Major pathophysiological changes in pulmonary disease provided a molecular insight based on deep learning approach

The outburst of pulmonary disorders among the society has shown the devastating effect of undergoing a delay in diagnosis and treatment. Sometimes the traditional methods in detecting and treating the airway disease fail to cure efficiently due to a lack of pathophysiological descriptions along with the molecular expression. The studies published so far are missing the collective information of the pathways and the role of signature molecules during the disease that constricts the use of therapeutics like nitric oxide(NO) and hydrogen sulfide(H₂S). In this mini systemic research article, we have followed the deep machine learning approach that is based on the artificial intelligence algorithm as a background search engine that compares various reported scientific studies and database information by building a network analysis platform to better understand the molecular pathways that show a correlation with the other molecules. We followed the MEDLINE search to list the published studies for all the major pulmonary diseases, and the published literature from the NIH database was used to list out the genes and translated proteins associated with the major pulmonary diseases. For the pathways and the associated molecular information, the ShinyGo tool has been used. The published studies till December 2023 have been represented in this article. Bioinformatics analysis of the disease was analyzed based on the expression profiles of the genes and the major proteins from the protein-protein interaction STRING network, concluding that the perturbed molecules interplay a vital role in the progression of airway diseases and targeting the major pathways can be a possible therapeutic intervention for curing the disease.