IBDTransDB: a manually curated transcriptomic database for inflammatory bowel disease

Abstract

Inflammatory Bowel Disease (IBD) therapies are ineffective in at least 40% patients, and transcriptomic datasets have been widely used to reveal the pathogenesis and to identify the novel drug targets for these patients. Although public IBD transcriptomic datasets are available from many web-based tools/databases, due to the unstructured metadata and data description of these public datasets, most of these tools/databases do not allow querying datasets based on multiple keywords (e.g. colon and infliximab). Furthermore, few tools/databases can compare and integrate the datasets from the query results. To fill these gaps, we have developed IBDTransDB (https://abbviegrc.shinyapps.io/ibdtransdb/), a manually curated transcriptomic database for IBD. IBDTransDB includes a manually curated database with 34 transcriptomic datasets (2932 samples, 122 differential comparisons) and a query system supporting 35 keywords from 5 attributes (e.g. tissue and treatment). IBDTransDB also provides three modules for data analyses and integration. IBDExplore allows interactive visualization of differential gene list, pathway enrichment, gene signature and cell deconvolution analyses from a single dataset. IBDCompare supports comparisons of selected genes or pathways from multiple datasets across different conditions. IBDIntegrate performs meta-analysis to prioritize a list of genes/pathways based on user-selected datasets and conditions. Using two case studies related to infliximab treatment, we demonstrated that IBDTransDB provides a unique platform for biologists and clinicians to reveal IBD pathogenesis and identify the novel targets by integrating with other omics data. Database URL: https://abbviegrc.shinyapps.io/ibdtransdb/.

Figure 1.

IBDTransDB for exploratory, comparative and integrative datasets to identify and validate the novel IBD targets. Top panel: data processing and meta data curation for 34 IBD bulk transcriptomics datasets and 2 single-cell RNASeq datasets. Bottom panel: three data analysis modules.

Figure 2.

Understanding the infliximab resistance molecular and cellular mechanisms. (A) Volcano plot of differentially expressed genes between non-responders and responders at baseline in GSE16879 CD colon samples. (B) Top 20 enriched Reactome pathways based on the up-regulated genes from (A). (C) Comparison of five representative Reactome-enriched pathways from (B) in five non-responder vs responder comparisons from four infliximab-treated IBD datasets. (D) Significant cell types between non-responders and responders at baseline in GSE16879 CD colon samples.

Figure 3.

Prioritization of the candidate targets with genetic evidence for the treatment of infliximab non-responders. (A) Top three candidates with adjusted meta P-value <0.05 and |mean log2(fold change)|>0.58 from IBDIntegrate module. (B) Comparison of three candidates in five non-responder vs responder comparisons from four infliximab-treated IBD datasets. (C) Comparison of CXCR2 expression between after-treatment and baseline samples for responders and non-responders in GSE16879. (D) Comparison of three candidates in three non-responder vs responder comparisons from two vedolizumab-treated IBD datasets.