DEVELOPMENT OF A GENOMIC DISEASE PREDICTION SYSTEM USING MACHINE LEARNING ALGORITHM
Abstract
ABSTRACT
The rising problem of inherited diseases has posed unimaginable threats to families worldwide. Many of today’s physical, cognitive and behavioural disorders and illnesses that reduce the quality of life of individuals and families can be traced to genetic inheritance. As a solution to this problem, this project aims at the development of a genomic prediction system using Random Forest machine learning algorithm. It focuses on the prediction of Type 2 Diabetes in children based on analysis of their parents’ DNA data. It bridges the gap formed by a lack of non-technical systems for couple genomic prediction through the design of a user-friendly system that accepts both parental inputs. This smart web app presented for the analysis and prediction of disease risks was developed using the following tools to improve result reliability: HTML, CSS, JavaScript, Jinja2, Python, Flask, Werkzeug, Flask-Login, SQLite, SQLAlchemy, Pandas, NumPy, Scikit-Learn, Random Forest, Matplotlib, Seaborn, VCFtools and Git. The findings of this research project have been implemented in this system using object-oriented analysis and design and the prediction results show a high level of accuracy and can serve as a reliable resource for the prediction of DNA based diseases in children in the field of genomic and family healthcare.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.