用蛋白结构和E3配体预测PROTAC降解能力，无需完整分子结构。
Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks
- 基于图神经网络，仅需蛋白结构与E3类型预测降解可行性。
- 在未见靶点上达0.646 AUROC，E3转移任务中达0.811 AUROC。
- 可推荐最优E3配体（Hit@3准确率74%），适合药物设计前期筛选。
蛋白水解靶向嵌合体（PROTACs）可选择性降解致病蛋白，但预测哪些靶点可被降解仍是关键瓶颈：现有计算方法需完整的PROTAC分子结构，而该信息在合成前不可得。我们提出DegradoMap，一种图神经网络，仅需蛋白结构与E3连接酶身份即可预测降解能力——这是靶点选择阶段唯一可用的最小信息。模型通过赖氨酸加权图池化结合每蛋白归一化编码生物物理先验，利用交叉注意力建模蛋白与E3的兼容性，并整合来自癌症依赖图谱（Cancer Dependency Map）的细胞背景信息。在PROTAC-8K基准数据集（3,101样本，155个靶点，10种E3配体）上，DegradoMap在未见靶点评估中达到0.646±0.124 AUROC（最佳种子：0.7449），在CRBN→VHL E3未见迁移任务中达0.811 AUROC，优于基线的GNN与机器学习方法。模型还以74%的命中率（Hit@3）推荐最优E3配体。两项发现具广泛意义：对于此标量预测任务，等变架构表现不如简单不变设计；而使用ESM-2嵌入仅在精细正则化下提升性能，直接融合会失败。DegradoMap为合成前提供降解性评估的计算指导；其校准良好的置信度分数（目标未见时ECE=0.029）使研究者可优先实验高置信度预测。然而，较高的种子方差（标准差0.124）与有限的E3覆盖范围要求集成多模型以实现可靠部署。
原文摘要 · Abstract (English)
Proteolysis-targeting chimeras (PROTACs) can selectively degrade disease-causing proteins, yet predicting which targets are amenable to degradation remains a critical bottleneck: existing computational methods require the complete PROTAC molecular structure, information unavailable before synthesis. We present DegradoMap, a graph neural network that predicts PROTAC-mediated degradability from protein structure and E3 ligase identity alone -- the minimal information available at the target selection stage. The model encodes biophysical priors through lysine-weighted graph pooling with per-protein normalization, models protein-E3 compatibility via cross-attention, and integrates cellular context from the Cancer Dependency Map. On the PROTAC-8K benchmark (3,101 samples, 155 targets, 10 E3 ligases), DegradoMap achieves 0.646+-0.124 AUROC on target-unseen evaluation (best seed: 0.7449) and 0.811 AUROC on CRBN->VHL E3-unseen transfer, outperforming GNN and machine learning baselines. The model additionally recommends optimal E3 ligases with 74% Hit@3 accuracy. Two findings carry broader implications: E(3)-equivariant architectures underperform the simpler invariant design for this scalar prediction task, and ESM-2 embeddings improve peak performance only with careful regularization -- naive integration fails. DegradoMap provides pre-synthesis computational guidance for degradability assessment; its well-calibrated confidence scores (ECE = 0.029, target-unseen) enable practitioners to prioritize high-confidence predictions for experimental follow-up. However, the high seed variance (std = 0.124) and limited E3 coverage require ensembling for reliable deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。