Patient Similarity Networks for Precision Medicine. Issue 18 (14th September 2018)

• Record Type: Journal Article
• Authors: Pai, Shraddha; Bader, Gary D.
• Is Part Of: Journal of molecular biology. Volume 430:Issue 18(2018)Part A
• Page Start: 2924
• Page End: 2938
• Publication Date: 2018-09-14
• Subjects: precision medicine -- machine learning -- patient classifier -- genomics -- networks; ASCVD Atherosclerotic Cardiovascular Disease -- AUROC area under the receiver operator characteristic curve -- AUPR area under the precision–recall curve -- PSN patient similarity network -- SNF Similarity Network Fusion; Molecular biology -- Periodicals; Biology -- Periodicals; Biochemistry -- Periodicals; Bacteriology -- Periodicals; Molecular Biology -- Periodicals; Biochemistry -- Periodicals; Biologie moléculaire -- Périodiques; Biologie -- Périodiques; Biochimie -- Périodiques; Moleculaire biologie; Biochemistry; Biology; Molecular biology; Periodicals; 572.805
• DOI: 10.1016/j.jmb.2018.05.037
• Languages: English
• ISSNs: 0022-2836

Abstract

Abstract: Clinical research and practice in the 21st century is poised to be transformed by analysis of computable electronic medical records and population-level genome-scale patient profiles. Genomic data capture genetic and environmental state, providing information on heterogeneity in disease and treatment outcome, but genomic-based clinical risk scores are limited. Achieving the goal of routine precision medicine that takes advantage of these rich genomics data will require computational methods that support heterogeneous data, have excellent predictive performance, and ideally, provide biologically interpretable results. Traditional machine-learning approaches excel at performance, but often have limited interpretability. Patient similarity networks are an emerging paradigm for precision medicine, in which patients are clustered or classified based on their similarities in various features, including genomic profiles. This strategy is analogous to standard medical diagnosis, has excellent performance, is interpretable, and can preserve patient privacy. We review new methods based on patient similarity networks, including Similarity Network Fusion for patient clustering and netDx for patient classification. While these methods are already useful, much work is required to improve their scalability for contemporary genetic cohorts, optimize parameters, and incorporate a wide range of genomics and clinical data. The coming 5 years will provide an opportunity to assess the utility of network-based algorithms for precision medicine. Graphical abstract: Highlights: Future clinics will combine clinical and genomic data with cellular models for precision medicine. Statistical risk calculators using genomics need to be interpretable due to small sample sizes. Patient similarity networks are a new model to integrate data to cluster/classify patients. Patient similarity networks are accurate, intuitive, preserve patient privacy, and supply mechanistic insight.