ContrastQA: A Label-guided Graph Contrastive Learning-based approach for protein complex structure quality assessment
Despite recent progress, the Estimation of Model Accuracy (EMA) for protein complexes remains less advanced compared to that for protein monomers. A key challenge lies in effectively integrating both interface-specific and global structural information to accurately assess the quality of protein complexes. Here, we introduce ContrastQA, the first EMA framework for protein complexes that incorporates the proposed label-guided graph contrastive learning based on interface quality. By integrating a geometric graph neural network to model global structural features, ContrastQA effectively captures both local (interface-level) and global (structure-level) information for accurate model quality estimation. ContrastQA achieved ranking losses of 0.123 and 0.116 on the TMscore and GDT-TS metrics on the CASP16 dataset, which are 0.015 (10.9%) and 0.012 (8.7%) lower than the second-best EMA method with ranking losses of 0.138 and 0.128. Furthermore, for the more challenging CASP16 hard targets, our method achieved a TMscore ranking loss of 0.131, which is 0.023 (14.9%) lower than that of the second-best EMA method with a ranking loss of 0.154. Our study demonstrates the strong effectiveness of the label-guided graph contrastive learning module. These findings suggest that our graph contrastive learning framework serves as a valuable pre-training strategy for learning protein structure representations. The source code is available at https://github.com/Cao-Labs/ContrastQA. Significance StatementHigh-quality proteins generated by high-precision structural prediction methods for protein complexes helping biologists prioritize models for drug discovery and understanding disease mechanisms. Recent advances in predicting protein complex structures (like AlphaFold3) still struggle to match experimental precision. A critical bottleneck lies in accurately estimating the quality of predicted models-known as Estimation of Model Accuracy (EMA). Here, we introduce ContrastQA, implementing label-guided graph contrastive learning framework to explore the generalization of high-quality proteins. Our method demonstrates outstanding performance, provides an effective solution for assessing the structural quality of protein complexes.