Data Analysis on Classifying the Severity of Genetic Mutations

Data Analysis on Classifying the Severity of Genetic Mutations

Presenter(s)

Kelly Laureen Pleiman

Description

Cancer tumors can have thousands of mutations but determining which of those mutations actually contribute to tumor growth is critical in understanding the disease. Through the use of productive models in machine learning, this capstone project focuses on determining the severity of different genetic mutations using available data from Kaggle on the mutation’s gene, variation, and clinical text evidence. By performing data analysis and applying different models on this complex data set, the class or severity of genetic mutations on a scale from 1-9 can be predicted. Decision tree, random forest, SVD, logistic regression, and K nearest neighbor are among the models that were used to classify genetic variation. Obtaining higher model accuracies allows for better classification of genetic mutations and could eventually expedite the time pathologists spend manually classifying mutations.

Publication Date

4-22-2021

Project Designation

Capstone Project

Primary Advisor

Ying-Ju Chen

Primary Advisor's Department

Mathematics

Keywords

Stander Symposium project, College of Arts and Sciences

United Nations Sustainable Development Goals

Industry, Innovation, and Infrastructure

Data Analysis on Classifying the Severity of Genetic Mutations

Share

COinS