SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization.

SumGNN: multi-typed drug interaction prediction via efficient knowledge graph summarization.
复制标题

DOI:
10.1093/bioinformatics/btab207
复制
发表时间:
2021-09-29
期刊:
Bioinformatics (Oxford, England)
影响因子:
--
通讯作者:
--
中科院分区:
其他
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

由于药物相互作用 (DDI) 数据集和大型生物医学知识图 (KG) 的可用性不断增加,使用机器学习模型准确检测不良 DDI 成为可能。然而,如何有效利用大型且嘈杂的生物医学 KG 进行 DDI 检测,在很大程度上仍然是一个悬而未决的问题。由于 KG 的庞大规模和噪声量,直接将 KG 与其他较小但较高质量的数据(例如实验数据)集成通常不太有利。大多数现有方法完全忽略知识图谱。有些人尝试通过图神经网络直接将知识图谱与其他数据集成,但成效有限。此外,以前的大多数工作都集中在二元 DDI 预测上,而多类型 DDI 药理作用预测更有意义,但任务更艰巨。为了填补这一空白,我们提出了一种新方法 SumGNN:知识摘要图神经网络,该方法由一个子图提取模块实现,该模块可以有效地锚定 KG 中的相关子图,一个基于自注意力的子图摘要方案,用于在子图中生成推理路径,以及一个多通道知识和数据集成模块,该模块利用大量外部生物医学知识来显着改进多类型 DDI 预测。 SumGNN 的性能优于最佳基线高达 5.54%,并且在低数据关系类型中性能增益尤其显着。此外,SumGNN 通过为每个预测生成的推理路径提供可解释的预测。该代码可在补充材料中找到。 补充数据可在生物信息学在线获取。
Thanks to the increasing availability of drug–drug interactions (DDI) datasets and large biomedical knowledge graphs (KGs), accurate detection of adverse DDI using machine learning models becomes possible. However, it remains largely an open problem how to effectively utilize large and noisy biomedical KG for DDI detection. Due to its sheer size and amount of noise in KGs, it is often less beneficial to directly integrate KGs with other smaller but higher quality data (e.g. experimental data). Most of existing approaches ignore KGs altogether. Some tries to directly integrate KGs with other data via graph neural networks with limited success. Furthermore most previous works focus on binary DDI prediction whereas the multi-typed DDI pharmacological effect prediction is more meaningful but harder task. To fill the gaps, we propose a new method SumGNN: knowledge summarization graph neural network, which is enabled by a subgraph extraction module that can efficiently anchor on relevant subgraphs from a KG, a self-attention based subgraph summarization scheme to generate reasoning path within the subgraph, and a multi-channel knowledge and data integration module that utilizes massive external biomedical knowledge for significantly improved multi-typed DDI predictions. SumGNN outperforms the best baseline by up to 5.54%, and performance gain is particularly significant in low data relation types. In addition, SumGNN provides interpretable prediction via the generated reasoning paths for each prediction. The code is available in Supplementary Material. Supplementary data are available at Bioinformatics online.
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: 10.1073/pnas.2025581118
发表时间: 2021-05-11
影响因子: 11.1
作者:
Morselli Gysi D;do Valle Í;Zitnik M;Ameli A;Gan X;Varol O;Ghiassian SD;Patten JJ;Davey RA;Loscalzo J;Barabási AL
通讯作者: Barabási AL
DOI: 10.1186/s12859-019-3284-5
发表时间: 2019-12-18
期刊: BMC BIOINFORMATICS
影响因子: 3
作者:
Celebi, Remzi;Uyar, Huseyin;Dumontier, Michel
通讯作者: Dumontier, Michel
DOI: 10.1021/ci100050t
发表时间: 2010-05-01
影响因子: 5.6
作者:
Rogers, David;Hahn, Mathew
通讯作者: Hahn, Mathew
DOI: 10.1038/s41598-017-05778-z
发表时间: 2017-07-20
期刊: Scientific reports
影响因子: 4.6
作者:
Rotmensch M;Halpern Y;Tlimat A;Horng S;Sontag D
通讯作者: Sontag D