Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Sep 30:5:910216.
doi: 10.3389/frai.2022.910216. eCollection 2022.

The precision medicine process for treating rare disease using the artificial intelligence tool mediKanren

Aleksandra Foksinska  1 , Camerron M Crowder  1   2 , Andrew B Crouse  1 , Jeff Henrikson  3 , William E Byrd  1 , Gregory Rosenblatt  1 , Michael J Patton  1 , Kaiwen He  1 , Thi K Tran-Nguyen  1 , Marissa Zheng  4 , Stephen A Ramsey  5 , Nada Amin  6 , John Osborne  7 ; UAB Precision Medicine Institute; Matthew Might  1
Collaborators, Affiliations

The precision medicine process for treating rare disease using the artificial intelligence tool mediKanren

Aleksandra Foksinska et al. Front Artif Intell. .

Abstract

There are over 6,000 different rare diseases estimated to impact 300 million people worldwide. As genetic testing becomes more common practice in the clinical setting, the number of rare disease diagnoses will continue to increase, resulting in the need for novel treatment options. Identifying treatments for these disorders is challenging due to a limited understanding of disease mechanisms, small cohort sizes, interindividual symptom variability, and little commercial incentive to develop new treatments. A promising avenue for treatment is drug repurposing, where FDA-approved drugs are repositioned as novel treatments. However, linking disease mechanisms to drug action can be extraordinarily difficult and requires a depth of knowledge across multiple fields, which is complicated by the rapid pace of biomedical knowledge discovery. To address these challenges, The Hugh Kaul Precision Medicine Institute developed an artificial intelligence tool, mediKanren, that leverages the mechanistic insight of genetic disorders to identify therapeutic options. Using knowledge graphs, mediKanren enables an efficient way to link all relevant literature and databases. This tool has allowed for a scalable process that has been used to help over 500 rare disease families. Here, we provide a description of our process, the advantages of mediKanren, and its impact on rare disease patients.

Keywords: artificial intelligence; biomedical reasoning; drug repurposing; precision medicine; rare disease.

PubMed Disclaimer

Conflict of interest statement

Author JH is employed by Groovescale. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Flowchart illustrating the workflow of the TMLHE case using mediKanren. Based on the conclusions of the case analysis, the analyst used mediKanren to identify therapeutic strategies to compensate for the loss of trimethyllysine hydroxylase activity and decrease in carnitine biosynthesis. One hundred and thirteen concepts were returned by mediKanren using the SemMedDB KG that were predicted to increase carnitine, and of those, levocarnitine is FDA-approved and supporting literature was reviewed to confirm the result. TMLHE, Trimethyllysine Hydroxylase, Epsilon; CURIE, compact uniform resource identifier; UMLS, Unified Medical Language System; FDA, Food and Drug Administration.
Figure 2
Figure 2
Flowchart illustrating the workflow of the RHOBTB2 case using mediKanren. (A) Based on the conclusions of the case analysis, the analyst used mediKanren to identify therapeutic strategies that will regulate RHOBTB2 gene expression. Ten concepts were returned by mediKanren using the SemMedDB KG that were predicted to regulate RHOBTB2 expression, but none of the concepts were drugs or compounds. Therefore, a two-hop approach was taken with E2F1, a gene that was identified as a regulator of RHOBTB2. (B) A second query was run to look for downregulators of E2F1, which resulted in 212 concepts. After filtering for drugs, sorting by relevance, and manually reviewing for FDA-approved compounds that pass the blood-brain barrier, Celecoxib was identified. RHOBTB2, Rho Related BTB Domain Containing 2; CURIE, compact uniform resource identifier; UMLS, Unified Medical Language System; E2F1, E2F Transcription Factor 1.
Figure 3
Figure 3
Flowchart illustrating the workflow of the cyclic vomiting syndrome case using mediKanren. (A) Over 422 concepts were returned by mediKanren using the SemMedDB and RTX KGs that were predicted to treat or prevent nausea and/or vomiting. (B) Ondansetron was the concept with the most publications, whereas isopropyl alcohol was located in the tail-end of the results with only three publications. CURIE, compact uniform resource identifier; UMLS, Unified Medical Language System; HP, human phenotype.
Figure 4
Figure 4
Flowchart illustrating the workflow of SARS-CoV-2 drug repurposing using mediKanren. Over 64 pro-viral and anti-viral _targets were queried in mediKanren for negative and positive regulators, respectively. Over 1,300 drugs were returned by mediKanren using the RTX-KG2. These drugs were sorted by the number of publications and number of _targets and manually reviewed to prioritize FDA-approved and safe drugs for testing in VeroE6 cells.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Beadle K. L., Helbling A. R., Love S. L., April M. D., Hunter C. J. (2016). Isopropyl alcohol nasal inhalation for nausea in the emergency department: a randomized controlled trial. Ann. Emerg. Med. 68, 1.e1–9.e1. 10.1016/j.annemergmed.2015.09.031 - DOI - PubMed
    1. Belal H., Nakashima M., Matsumoto H., Yokochi K., Taniguchi-Ikeda M., Aoto K., et al. . (2018). De novo variants in RHOBTB2, an atypical Rho GTPase gene, cause epileptic encephalopathy. Hum. Mutat. 39, 1070–1075. 10.1002/humu.23550 - DOI - PubMed
    1. Berman H. M., Westbrook J., Feng Z., Gilliland G., Bhat T. N., Weissig H., et al. . (2000). The protein data bank. Nucleic Acids Res. 28, 235–242. 10.1093/nar/28.1.235 - DOI - PMC - PubMed
    1. Biomedical Data Translator Consortium (2019). Toward A universal biomedical data translator. Clin. Transl. Sci. 12, 86–90. 10.1111/cts.12591 - DOI - PMC - PubMed
    1. Cadegiani F. A., McCoy J., Gustavo Wambier C., Vaño-Galván S., Shapiro J., Tosti A., et al. . (2021). Proxalutamide significantly accelerates viral clearance and reduces time to clinical remission in patients with mild to moderate COVID-19: results from a randomized, double-blinded, placebo-controlled trial. Cureus 13, e13492. 10.7759/cureus.13492 - DOI - PMC - PubMed
  NODES
admin 1
twitter 2