A knowledge graph representation learning approach to predict novel kinase-substrate interactions.

A knowledge graph representation learning approach to predict novel kinase-substrate interactions.
复制标题

DOI:
10.1039/d1mo00521a
复制
发表时间:
2022-10-31
期刊:
影响因子:
2.9
通讯作者:
--
中科院分区:
生物学4区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

人类蛋白质组包含相互作用的激酶和底物的巨大网络。尽管一些激酶已被证明是非常有用的治疗靶点,但大多数仍然没有得到充分研究。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新的相互作用的合作伙伴未充分研究的激酶。我们的方法使用了一个磷酸化蛋白质组学知识图,该知识图是通过整合来自iPTMnet、蛋白质本体、基因本体和BioKG的数据构建的。在这个知识图中的激酶和底物的表示是通过在与修改的SkipGram或CBOW模型耦合的三元组上执行定向随机游走来学习的。然后,这些表示被用作监督分类模型的输入,以预测未充分研究的激酶的新的相互作用。我们还提出了预测相互作用的预测后分析和磷酸蛋白质组学知识图的消融研究,以深入了解未充分研究的激酶的生物学。在这项工作中,我们提出了一种方法来预测新的相互作用的合作伙伴研究不足的激酶。我们的方法包括构建一个生物医学知识图,然后使用三重步行算法从这个知识图中学习。
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. In this work we present an approach to predict novel interaction partners for understudied kinases. Our approach involves constructing a biomedical knowledge graph and then using a triple walking algorithm to learn from this knowledge graph.
DOI: 10.1145/2939672.2939754
发表时间: 2016-08
期刊: KDD : proceedings. International Conference on Knowledge Discovery & Data Mining
影响因子: --
作者:
Grover A;Leskovec J
通讯作者: Leskovec J
DOI: 10.1093/nar/gkg584
发表时间: 2003-07-01
影响因子: 14.9
作者:
Obenauer, JC;Cantley, LC;Yaffe, MB
通讯作者: Yaffe, MB
DOI: 10.1093/nar/gkw1099
发表时间: 2017-01-04
影响因子: 14.9
作者:
The UniProt Consortium
通讯作者: The UniProt Consortium
DOI: 10.1007/978-1-4939-6783-4_3
发表时间: 2017-01-01
期刊: PROTEIN BIOINFORMATICS: FROM PROTEIN MODIFICATIONS AND NETWORKS TO PROTEOMICS
影响因子: --
作者:
Arighi, Cecilia N.;Drabkin, Harold;Natale, Darren A.
通讯作者: Natale, Darren A.
DOI: 10.1093/nar/gkw1075
发表时间: 2017-01-04
影响因子: 14.9
作者:
Natale DA;Arighi CN;Blake JA;Bona J;Chen C;Chen SC;Christie KR;Cowart J;D'Eustachio P;Diehl AD;Drabkin HJ;Duncan WD;Huang H;Ren J;Ross K;Ruttenberg A;Shamovsky V;Smith B;Wang Q;Zhang J;El-Sayed A;Wu CH
通讯作者: Wu CH