Literature-Based Discoveries in Lupus Treatment

Authors: Oluwaseyi Jaiyeoba, Vetria Byrd

Abstract:

Systemic lupus erythematosus (aka lupus) is a chronic disease known for its chameleon-like ability to mimic symptoms of other diseases rendering it hard to detect, diagnose and treat. The heterogeneous nature of the disease generates disparate data that are often multifaceted and multi-dimensional. Musculoskeletal manifestation of lupus is one of the most common clinical manifestations of lupus. This research links disparate literature on the treatment of lupus as it affects the musculoskeletal system using the discoveries from literature-based research articles available on the PubMed database. Several Natural Language Processing (NPL) tools exist to connect disjointed but related literature, such as Connected Papers, Bitola, and Gopalakrishnan. Literature-based discovery (LBD) has been used to bridge unconnected disciplines based on text mining procedures. The technical/medical literature consists of many technical/medical concepts, each having its  sub-literature. This approach has been used to link Parkinson’s, Raynaud, and Multiple Sclerosis treatment within works of literature.  Literature-based discovery methods can connect two or more related but disjointed literature concepts to produce a novel and plausible approach to solving a research problem. Data visualization techniques with the help of natural language processing tools are used to visually represent the result of literature-based discoveries. Literature search results can be voluminous, but Data visualization processes can provide insight and detect subtle patterns in large data. These insights and patterns can lead to discoveries that would have otherwise been hidden from disjointed literature. In this research, literature data are mined and combined with visualization techniques for heterogeneous data to discover viable treatments reported in the literature for lupus expression in the musculoskeletal system. This research answers the question of using literature-based discovery to identify potential treatments for a multifaceted disease like lupus. A three-pronged methodology is used in this research: text mining, natural language processing, and data visualization. These three research-related fields are employed to identify patterns in lupus-related data that, when visually represented, could aid research in the treatment of lupus. This work introduces a method for visually representing interconnections of various lupus-related literature. The methodology outlined in this work is the first step toward literature-based research and treatment planning for the musculoskeletal manifestation of lupus. The results also outline the interconnection of complex, disparate data associated with the manifestation of lupus in the musculoskeletal system. The societal impact of this work is broad. Advances in this work will improve the quality of life for millions of persons in the workforce currently diagnosed and silently living with a musculoskeletal disease associated with lupus.

Keywords: Systemic lupus erythematosus, LBD, Data Visualization, musculoskeletal system, treatment.

References:

