Capturing heart valve development with Gene Ontology

Abstract

Introduction: The normal development of all heart valves requires highly coordinated signaling pathways and downstream mediators. While genomic variants can be responsible for congenital valve disease, environmental factors can also play a role. Later in life valve calcification is a leading cause of aortic valve stenosis, a progressive disease that may lead to heart failure. Current research into the causes of both congenital valve diseases and valve calcification is using a variety of high-throughput methodologies, including transcriptomics, proteomics and genomics. High quality genetic data from biological knowledge bases are essential to facilitate analyses and interpretation of these high-throughput datasets. The Gene Ontology (GO, http://geneontology.org/) is a major bioinformatics resource used to interpret these datasets, as it provides structured, computable knowledge describing the role of gene products across all organisms. The UCL Functional Gene Annotation team focuses on GO annotation of human gene products. Having identified that the GO annotations included in transcriptomic, proteomic and genomic data did not provide sufficient descriptive information about heart valve development, we initiated a focused project to address this issue. Methods: This project prioritized 138 proteins for GO annotation, which led to the curation of 100 peer-reviewed articles and the creation of 400 heart valve development-relevant GO annotations. Results: While the focus of this project was heart valve development, around 600 of the 1000 annotations created described the broader cellular role of these proteins, including those describing aortic valve morphogenesis, BMP signaling and endocardial cushion development. Our functional enrichment analysis of the 28 proteins known to have a role in bicuspid aortic valve disease confirmed that this annotation project has led to an improved interpretation of a heart valve genetic dataset. Discussion: To address the needs of the heart valve research community this project has provided GO annotations to describe the specific roles of key proteins involved in heart valve development. The breadth of GO annotations created by this project will benefit many of those seeking to interpret a wide range of cardiovascular genomic, transcriptomic, proteomic and metabolomic datasets.

Keywords: Gene Ontology; bioinformatics; functional analysis; genomics; heart valve development; proteomics; transcriptomics.

FIGURE 1

Ontology relevant to heart valve development. Graph of the part of the heart development ontology, available in QuickGO (Binns et al., 2009). Seven descriptive child terms of ‘heart development’ are highlighted in yellow. The ‘is_a’ relations between GO terms are indicated by black arrows, the ‘part_of’ relations as blue arrows (Ashburner et al., 2000; Gene Ontology Consortium, 2021).

FIGURE 2

Flowchart highlighting the steps taken to manually curate each article. Manual GO curation of published articles applied GO Consortium guidelines and use the GO browser, QuickGO, to identify any previous annotations associated with each article as well as to identify appropriate GO terms to associate with the described proteins. The HGNC orthology prediction tool HCOP (Yates et al., 2021), was used to confirm orthology between non-human proteins and human proteins.