Cov19VaxKB: A Web-based Integrative COVID-19 Vaccine Knowledge Base

Abstract

The development of SARS-CoV-2 vaccines during the COVID-19 pandemic has prompted the emergence of COVID-19 vaccine data. Timely access to COVID-19 vaccine information is crucial to researchers and public. To support more comprehensive annotation, integration, and analysis of COVID-19 vaccine information, we have developed Cov19VaxKB, a knowledge-focused COVID-19 vaccine database (http://www.violinet.org/cov19vaxkb/). Cov19VaxKB features comprehensive lists of COVID-19 vaccines, vaccine formulations, clinical trials, publications, news articles, and vaccine adverse event case reports. A web-based query interface enables comparison of product information and host responses among various vaccines. The knowledge base also includes a vaccine design tool for predicting vaccine targets and a statistical analysis tool that identifies enriched adverse events for FDA-authorized COVID-19 vaccines based on VAERS case report data. To support data exchange, Cov19VaxKB is synchronized with Vaccine Ontology and the Vaccine Investigation and Online Information Network (VIOLIN) database. The data integration and analytical features of Cov19VaxKB can facilitate vaccine research and development while also serving as a useful reference for the public.

Keywords: AE, adverse event; CDC, Centers for Disease Control and Prevention; COVID-19; COVID-19 vaccine; COVID-19, Coronavirus disease 2019; Cov19VaxKB; FDA, Food and Drug Administration; MERS-CoV, Middle Eastern Respiratory Syndrome; NCBI, National Center for Biotechnology Information; OWL, Web Ontology Language; PMID, PubMed identification number; PRR, Proportional Reporting Ratio; SARS-CoV, Severe Acute Respiratory Syndrome Coronavirus; SARS-CoV-2; SARS-CoV-2, Severe Acute Respiratory Syndrome Coronavirus 2; VAERS; VAERS, Vaccine Adverse Event Reporting System; VIOLIN, Vaccine Investigation and Online Information Network; VO, Vaccine Ontology; WHO, World Health Organization; adverse event; bioinformatics; database; knowledge base; ontology; vaccine.

Fig. 1

Cov19VaxKB workflow and system design. COVID-19 vaccine data from peer-reviewed PubMed publications, clinical trial records, and the WHO “Draft landscape and tracker of COVID-19 candidate vaccines” was annotated and stored into the Cov19VaxKB and VIOLIN databases. Data sharing and transfer was enabled by Vaccine Ontology (VO) IDs assigned for COVID-19 vaccines. Adverse event case report data was extracted from VAERS and analyzed in Cov19VaxKB using a server-side script.

Fig. 2

Cov19VaxKB data query. (A) A user can begin by selecting a specific category in the drop-down menu and typing in a keyword that will be used to query vaccines that only contain that keyboard. Up to three different categories can be specified to query a list of COVID-19 vaccines. The query feature also allows the user to sort vaccines according to conditions such as vaccine name or Vaccine Ontology ID. (B) Once the user has clicked “Search,” the query will produce a list of vaccines that satisfy the specified criteria. The user can select one or more of these vaccines and click “Compare” to compare the VIOLIN entries of the desired vaccines. (C) By doing so, the user will be presented with formatted side-by-side lists that contain general vaccine and host response information. General vaccine information contains data such as the product name of the vaccine, vaccine type, and antigen. Host response information contains brief summaries of randomized controlled trial data found in relevant publications. (D) Also, from the list of vaccines generated from the initial query, the user can click on the VO ID link. This will direct the user to a formatted VO vaccine entry in the Ontobee data server.

Fig. 3

Cov19VaxKB adverse event query and statistical analysis tool. (A) A user can begin by selecting a specific vaccine and specifying various filters including US state/territory, age, sex, year vaccinated, and VAERS report year. (B) After the user clicks “Query,” the query will generate a list of adverse events with their frequency of case reports. (C) The user can click an adverse event frequency to view a detailed table of individual VAERS case reports. (D) To perform statistical analyses, the user can select an adverse event and specify a vaccine of interest. (E) After clicking “Run Test,” the user will be presented with a formatted 2x2 table of AE case report counts and statistical test results, including a Chi-squared analysis, PRR, and statistical significance result.

Fig. 4

Venn diagram of enriched adverse events. The number and distribution of unique statistically significant AEs for the Pfizer, Janssen, and Moderna COVID-19 vaccines are displayed. The significance cutoff was Chi-squared value > 4, PRR > 2, and number of case reports > 0.2% of total case reports for the specified vaccine.

Fig. 5

Vaccine Ontology framework for Pfizer/BioNTech COVID-19 vaccine. This design pattern depicts the VO’s logical representations and linkages of different material entities, qualities, dispositions, and processes related to the Pfizer-BioNTech COVID-19 vaccine. The terms in the diagram are either generated in VO or imported from other ontologies.