Formal axioms in biomedical ontologies improve analysis and interpretation of associated data

Coordinating virus research: The Virus Infectious Disease Ontology

The COVID-19 pandemic prompted immense work on the investigation of the SARS-CoV-2 virus. Rapid, accurate, and consistent interpretation of generated data is thereby of fundamental concern. Ontologies-structured, controlled, vocabularies-are designed to support consistency of interpretation, and thereby to prevent the development of data silos. This paper describes how ontologies are serving this purpose in the COVID-19 research domain, by following principles of the Open Biological and Biomedical Ontology (OBO) Foundry and by reusing existing ontologies such as the Infectious Disease Ontology (IDO) Core, which provides terminological content common to investigations of all infectious diseases. We report here on the development of an IDO extension, the Virus Infectious Disease Ontology (VIDO), a reference ontology covering viral infectious diseases. We motivate term and definition choices, showcase reuse of terms from existing OBO ontologies, illustrate how ontological decisions were motivated by relevant life science research, and connect VIDO to the Coronavirus Infectious Disease Ontology (CIDO). We next use terms from these ontologies to annotate selections from life science research on SARS-CoV-2, highlighting how ontologies employing a common upper-level vocabulary may be seamlessly interwoven. Finally, we outline future work, including bacteria and fungus infectious disease reference ontologies currently under development, then cite uses of VIDO and CIDO in host-pathogen data analytics, electronic health record annotation, and ontology conflict-resolution projects.

HeNeCOn: An ontology for integrative research in Head and Neck cancer

BACKGROUND

Head and Neck Cancer (HNC) has a high incidence and prevalence in the worldwide population. The broad terminology associated with these diseases and their multimodality treatments generates large amounts of heterogeneous clinical data, which motivates the construction of a high-quality harmonization model to standardize this multi-source clinical data in terms of format and semantics. The use of ontologies and semantic techniques is a well-known approach to face this challenge.

OBJECTIVE

This work aims to provide a clinically reliable data model for HNC processes during all phases of the disease: prognosis, treatment, and follow-up. Therefore, we built the first ontology specifically focused on the HNC domain, named HeNeCOn (Head and Neck Cancer Ontology).

METHODS

First, an annotated dataset was established to provide a formal reference description of HNC. Then, 170 clinical variables were organized into a taxonomy, and later expanded and mapped to formalize and integrate multiple databases into the HeNeCOn ontology. The outcomes of this iterative process were reviewed and validated by clinicians and statisticians.

RESULTS

HeNeCOn is an ontology consisting of 502 classes, a taxonomy with a hierarchical structure, semantic definitions of 283 medical terms and detailed relations between them, which can be used as a tool for information extraction and knowledge management.

CONCLUSION

HeNeCOn is a reusable, extendible and standardized ontology which establishes a reference data model for terminology structure and standard definitions in the Head and Neck Cancer domain. This ontology allows handling both current and newly generated knowledge in Head and Neck cancer research, by means of data linking and mapping with other public ontologies.

TANGO: A GO-Term Embedding Based Method for Protein Semantic Similarity Prediction

We aim to quantitatively predict protein semantic similarities (PSS), which is vital to making biological discoveries. Previously, researchers commonly exploited Gene Ontology (GO) graphs (containing standardized hierarchically-organized GO terms for annotating distinct protein attributes) to learn GO term embeddings (vector representations) for quantifying protein attribute similarities and aggregate these embeddings to form protein embeddings for similarity measurement. However, two key properties of GO terms and annotated proteins are not yet well-explored by these learning-based methods: (1) taxonomy relations between GO terms; (2) GO terms' different contributions in describing protein semantics. In this paper, we propose TANGO, a new framework composed of a TAxoNomy-aware embedding module and an aggreGatiOn module. Our Embedding Module encodes taxonomic information into GO term embeddings by incorporating GO term topological distances in the GO graph hierarchy. Hence, distances between GO term embeddings can be used to more accurately measure shared meanings between correlated protein attributes. Our Aggregation Module automatically determines the contributions of GO terms when merging into the target protein embeddings, by mining GO term concept dependency relations in the GO graph and correlations in protein annotations. We conduct extensive experiments on several public datasets. On two PSS metrics, our new method significantly outperforms known methods by a large margin.

RTX-KG2: a system for building a semantically standardized knowledge graph for translational biomedicine

BACKGROUND

Biomedical translational science is increasingly using computational reasoning on repositories of structured knowledge (such as UMLS, SemMedDB, ChEMBL, Reactome, DrugBank, and SMPDB in order to facilitate discovery of new therapeutic targets and modalities. The NCATS Biomedical Data Translator project is working to federate autonomous reasoning agents and knowledge providers within a distributed system for answering translational questions. Within that project and the broader field, there is a need for a framework that can efficiently and reproducibly build an integrated, standards-compliant, and comprehensive biomedical knowledge graph that can be downloaded in standard serialized form or queried via a public application programming interface (API).

