An approach for collaborative development of a federated biomedical knowledge graph-based question-answering system: Question-of-the-Month challenges

Karamarie Fecho; Chris Bizon; Tursynay Issabekova; Sierra Moxon; Anne E Thessen; Shervin Abdollahi; Sergio E Baranzini; Basazin Belhu; William E Byrd; Lawrence Chung; Andrew Crouse; Marc P Duby; Stephen Ferguson; Aleksandra Foksinska; Laura Forero; Jennifer Friedman; Vicki Gardner; Gwênlyn Glusman; Jennifer Hadlock; Kristina Hanspers; Eugene Hinderer; Charlotte Hobbs; Gregory Hyde; Sui Huang; David Koslicki; Philip Mease; Sandrine Muller; Christopher J Mungall; Stephen A Ramsey; Jared Roach; Irit Rubin; Shepherd H Schurman; Anath Shalev; Brett Smith; Karthik Soman; Sarah Stemann; Andrew I Su; Casey Ta; Paul B Watkins; Mark D Williams; Chunlei Wu; Colleen H Xu; Biomedical Data Translator Consortium

doi:10.1017/cts.2023.619

An approach for collaborative development of a federated biomedical knowledge graph-based question-answering system: Question-of-the-Month challenges

J Clin Transl Sci. 2023 Sep 14;7(1):e214. doi: 10.1017/cts.2023.619. eCollection 2023.

Authors

Karamarie Fecho^{1

2}, Chris Bizon¹, Tursynay Issabekova³, Sierra Moxon⁴, Anne E Thessen³, Shervin Abdollahi⁵, Sergio E Baranzini⁶, Basazin Belhu⁷, William E Byrd⁸, Lawrence Chung⁹, Andrew Crouse⁸, Marc P Duby⁹, Stephen Ferguson¹⁰, Aleksandra Foksinska⁸, Laura Forero^{11

12}, Jennifer Friedman^{11

12}, Vicki Gardner¹, Gwênlyn Glusman⁷, Jennifer Hadlock⁷, Kristina Hanspers¹³, Eugene Hinderer¹⁴, Charlotte Hobbs¹¹, Gregory Hyde¹⁵, Sui Huang⁷, David Koslicki¹⁶, Philip Mease^{17

18}, Sandrine Muller⁹, Christopher J Mungall⁴, Stephen A Ramsey¹⁹, Jared Roach⁷, Irit Rubin⁷, Shepherd H Schurman²⁰, Anath Shalev⁸, Brett Smith⁷, Karthik Soman⁶, Sarah Stemann⁵, Andrew I Su²¹, Casey Ta²², Paul B Watkins²³, Mark D Williams⁵, Chunlei Wu²¹, Colleen H Xu²¹; Biomedical Data Translator Consortium

Affiliations

¹ Renaissance Computing Institute (RENCI), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.
² Copperline Professional Solutions, Pittsboro, NC, USA.
³ Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO, USA.
⁴ Biosystems Data Science Department, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
⁵ Division of Preclinical Innovation, National Center for Advancing Translational Sciences, National Institutes of Health, Rockville, MD, USA.
⁶ Department of Neurology, Weill Institute for Neuroscience, University of California - San Francisco, San Francisco, CA, USA.
⁷ Institute for Systems Biology, Seattle, WA, USA.
⁸ The Hugh Kaul Precision Medicine Institute, University of Alabama at Birmingham, Birmingham, AL, USA.
⁹ The Broad Institute of MIT and Harvard, Cambridge, MA, USA.
¹⁰ National Institute of Environmental Health Sciences, National Institutes of Health, Research Triangle Park, NC, USA.
¹¹ Rady Children's Institute for Genomic Medicine, Rady Children's Hospital, San Diego, CA, USA.
¹² University of California at San Diego, San Diego, CA, USA.
¹³ Gladstone Institutes, University of California - San Francisco, San Francisco, CA, USA.
¹⁴ Tufts Clinical and Translational Science Institute, Tufts Medical Center, Boston, MA, USA.
¹⁵ Thayer School of Engineering at Dartmouth College, Hanover, NH, USA.
¹⁶ Departments of Computer Science and Engineering, Biology, and the Huck Institutes of the Life Sciences, Penn State University, University Park, PA, USA.
¹⁷ Swedish Medical Center, St. Joseph Health, Seattle, WA, USA.
¹⁸ University of Washington, Seattle, WA, USA.
¹⁹ Oregon State University, Corvallis, OR, USA.
²⁰ National Institute on Aging, National Institutes of Health, Baltimore, MD, USA.
²¹ The Scripps Research Institute, La Jolla, CA, USA.
²² Columbia University Irving Medical Center, New York, NY, USA.
²³ Division of Pharmacotherapy and Experimental Therapeutics, Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Abstract

Knowledge graphs have become a common approach for knowledge representation. Yet, the application of graph methodology is elusive due to the sheer number and complexity of knowledge sources. In addition, semantic incompatibilities hinder efforts to harmonize and integrate across these diverse sources. As part of The Biomedical Translator Consortium, we have developed a knowledge graph-based question-answering system designed to augment human reasoning and accelerate translational scientific discovery: the Translator system. We have applied the Translator system to answer biomedical questions in the context of a broad array of diseases and syndromes, including Fanconi anemia, primary ciliary dyskinesia, multiple sclerosis, and others. A variety of collaborative approaches have been used to research and develop the Translator system. One recent approach involved the establishment of a monthly "Question-of-the-Month (QotM) Challenge" series. Herein, we describe the structure of the QotM Challenge; the six challenges that have been conducted to date on drug-induced liver injury, cannabidiol toxicity, coronavirus infection, diabetes, psoriatic arthritis, and ATP1A3-related phenotypes; the scientific insights that have been gleaned during the challenges; and the technical issues that were identified over the course of the challenges and that can now be addressed to foster further development of the prototype Translator system. We close with a discussion on Large Language Models such as ChatGPT and highlight differences between those models and the Translator system.

Keywords: Translational research; bioinformatics; knowledge graphs; semantic technology; team science.