[1] K. Mahmoud, A. Zayat, and E. M. Vital, ”Musculoskeletal manifestations of systemic lupus erythmatosus,” Current opinion in rheumatology, vol. 29, pp. 486-492, 2017.
[2] T. D¨orner and R. Furie, ”Novel paradigms in systemic lupus erythematosus,” The Lancet, vol. 393, pp. 2344-2358, 2019.
[3] S. Yavuz and P. E. Lipsky, ”Current Status of the Evaluation and Management of Lupus Patients and Future Prospects,” Frontiers in medicine, vol. 8, 2021.
[4] E. Heiman, S. S. Lim, G. Bao, and C. Drenkard, ”Depressive symptoms are associated with low treatment adherence in African American individuals with systemic lupus erythematosus,” Journal of clinical rheumatology: practical reports on rheumatic & musculoskeletal diseases, vol. 24, p. 368, 2018.
[5] G. R. V. Hughes, Lupus: The Facts: Oxford University Press, 2000.
[6] A. Stockl, ”Complex syndromes, ambivalent diagnosis, and existential uncertainty: the case of Systemic Lupus Erythematosus (SLE),” Social science & medicine, vol. 65, pp. 1549-1559, 2007.
[7] S. R. Johnson, R. Brinks, K. H. Costenbader, D. Daikh, M. Mosca, R. Ramsey-Goldman, et al., ”Performance of the 2019 EULAR/ACR classification criteria for systemic lupus erythematosus in early disease, across sexes and ethnicities,” Annals of the rheumatic diseases, vol. 79, pp. 1333-1339, 2020.
[8] M. E. Orme, A. Voreck, R. Aksouh, R. Ramsey-Goldman, and M. W. Schreurs, ”Systematic review of anti-dsDNA testing for systemic lupus erythematosus: a meta-analysis of the diagnostic test specificity of an anti-dsDNA fluorescence enzyme immunoassay,” Autoimmunity Reviews, vol. 20, p. 102943, 2021.
[9] C. Arrigoni, S. Lopa, C. Candrian, and M. Moretti, ”Organs-on-a-chip as model systems for multifactorial musculoskeletal diseases,” Current opinion in biotechnology, vol. 63, pp. 79-88, 2020.
[10] K. Mahmoud, A. Zayat, and E. M. Vital, ”Musculoskeletal manifestations of systemic lupus erythmatosus,” Current opinion in rheumatology, vol. 29, pp. 486-492, 2017.
[11] R. Johnson, A. Watkinson, and M. Mabe, ”The STM report: An overview of scientific and scholarly publishing,” International Association of Scientific, Technical and Medical Publishers, pp. 1-214, 2018.
[12] S. Henry and B. T. McInnes, ”Literature based discovery: models, methods, and trends,” Journal of biomedical informatics, vol. 74, pp. 20-32, 2017.
[13] H.-T. Yang, J.-H. Ju, Y.-T. Wong, I. Shmulevich, and J.-H. Chiang, ”Literature-based discovery of new candidates for drug repurposing,” Briefings in bioinformatics, vol. 18, pp. 488-497, 2017.
[14] S. Henry, D. S. Wijesinghe, A. Myers, and B. T. McInnes, ”Using literature based discovery to gain insights into the metabolomic processes of cardiac arrest,” Frontiers in Research Metrics and Analytics, vol. 6, p. 32, 2021.
[15] S. Pyysalo, S. Baker, I. Ali, S. Haselwimmer, T. Shah, A. Young, et al., ”LION LBD: a literature-based discovery system for cancer biology,” Bioinformatics, vol. 35, pp. 1553-1561, 2019.
[16] Y. Zhu, W. Jung, F. Wang, and C. Che, ”Drug repurposing against Parkinson’s disease by text mining the scientific literature,” Library Hi Tech, 2020.
[17] G. Crichton, S. Baker, Y. Guo, and A. Korhonen, ”Neural networks for open and closed Literature-based Discovery,” Plos one, vol. 15, p. e0232891, 2020.
[18] A. Usai, M. Pironti, M. Mital, and C. A. Mejri, ”Knowledge discovery out of text data: a systematic review via text mining,” Journal of knowledge management, 2018.
[19] V. Gopalakrishnan, K. Jha, W. Jin, and A. Zhang, ”A survey on literature based discovery approaches in biomedical domain,” Journal of biomedical informatics, vol. 93, p. 103141, 2019.
[20] M. Weeber, J. A. Kors, and B. Mons, ”Online tools to support literature-based discovery in the life sciences,” Briefings in bioinformatics, vol. 6, pp. 277-286, 2005.
[21] M. Weeber, R. Vos, H. Klein, L. T. de Jong-van den Berg, A. R. Aronson, and G. Molema, ”Generating hypotheses by discovering implicit associations in the literature: a case report of a search for new potential therapeutic uses for thalidomide,” Journal of the American Medical Informatics Association, vol. 10, pp. 252-259, 2003.
[22] P. Srinivasan and B. Libbus, ”Mining MEDLINE for implicit links between dietary substances and diseases,” Bioinformatics, vol. 20, pp. i290-i296, 2004.
[23] Z. Dai, Q. Li, G. Yang, Y. Wang, Y. Liu, Z. Zheng, et al., ”Using literature-based discovery to identify candidate genes for the interaction between myocardial infarction and depression,” BMC Medical Genetics, vol. 20, pp. 1-10, 2019.
[24] A. Lenci, ”Distributional models of word meaning,” Annual review of Linguistics, vol. 4, pp. 151-171, 2018.
[25] P. Bruza, R. Cole, D. Song, and Z. Bari, ”Towards operational abduction from a cognitive perspective,” Logic Journal of IGPL, vol. 14, pp. 161-177, 2006.
[26] M. C. Ganiz, W. M. Pottenger, and C. D. Janneck, ”Recent advances in literature based discovery,” Journal of the American Society for Information Science and Technology, JASIST (Submitted), 2005.
[27] C. M. Miller, T. C. Rindflesch, M. Fiszman, D. Hristovski, D. Shin, G. Rosemblat, et al., ”A closed literature-based discovery technique finds a mechanistic link between hypogonadism and diminished sleep quality in aging men,” Sleep, vol. 35, pp. 279-285, 2012.
[28] M. Thilakaratne, K. Falkner, and T. Atapattu, ”A systematic review on literature-based discovery: general overview, methodology, & statistical analysis,” ACM Computing Surveys (CSUR), vol. 52, pp. 1-34, 2019.
[29] C. E. Lipscomb, ”Medical subject headings (MeSH),” Bulletin of the Medical Library Association, vol. 88, p. 265, 2000.
[30] H. Kilicoglu, G. Rosemblat, M. Fiszman, and D. Shin, ”Broad-coverage biomedical relation extraction with SemRep,” BMC bioinformatics, vol. 21, pp. 1-28, 2020.
[31] R. N. Kostoff and U. Patel, ”Literature-related discovery and innovation: Chronic kidney disease,” Technological Forecasting and Social Change, vol. 91, pp. 341-351, 2015.