural complexity of protein interfaces

JM Strom, K Luck - Current Opinion in Structural Biology, 2025 - Elsevier
Highlights•Protein interfaces involving disordered protein regions are underrepresented in
training data for structure prediction models.•Benchmarking of structure prediction models …

[HTML][HTML] SpatialPPIv2: Enhancing protein–protein interaction prediction through graph neural networks with protein language models

W Hu, M Ohue - Computational and Structural Biotechnology Journal, 2025 - Elsevier
Protein–protein interactions (PPIs) are fundamental to cellular functions, and accurately
predicting such interactions is crucial for understanding biological mechanisms and …

[HTML][HTML] Unified Sampling and Ranking for Protein Docking with DFMDock

LS Chu, S Sarma, JJ Gray - bioRxiv, 2024 - pmc.ncbi.nlm.nih.gov
Diffusion models have shown promise in addressing the protein docking problem.
Traditionally, these models are used solely for sampling docked poses, with a separate …

Have protein-ligand co-folding methods moved beyond memorisation?

P Škrinjar, J Eberhardt, J Durairaj, T Schwede - bioRxiv, 2025 - biorxiv.org
Deep learning has driven major breakthroughs in protein structure prediction, however the
next critical advance is accurately predicting how proteins interact with other molecules …

SpatialPPI 2.0: Enhancing Protein-Protein Interaction Prediction through Inter-Residue Analysis in Graph Attention Networks

W Hu, M Ohue - bioRxiv, 2024 - biorxiv.org
Protein-protein interactions (PPIs) are fundamental to cellular functions, and accurate
prediction of these interactions is crucial to understanding biological mechanisms and …