Adjustment of p-Value Expression To Ontology Using Machine Learning For Genetic Prediction, Prioritization, Interaction, And Its Validation In Glomerular Disease

Background: The selection of gene expression mixed to multiple similarity scores of their gene ontology terms (GO), were adjusted by our algorithm as essential prediction tasks for evaluating the regulatory pathways. Moreover applying machine learning techniques, in order to link the gene products into networks that prioritize candidate genes as classification. Finally detecting some significant genetic interactions by applying our algorithm model as validation of the results. Results: : Experimental validation of all associations facilitates the discovery of causative genes known to be related to glomerular diseases (GD). As well as EGR1, IL33, BMP2, SLAMF8. In which their GO annotations related to this gene include kidney vasculature development, regulation of cell activation/ inflammatory/immune effector/adaptive immune/glomerulus/glomerular mesangial cell proliferation development, etc. Other genes as TNXA, FCER1A, NME3, FMOD, BTG2, PTGER4, AXL, CYP1A2, CYTL1, BHLHE40, IFI16, SPON1, ETNPPL, COL14A1, ITGAV, MYOZ2, CAMK2A, SORT1, RANBP1, in which their variants information include complement a set of C3, C4, and C7 measurement, serum IgE/IgA measurement, c-reactive protein measurement, nephrotic syndrome, immune system disease, tuberculosis, glomerular filtration rate, chronic kidney disease, etc. The lasts enable a rapid interpretation of complex gene expression studies. As well, other high-throughput genomics assays illustrate an overview of a computational model for gene prioritization and their genetic interactions. Conclusions: : The furtherance of combining and adjusting the genes expression to multiple similarity scores of their gene ontology (GO) and interacting all possible cross-association of the results reported classification of genes between among to the subject category and validated the abstracts.