GPKB- for Gene Disease Identification and Medical Diagnosis using MF, CC, BF, Micro RNA and Transcription Factors

Abstract

Multiple genomic and proteomic semantic annotations scattered in many
distributed and heterogeneous data sources; such heterogeneity and dispersion hamper
the biologists’ ability of asking global queries and performing global evaluations. To
overwhelm this problem, we developed a software planning to create and maintain a
Genomic and Proteomic Knowledge Base (GPKB), which integrates several of the most
relevant sources .Gene Ontology (GO) is a structured repository of concepts that are
associated to one or more gene products through a process referred to as annotation.
There are different method of analysis to get bio information. One of the method is the use
of Association Rules (AR) which discovers biologically applicable associations between
terms of GO. In existing work we used GO-WAR (Gene Ontology-based Weighted
Association Rules) for extracting Weighted Association Rules from ontology- based
annotated datasets. We here adapt the MOAL algorithm to mine cross-ontology association
rules, i.e. rules that involve GO terms present in the three sub- ontologies of GO. We are
proposing cross ontology to manipulate the Protein values from three sub ontologies for
identifying the gene attacked disease. Also our proposed system, focus on intrinsic and
extrinsic. Based on cellular component, molecular function and biological process values
intrinsic and extrinsic values would be calculated. For each proteomic analysis for every
gene disease, we analyze OMIM id, disease caused by, associated genes, medicine if
available, and images of that particular gene disorder. Thus a common man also would be
able to understand the membranes and enzymes associated for his / her gene disorder and
able to identify intrinsic and extrinsic factors. In this Paper, We done the Co-Regulatory
modules between miRNA (microRNA), TF (Transcription Factor) and gene on function
level with multiple genomic data.. We compare the regulations between miRNA-TF
interaction, TF-gene interactions and gene-miRNA interaction with the help of integration
technique. These interaction could be taken the genetic disease like breast cancer, etc..
Iterative Multiplicative Updating Algorithm is used in our paper to solve the optimization
module function for the above interactions. After that interactions, we compare the
regulatory modules and protein value for gene and generate Bayesian rose tree for
efficiency of our result.