Comparing methods for drug–gene interaction prediction on the biomedical literature knowledge graph: performance versus explainability

BMC Bioinformatics

Research

Georgios Paliouras¹  Fotis Aisopos¹ 

[1] Institute of Informatics and Telecommunications, National Centre for Scientific Research Demokritos, Athens, Greece;

关键词: Drug–target interaction;    Knowledge graph;    Graph embeddings;    Deep learning;   

DOI  :  10.1186/s12859-023-05373-2

 received in 2023-04-07, accepted in 2023-06-01,  发布年份 2023

来源: Springer

【 摘 要 】

This paper applies different link prediction methods on a knowledge graph generated from biomedical literature, with the aim to compare their ability to identify unknown drug-gene interactions and explain their predictions. Identifying novel drug–target interactions is a crucial step in drug discovery and repurposing. One approach to this problem is to predict missing links between drug and gene nodes, in a graph that contains relevant biomedical knowledge. Such a knowledge graph can be extracted from biomedical literature, using text mining tools. In this work, we compare state-of-the-art graph embedding approaches and contextual path analysis on the interaction prediction task. The comparison reveals a trade-off between predictive accuracy and explainability of predictions. Focusing on explainability, we train a decision tree on model predictions and show how it can aid the understanding of the prediction process. We further test the methods on a drug repurposing task and validate the predicted interactions against external databases, with very encouraging results.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

Fig. 4

Fig. 1

Fig. 7

Fig. 4

Fig. 1

Fig. 4

Fig. 4

Fig. 6

Fig. 2

Fig. 5

Fig. 2

Fig. 2

Fig. 3

42492_2023_141_Article_IEq14.gif

Fig. 4

42492_2023_141_Article_IEq12.gif

Fig. 4

Fig. 2

Fig. 6

Fig. 1

Fig. 2

42492_2023_141_Article_IEq5.gif

Fig. 8

Fig. 3

Fig. 6

Fig. 4

Fig. 1

Fig. 2

Fig. 3

Fig. 2

Fig. 1

Fig. 6

Fig. 1

Fig. 5

Fig. 5

Fig. 1

40648_2023_255_Article_IEq12.gif

Fig. 10

Fig. 3

12936_2023_4510_Article_IEq8.gif

Fig. 3

Fig. 2

Fig. 10

Fig. 2

Fig. 5

Fig. 4

Fig. 1

Fig. 1

Fig. 4

12903_2023_3210_Article_IEq4.gif

Fig. 3

Fig. 11

Fig. 5

Fig. 3

Fig. 1

41239_2023_389_Article_IEq76.gif

13015_2023_227_Article_IEq341.gif

Fig. 5

Fig. 5

Fig. 1

Fig. 4