Exploration and practice of potential association prediction between diseases and drugs based on Swanson framework and bioinformatics

Abstract

Compared to traditional intermediate concepts, specific bioinformatics entities are more informative and higher directional. This study is based on the BITOLA system and combines bioinformatics methods to determine the intermediate concept which is key to improve efficiency of Literature-based Knowledge Discovery, proposes the concept of "Swanson framework + Bioinformatics", and conducts practice of Literature-based Knowledge Discovery to improve the scientificity and efficiency of research and development. Firstly, detected the disease related genes (i.e. differentially expressed genes) according to the results of gene functional analysis as intermediate concepts to carry out Literature-based Knowledge Discovery. Taking the disease "Autism Spectrum Disorder (ASD)" as an example, the potential "disease-drug" association was predicted, and the predicted drugs were verified from the perspective of bioinformatics. Two drugs potentially associated with ASD were found: Fish oil and Forskolin, which were closely related to ASD in bioinformatics analysis results and literature verification. The two "disease-drug" association results showed better scientificity. The BIOINF-ABC⁺ model improves the accuracy of calculations by 76% compared to using the BITOLA system alone. In addition, it also shows high accuracy and credibility in literature verification. The BIOINF-ABC⁺ model based on the "Swanson framework + Bioinformatics" has good practicality, applicability, and accuracy in conducting "disease-drug" association prediction in the biomedical field, and can be used for mining "disease-drug" relationships.

Keywords: Autism Spectrum disorders; BIOINF-ABC+ model; Differentially expressed genes; Drug Discovery; Literature-based Knowledge Discovery.

Fig. 1

Technical roadmap of the BIOINF-ABC⁺ Literature-based Discovery Model.

Fig. 2

Top 10 hub genes of Fish oil and Forskolin. Frequency refers to the occurrence frequency of the top 10 proteins ranked by the 12 algorithms of CytoHubba plug-in.

Fig. 3

Results of KEGG pathway enrichment analysis of Fish oil and Forskolin^–.Count refers to the number of genes associated with a certain pathway.Orange indicates the pathways that up-regulated differentially expressed genes involved, and blue indicates the pathways that down-regulated differentially expressed genes involved.

Fig. 4

Two signaling pathways that Fish oil and Forskolin involved^–.The red and green colors in the figure represent the positions of upregulated and downregulated differentially expressed genes, respectively. The darker the color, the stronger the expression.a The ovarian steroidogenesis pathway that Fish oil involved. b The MAPK signaling pathway that Forskolin involved.

Fig. 4

Two signaling pathways that Fish oil and Forskolin involved^–.The red and green colors in the figure represent the positions of upregulated and downregulated differentially expressed genes, respectively. The darker the color, the stronger the expression.a The ovarian steroidogenesis pathway that Fish oil involved. b The MAPK signaling pathway that Forskolin involved.