A strategy for high‐dimensional multivariable analysis classifies childhood asthma phenotypes from genetic, immunological, and environmental factors

Abstract

Background Associations between childhood asthma phenotypes and genetic, immunological, and environmental factors have been previously established. Yet, strategies to integrate high‐dimensional risk factors from multiple distinct data sets, and thereby increase the statistical power of analyses, have been hampered by a preponderance of missing data and lack of methods to accommodate them. Methods We assembled questionnaire, diagnostic, genotype, microarray, RT‐qPCR, flow cytometry, and cytokine data (referred to as data modalities) to use as input factors for a classifier that could distinguish healthy children, mild‐to‐moderate allergic asthmatics, and nonallergic asthmatics. Based on data from 260 German children aged 4‐14 from our university outpatient clinic, we built a novel multilevel prediction approach for asthma outcome which could deal with a present complex missing data structure. Results The optimal learning method was boosting based on all data sets, achieving an area underneath the receiver operating characteristic curve (AUC) for three classes of phenotypes of 0.81 (95%‐confidence interval (CI): 0.65‐0.94) using leave‐one‐out cross‐validation. Besides improving the AUC, our integrative multilevel learning approach led to tighter CIs than using smaller complete predictor data sets (AUC = 0.82 [0.66‐0.94] for boosting). The most important variables for classifying childhood asthma phenotypes comprised novel identified genes, namely PKN2 (protein kinase N2), PTK2 (protein tyrosine kinase 2), and ALPP (alkaline phosphatase, placental). Conclusion Our combination of several data modalities using a novel strategy improved classification of childhood asthma phenotypes but requires validation in external populations. The generic approach is applicable to other multilevel data‐based risk prediction settings, which typically suffer from incomplete data.

Advances and recent developments in asthma in 2020

“…Following this new discovery approach, genes such as PKN2 (protein kinase N2), PTK2 (protein tyrosine kinase 2), and ALPP (alkaline phosphatase, placental) seem to be the most important asthma risk factors. 18 Interleukin 1 receptor-like 1 (ST2) is known to be related to the pathogenesis of allergic diseases by mediating the response to IL-33.…”

“…Krautenbacher et al evaluated a new strategy combining cytokine, genotype, flow cytometry, diagnostic, questionnaire, reverse transcription‐polymerase chain reaction (RT‐PCR), and microarray data by using an integrative multilevel learning approach. Following this new discovery approach, genes such as PKN2 (protein kinase N2), PTK2 (protein tyrosine kinase 2), and ALPP (alkaline phosphatase, placental) seem to be the most important asthma risk factors 18 …”

TNF-α–induced protein 3 is a key player in childhood asthma development and environment-mediated protection

“…The CLARA/CLAUS cohort includes 4-to 15-year-old healthy control subjects (HCs) and children with mild-to-moderate asthma (n 5 273 and 334, respectively) recruited at LMU Children's Hospital since January 2009. 9,10 Asthmatic patients received diagnoses according to Global Initiative for Asthma guidelines. 11 Eligibility criteria for asthmatic patients were classical asthma symptoms, at least 3 episodes of wheeze and/or a doctor's diagnosis and/or a history of asthma medication, and lung function indicating significant reversible airflow obstruction according to American Thoracic Society/European Respiratory Society guidelines.…”

“…To investigate the regulation of TNFAIP3 and related NF-kB signaling genes, we assessed gene expression in PBMCs of steroid-naive asthmatic and healthy school-aged children from urban Germany. 9,10 The NF-kB pathway genes TNFAIP3, TLR4, myeloid differentiation primary response gene-88 (MYD88), mucosa-associated lymphoid tissue lymphoma translocation protein 1 (MALT1), TNF receptor-associated factor 6 (TRAF6), TNFAIP3-interacting protein 2 (TNIP2), and Tax1-binding protein 1 (TAX1BP1) and the T cell-associated genes CD274, programmed cell death 1 (PDCD1), CD80, cytotoxic T-lymphocyte associated protein 4 (CTLA4), CD86, and CD28 were examined.…”

Prioritizing Research Challenges and Funding for Allergy and Asthma and the Need for Translational Research — The European Strategic Forum on Allergic Diseases

“…При этом недостаточно просто оценить риски с точки зрения генетики, необходимо оценить и влияние факторов внешней среды. Основным направлением для прогресса в этой области является улучшенный методологический подход, доказывающий причинно-следственные связи, а не простые ассоциации, дополненный данными по влиянию окружающей среды на развитие аллергии и астмы [23,73,74].…”