Machine learning application for patient stratification and phenotype/genotype investigation in a rare disease. Issue 5 (4th February 2021)

• Record Type: Journal Article
• Authors: Spiga, Ottavia; Cicaloni, Vittoria; Dimitri, Giovanna Maria; Pettini, Francesco; Braconi, Daniela; Bernini, Andrea; Santucci, Annalisa
• Is Part Of: Briefings in bioinformatics. Volume 22:Issue 5(2021)
• Publication Date: 2021-02-04
• Subjects: rare disease -- alkaptonuria -- machine learning -- precision medicine -- patient stratification; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbaa434
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: Alkaptonuria (AKU, OMIM: 203500) is an autosomal recessive disorder caused by mutations in the Homogentisate 1, 2-dioxygenase ( HGD ) gene. A lack of standardized data, information and methodologies to assess disease severity and progression represents a common complication in ultra-rare disorders like AKU. This is the reason why we developed a comprehensive tool, called ApreciseKUre, able to collect AKU patients deriving data, to analyse the complex network among genotypic and phenotypic information and to get new insight in such multi-systemic disease. By taking advantage of the dataset, containing the highest number of AKU patient ever considered, it is possible to apply more sophisticated computational methods (such as machine learning) to achieve a first AKU patient stratification based on phenotypic and genotypic data in a typical precision medicine perspective. Thanks to our sufficiently populated and organized dataset, it is possible, for the first time, to extensively explore the phenotype–genotype relationships unknown so far. This proof of principle study for rare diseases confirms the importance of a dedicated database, allowing data management and analysis and can be used to tailor treatments for every patient in a more effective way.