Risk Analysis on Genetic Diseases Using ML

  • Sudalaimuthu T, K.Chandana, Azhar Shaik, B.Shivani, S.V.Anusha


The invention of new technologies in the filed of genetic diseases resulted the easiness to treat the genetic diseases.  Among all the foremost daunting tasks within the post-genomic period , one among those is the detection of genes that cause diseases from an outsized amount of genetic data. Complex diseases often present a highly heterogeneous genotype, which makes it difficult to acknowledge biological markers. Machine learning algorithms are commonly want to define such markers, but their success depends heavily on the dimensions and quality of the info available. The machine learning area, which mainly aims to create  algorithms that improve with practice, promises to permit computers to assist people,  analyse big and complex data sets. we developed a supervised methodology of machine learning to predict complex genes that cause diseases and the designed algorithm was experimented that Gene Ontology (GO)-trained machine learning classifiers can enhance and  identify the genes that are involved in complex diseases. The analyzer for genetic diseases, Gentic Diseases Analyzer (GDA) using machine learning have been formulated by using the hybrid model of PCA, Regression, Random Forest, Decision tress algorithms. The GDA was experimented with PCA and Random Forest algorithms and the results are compared. The P-GDA model is provided the accuracy as 97.34% and sensitivity as 96.45% for the GEO dataset. The findings of machine learning approaches and their practical implementation was discussed for the study of genetic and genomic data sets.

Keywords–Machine Learning, Manual testing, Automation testing, Defects, Software, Errors, Regression testing, Testing Methodologies, Verification, Detecting bugs, Test execution

How to Cite
Sudalaimuthu T, K.Chandana, Azhar Shaik, B.Shivani, S.V.Anusha. (2020). Risk Analysis on Genetic Diseases Using ML. International Journal of Advanced Science and Technology, 29(06), 6876 - 6881. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/22419