RESUMO
The presentation, pathobiology, and prognosis of asthma are highly heterogeneous and challenging for clinicians to diagnose and treat. In addition to the adaptive immune response that underlies allergic inflammation, innate immune mechanisms are increasingly recognized to be critical mediators of the eosinophilic airway inflammation present in most patients with asthma. Efforts to classify patients by severity and immune response have identified a number of different clinical and immune phenotypes, indicating that the innate and adaptive immune responses are differentially active among patients with the disease. Advances in the detection of these subgroups using clinical characteristics and biomarkers have led to the successful development of targeted biologics. This has moved us to a more personalized approach to managing asthma. Here we review the emerging endotypes of asthma and the biologics that have been developed to treat them.
Assuntos
Corticosteroides/uso terapêutico , Asma/genética , Asma/terapia , Terapia Biológica/tendências , Citocinas/metabolismo , Asma/diagnóstico , Asma/imunologia , Terapia Biológica/métodos , Testes de Provocação Brônquica , Broncodilatadores/uso terapêutico , Broncoscopia/métodos , Feminino , Previsões , Humanos , Masculino , Prognóstico , Testes de Função Respiratória , Medição de Risco , Índice de Gravidade de Doença , Resultado do TratamentoRESUMO
BACKGROUND: The pathogenesis of asthma is a complex process involving multiple genes and pathways. Identifying biomarkers from asthma datasets, especially those that include heterogeneous subpopulations, is challenging. Potentially, autoencoders provide ideal frameworks for such tasks as they can embed complex, noisy high-dimensional gene expression data into a low-dimensional latent space in an unsupervised fashion, enabling us to extract distinguishing features from expression data. RESULTS: Here, we developed a framework combining a denoising autoencoder and a supervised learning classifier to identify gene signatures related to asthma severity. Using the trained autoencoder with 50 hidden units, we found that hierarchical clustering on the low-dimensional embedding corresponds well with previously defined and clinically relevant clusters of patients. Moreover, each hidden unit has contributions from each of the genes, and pathway analysis of these contributions shows that the hidden units are significantly enriched in known asthma-related pathways. We then used genes that contribute most to the hidden units to develop a secondary random-forest classifier for directly predicting asthma severity. The feature importance metric from this classifier identified a signature based on 50 key genes, which are associated with severity. Furthermore, we can use these key genes to successfully estimate FEV1/FVC ratios across patients, via support-vector-machine regression. CONCLUSION: We found that the denoising autoencoder framework can extract meaningful patterns corresponding to functional gene groups and patient clusters from the gene expression of asthma patients.