University of Delaware, Newark, DE 590 Avenue 1743, Suite 147, Newark, DE, USA.
Georgetown University Medical Center, Washington DC, USA.
Mol Omics. 2022 Oct 31;18(9):853-864. doi: 10.1039/d1mo00521a.
The human proteome contains a vast network of interacting kinases and substrates. Even though some kinases have proven to be immensely useful as therapeutic targets, a majority are still understudied. In this work, we present a novel knowledge graph representation learning approach to predict novel interaction partners for understudied kinases. Our approach uses a phosphoproteomic knowledge graph constructed by integrating data from iPTMnet, protein ontology, gene ontology and BioKG. The representations of kinases and substrates in this knowledge graph are learned by performing directed random walks on triples coupled with a modified SkipGram or CBOW model. These representations are then used as an input to a supervised classification model to predict novel interactions for understudied kinases. We also present a post-predictive analysis of the predicted interactions and an ablation study of the phosphoproteomic knowledge graph to gain an insight into the biology of the understudied kinases.
人类蛋白质组包含一个庞大的相互作用激酶和底物网络。尽管一些激酶已被证明是非常有用的治疗靶点，但大多数激酶仍在研究中。在这项工作中，我们提出了一种新的知识图表示学习方法来预测研究较少的激酶的新相互作用伙伴。我们的方法使用了一个由 iPTMnet、蛋白质本体、基因本体和 BioKG 整合数据构建的磷酸化蛋白质组学知识图。通过在三元组上执行定向随机游走，并结合改进的 SkipGram 或 CBOW 模型来学习激酶和底物在这个知识图中的表示。然后，将这些表示作为输入到有监督的分类模型中，以预测研究较少的激酶的新相互作用。我们还对预测的相互作用进行了预测后分析，并对磷酸化蛋白质组学知识图进行了消融研究，以深入了解研究较少的激酶的生物学。
