Artificial neural network identified the significant genes to distinguish Idiopathic pulmonary fibrosis

Abstract

Idiopathic pulmonary fibrosis (IPF) is a progressive interstitial lung disease that causes irreversible damage to lung tissue characterized by excessive deposition of extracellular matrix (ECM) and remodeling of lung parenchyma. The current diagnosis of IPF is complex and usually completed by a multidisciplinary team including clinicians, radiologists and pathologists they work together and make decision for an effective treatment, it is imperative to introduce novel practical methods for IPF diagnosis. This study provided a new diagnostic model of idiopathic pulmonary fibrosis based on machine learning. Six genes including CDH3, DIO2, ADAMTS14, HS6ST2, IL13RA2, and IGFL2 were identified based on the differentially expressed genes in IPF patients compare to healthy subjects through a random forest classifier with the existing gene expression databases. An artificial neural network model was constructed for IPF diagnosis based these genes, and this model was validated by the distinctive public datasets with a satisfactory diagnostic accuracy. These six genes identified were significant correlated with lung function, and among them, CDH3 and DIO2 were further determined to be significantly associated with the survival. Putting together, artificial neural network model identified the significant genes to distinguish idiopathic pulmonary fibrosis from healthy people and it is potential for molecular diagnosis of IPF.

Implicating the cholecystokinin B receptor in liver stem cell oncogenesis

“…Most of the genes downregulated when the CCK-BR was knocked out promote HCC proliferation such as Tmem45a (transmembrane protein 45a; 52 ), Spp1 (secreted phosphoprotein 1-Osteopontin; 53 ), Slco3a1 (solute carrier organic anion transporter; 54 ), and GSE1 (genetic suppressor element; 55 ). Knocking out the CCK-BR also decreased the expression of fibrosis-promoting genes including Adamts14 (codes for a disintegrin-like and metallopeptidase; 56 ) and Fst (follistatin-like 1; 57 ). Five hundred and five genes were similarly altered in DDC-fed mice treated with proglumide or in transgenic CCK-BR-KO mice are shown in the Venn diagram ( Fig.…”

Unagi: Deep Generative Model for Deciphering Cellular Dynamics and In-Silico Drug Discovery in Complex Diseases

“…In the context of the FibAlv-4 track, the method identifies genes like COL3A1 and SERPINE1, which are induced by the TGF-Beta pathway 60 , a key player in IPF. Furthermore, the inclusion of top dynamic marker candidates such as DCLK1 62 , TENM3, TENM2, ADRA1A, and GRIA1, all of which have established associations with IPF [61][62][63][64] , attests to the method's robustness in capturing diseaserelevant genes (Fig. 3d).…”

“…Notably, NLGN1, GFRA1, and AOX1 are markers for adventitial fibroblasts 66 and emerge as a top-decreasing temporal dynamic marker in this track, suggestive of a loss of respective cell identity. The FibAlv-4 track, on the other hand, features markers like DCLK1, TENM3, ADRA1A, GRIA1, and EPHA3, all of which have strong ties to lung fibrosis [61][62][63][64]67 . It is important to mention that while our discussion here primarily focused on monotonically increasing and decreasing biomarkers, which are of main interest in our study, the model we developed is also able to identify biomarker genes with other patterns.…”

Recent Advances of Artificial Intelligence Applications in Interstitial Lung Diseases

“…Based on the analysis of approximately 300 patients, the authors reported 674 CHP biomarkers with an ultimate aim to facilitate precise gene therapy for CHP. In a similar approach that was recently published, Li et al [ 28 ] identified a six-gene subset whose expression was significantly different in patients with IPF compared to healthy controls. A random forest algorithm was used upon a set of more than 600 patients, yielding an AUC of 0.856.…”