SciBite Elsevier marked World Psoriasis Day on 29th October, by expanding our coverage for psoriasis-related concepts. Our goal was to find words or phrases related to psoriasis that are missing from SciBite’s VOCabs—our named entity recognition (NER)-specialized vocabularies covering a plethora of topics in the healthcare and pharmaceutical domains, such as drugs, anatomy and diseases—that form the basis of our software solutions. In keeping with the FAIR philosophy, SciBite VOCabs are mainly based on public standards and are used in a variety of ways to help our customers standardise their data and efficiently find relevant literature and documentation around their subject of interest, for use in drug discovery, manufacturing and more.
During the jamboree we used TERMite, our NER engine, to scan documents, articles and webpages on psoriasis and identify terms that would add value to our vocabularies to ensure our customers achieve maximum recall of information (see screenshot below).
If pertinent words and phrases are not present in our vocabularies, it means that insightful information or data is less likely to be found by our customers. By enriching psoriasis-related concepts with new entities and synonyms, we increase the likelihood that the information is easily findable for improving the understanding and management of this pernicious condition.
The outcome of the jamboree was that we identified approximately 100 psoriasis-related concepts that can be augmented with either additional synonyms or context-appropriate curation to improve searchability of these terms.
Moreover, in the spirit of giving back to the bio-ontology community, SciBite curator Paola reviewed the representation of psoriasis in the Mondo Disease Ontology. She identified several issues and gaps, and suggested solutions to the resource’s curators—including improvements to the placement of terms in the hierarchy, clarification of term names, addition of synonyms and fixing typographical errors—thereby improving this valuable public resource alongside SciBite’s vocabulary assets.
We organise 2-3 curation jamborees focused on specific healthcare or disease recognition days throughout the year. You can read about our past jamborees on the SciBite website [1,2,3].
The screenshot shows some psoriasis-specific entities in TERMite, SciBite’s NER engine. Though concepts like “psoriasis”, “erythematous” and “steroid creams” were indexed by our vocabularies, other phrases such as “chronic plaque-type psoriasis” and “flaky patches of skin” were not.
This project will ensure these and other phrases, such as CPTP and FPOS, are added to the SciBite vocabularies and made available for our customers.
Rachael Huntley is Lead Scientific Curator at SciBite with over 20 years biocuration experience. Dr. Huntley received her PhD in plant biochemistry from the University of Cambridge and completed post-doctoral research in both Cambridge, UK and Stanford, USA.
During her time at EMBL-EBI and University College London she contributed to functional annotation of human proteins and microRNAs involved in human health and disease. Throughout her biocuration career, she has worked closely with the Gene Ontology Consortium and major pharmaceutical companies and has contributed to the development of ontologies, biocuration standards and curation tools.