Institute of Molecular Biology (IMB) gGmbH, Mainz 55128, Germany.
3rd Medical Department, University Medical Center, Johannes Gutenberg University Mainz, Mainz 55131, Germany.
Bioinformatics. 2024 Aug 2;40(8). doi: 10.1093/bioinformatics/btae482.
While the release of AlphaFold (AF) represented a breakthrough for the prediction of protein complex structures, its sensitivity, especially when using full length protein sequences, still remains limited. Modeling success rates might increase if AF predictions were guided by likely interacting protein fragments. This approach requires available sets of highly confident protein-protein interface types. Computational resources, such as 3did, infer interacting globular domain types from observed contacts in protein structures. Assessing the accuracy of these predicted interface types is difficult because we lack hand-curated reference sets of verified domain-domain interface (DDI) types.
To improve protein complex modeling of DDIs by AF, we manually inspected 80 randomly selected DDI types from the 3did resource to generate a first reference set of DDI types. Identified cases of DDI type nonapproval (40%) primarily resulted from inaccurate Pfam domain matches, crystal contacts, and synthetic protein constructs. Using logistic regression, we predicted a subset of 2411 out of 5724 considered DDI types in 3did to be of high confidence, which we subsequently applied to 53 000 human-protein interactions to predict DDIs followed by AF modeling. We obtained highly confident AF models for 604 out of 1129 predicted DDIs. Of note, for 47% of them no confident AF structural model could be obtained using full length protein sequences.
Code is available at https://github.com/KatjaLuckLab/DDI_manuscript.
虽然 AlphaFold (AF) 的发布代表了蛋白质复合物结构预测的突破，但它的灵敏度，尤其是在使用全长蛋白质序列时，仍然有限。如果 AF 预测能够得到可能相互作用的蛋白质片段的指导，建模成功率可能会提高。这种方法需要可用的高度置信的蛋白质-蛋白质界面类型集。计算资源，如 3did，从蛋白质结构中的观察到的接触推断出相互作用的球状结构域类型。评估这些预测的界面类型的准确性是困难的，因为我们缺乏经过手工整理的已验证的域-域界面 (DDI) 类型的参考集。
为了通过 AF 改进 DDIs 的蛋白质复合物建模，我们手动检查了 3did 资源中随机选择的 80 个 DDI 类型，以生成 DDI 类型的第一个参考集。DDI 类型不被批准的情况（40%）主要是由于 Pfam 结构域匹配、晶体接触和合成蛋白质结构不准确造成的。使用逻辑回归，我们预测了 3did 中考虑的 5724 个 DDI 类型中的 2411 个子集具有高度置信度，随后我们将其应用于 53000 个人-蛋白质相互作用，以预测 DDIs，然后进行 AF 建模。我们对预测的 1129 个 DDIs 中的 604 个获得了高度置信的 AF 模型。值得注意的是，对于其中的 47%，使用全长蛋白质序列无法获得可靠的 AF 结构模型。