RESULTS

To create a knowledge provider system within the Translator project, we have developed RTX-KG2, an open-source software system for building-and hosting a web API for querying-a biomedical knowledge graph that uses an Extract-Transform-Load approach to integrate 70 knowledge sources (including the aforementioned core six sources) into a knowledge graph with provenance information including (where available) citations. The semantic layer and schema for RTX-KG2 follow the standard Biolink model to maximize interoperability. RTX-KG2 is currently being used by multiple Translator reasoning agents, both in its downloadable form and via its SmartAPI-registered interface. Serializations of RTX-KG2 are available for download in both the pre-canonicalized form and in canonicalized form (in which synonyms are merged). The current canonicalized version (KG2.7.3) of RTX-KG2 contains 6.4M nodes and 39.3M edges with a hierarchy of 77 relationship types from Biolink.

CONCLUSION

RTX-KG2 is the first knowledge graph that integrates UMLS, SemMedDB, ChEMBL, DrugBank, Reactome, SMPDB, and 64 additional knowledge sources within a knowledge graph that conforms to the Biolink standard for its semantic layer and schema. RTX-KG2 is publicly available for querying via its API at arax.rtx.ai/api/rtxkg2/v1.2/openapi.json . The code to build RTX-KG2 is publicly available at github:RTXteam/RTX-KG2 .

Predicting candidate genes from phenotypes, functions and anatomical site of expression

Motivation

Over the past years, many computational methods have been developed to incorporate information about phenotypes for disease–gene prioritization task. These methods generally compute the similarity between a patient’s phenotypes and a database of gene-phenotype to find the most phenotypically similar match. The main limitation in these methods is their reliance on knowledge about phenotypes associated with particular genes, which is not complete in humans as well as in many model organisms, such as the mouse and fish. Information about functions of gene products and anatomical site of gene expression is available for more genes and can also be related to phenotypes through ontologies and machine-learning models.

Results

We developed a novel graph-based machine-learning method for biomedical ontologies, which is able to exploit axioms in ontologies and other graph-structured data. Using our machine-learning method, we embed genes based on their associated phenotypes, functions of the gene products and anatomical location of gene expression. We then develop a machine-learning model to predict gene–disease associations based on the associations between genes and multiple biomedical ontologies, and this model significantly improves over state-of-the-art methods. Furthermore, we extend phenotype-based gene prioritization methods significantly to all genes, which are associated with phenotypes, functions or site of expression.

Availability and implementation

Software and data are available at https://github.com/bio-ontology-research-group/DL2Vec.

Supplementary information

Supplementary data are available at Bioinformatics online.

DeepViral: prediction of novel virus-host interactions from protein sequences and infectious disease phenotypes

MOTIVATION

Infectious diseases caused by novel viruses have become a major public health concern. Rapid identification of virus-host interactions can reveal mechanistic insights into infectious diseases and shed light on potential treatments. Current computational prediction methods for novel viruses are based mainly on protein sequences. However, it is not clear to what extent other important features, such as the symptoms caused by the viruses, could contribute to a predictor. Disease phenotypes (i.e., signs and symptoms) are readily accessible from clinical diagnosis and we hypothesize that they may act as a potential proxy and an additional source of information for the underlying molecular interactions between the pathogens and hosts.

RESULTS

We developed DeepViral, a deep learning based method that predicts protein-protein interactions (PPI) between humans and viruses. Motivated by the potential utility of infectious disease phenotypes, we first embedded human proteins and viruses in a shared space using their associated phenotypes and functions, supported by formalized background knowledge from biomedical ontologies. By jointly learning from protein sequences and phenotype features, DeepViral significantly improves over existing sequence-based methods for intra- and inter-species PPI prediction.

AVAILABILITY

Code and datasets for reproduction and customization are available at https://github.com/bio-ontology-research-group/DeepViral. Prediction results for 14 virus families are available at https://doi.org/10.5281/zenodo.4429824.

Design and Use of Semantic Resources: Findings from the Section on Knowledge Representation and Management of the 2020 International Medical Informatics Association Yearbook

OBJECTIVE

To select, present, and summarize the best papers in the field of Knowledge Representation and Management (KRM) published in 2019.

METHODS

A comprehensive and standardized review of the biomedical informatics literature was performed to select the most interesting papers of KRM published in 2019, based on PubMed and ISI Web Of Knowledge queries.

RESULTS

Four best papers were selected among 1,189 publications retrieved, following the usual International Medical Informatics Association Yearbook reviewing process. In 2019, research areas covered by pre-selected papers were represented by the design of semantic resources (methods, visualization, curation) and the application of semantic representations for the integration/enrichment of biomedical data. Besides new ontologies and sound methodological guidance to rethink knowledge bases design, we observed large scale applications, promising results for phenotypes characterization, semantic-aware machine learning solutions for biomedical data analysis, and semantic provenance information representations for scientific reproducibility evaluation.

CONCLUSION

In the KRM selection for 2019, research on knowledge representation demonstrated significant contributions both in the design and in the application of semantic resources. Semantic representations serve a great variety of applications across many medical domains, with actionable results.