Abstract
We introduce a MeSH-based method that accurately quantifies similarity between heritable diseases at molecular level. This method effectively brings together the existing information about diseases that is scattered across the vast corpus of biomedical literature. We prove that sets of MeSH terms provide a highly descriptive representation of heritable disease and that the structure of MeSH provides a natural way of combining individual MeSH vocabularies. We show that our measure can be used effectively in the prediction of candidate disease genes. We developed a web application to query more than 28.5 million relationships between 7,574 hereditary diseases (96% of OMIM) based on our similarity measure.
Highlights
We introduce a Medical Subject Headings (MeSH)-based method that accurately quantifies similarity between heritable diseases at molecular level
This allows us to establish a mapping between diseases in OMIM and the MeSH ontology: every disease is annotated by the set of MeSH terms associated with its publications
Our method annotates diseases using the MeSH terms associated to the publications found in OMIM and combines these annotations with the structure of the MeSH ontology
Summary
We introduce a MeSH-based method that accurately quantifies similarity between heritable diseases at molecular level. This method effectively brings together the existing information about diseases that is scattered across the vast corpus of biomedical literature. Van Driel et al.[4] present a measure based on text-mining analysis of the disease phenotype descriptions found in the OMIM compendium of heritable diseases[6]. These descriptions are mined for a predefined set of Medical Subject Headings (MeSH) terms which are used to construct feature vectors for every disease. Similarity between diseases is calculated using an information content-based similarity measure on the HPO
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.