Department of Pharmacological Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, United States of America.
Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, United States of America.
PLoS Comput Biol. 2024 Jul 24;20(7):e1012302. doi: 10.1371/journal.pcbi.1012302. eCollection 2024 Jul.
Protein kinase function and interactions with drugs are controlled in part by the movement of the DFG and ɑC-Helix motifs that are related to the catalytic activity of the kinase. Small molecule ligands elicit therapeutic effects with distinct selectivity profiles and residence times that often depend on the active or inactive kinase conformation(s) they bind. Modern AI-based structural modeling methods have the potential to expand upon the limited availability of experimentally determined kinase structures in inactive states. Here, we first explored the conformational space of kinases in the PDB and models generated by AlphaFold2 (AF2) and ESMFold, two prominent AI-based protein structure prediction methods. Our investigation of AF2's ability to explore the conformational diversity of the kinome at various multiple sequence alignment (MSA) depths showed a bias within the predicted structures of kinases in DFG-in conformations, particularly those controlled by the DFG motif, based on their overabundance in the PDB. We demonstrate that predicting kinase structures using AF2 at lower MSA depths explored these alternative conformations more extensively, including identifying previously unobserved conformations for 398 kinases. Ligand enrichment analyses for 23 kinases showed that, on average, docked models distinguished between active molecules and decoys better than random (average AUC (avgAUC) of 64.58), but select models perform well (e.g., avgAUCs for PTK2 and JAK2 were 79.28 and 80.16, respectively). Further analysis explained the ligand enrichment discrepancy between low- and high-performing kinase models as binding site occlusions that would preclude docking. The overall results of our analyses suggested that, although AF2 explored previously uncharted regions of the kinase conformational space and select models exhibited enrichment scores suitable for rational drug discovery, rigorous refinement of AF2 models is likely still necessary for drug discovery campaigns.
蛋白激酶的功能和与药物的相互作用部分受到 DFG 和 αC-螺旋基序运动的控制，这些基序与激酶的催化活性有关。小分子配体通过独特的选择性谱和停留时间产生治疗效果，这通常取决于它们结合的激酶的活性或非活性构象。现代基于人工智能的结构建模方法有可能扩展实验确定的激酶在非活性状态下的结构的有限可用性。在这里，我们首先探索了 PDB 中激酶的构象空间以及由两个知名的基于人工智能的蛋白质结构预测方法 AlphaFold2 (AF2) 和 ESMFold 生成的模型。我们对 AF2 探索不同多重序列比对 (MSA) 深度下激酶构象多样性的能力的研究表明，在预测的 DFG-in 构象激酶结构中存在偏见，特别是那些受 DFG 基序控制的激酶结构，这是基于它们在 PDB 中的丰富度。我们证明，使用 AF2 在较低 MSA 深度预测激酶结构可以更广泛地探索这些替代构象，包括为 398 种激酶确定以前未观察到的构象。对 23 种激酶的配体富集分析表明，平均而言，对接模型比随机模型更好地区分活性分子和诱饵（平均 AUC (avgAUC) 为 64.58），但选择模型表现良好（例如，PTK2 和 JAK2 的 avgAUC 分别为 79.28 和 80.16）。进一步的分析解释了低性能和高性能激酶模型之间的配体富集差异，因为结合位点的闭塞会阻止对接。我们的分析结果表明，尽管 AF2 探索了激酶构象空间的以前未知区域，并且选择的模型表现出适合合理药物发现的富集分数，但对于药物发现活动来说，AF2 模型的严格细化可能仍然是必要的。
