AI-Powered Predictive Modeling in DNA Analysis

Presenter

Yeilin M. Landaverde

Campus

Bunker Hill Community College

Sponsor

Paul Kasili, Department of Biology and Chemistry, Bunker Hill Community College

Schedule

Session 2, 11:30 AM - 12:15 PM [Schedule by Time][Poster Grid for Time/Location]

Location

Poster Board A11, Campus Center Auditorium, Row 1 (A1-A20) [Poster Location Map]

Abstract

The ability to get accurate predictions and to interpret genetic data facilitates the identification of potential disease risks, and personalized medicine in a matter of minutes or less. Artificial intelligence (AI) has been pivotal in predictive modeling and DNA analysis. It was inspired by the need to understand the complexity of vast databases to identify patterns and mutations within a patient's genetic information. While analyzing this information, AI makes accurate predictions based on a filtering system. This work explores predictive modeling for DNA analysis, a comprehensive methodology that involves data preprocessing, feature selection, model training, and validation. This process integrates statistical and machine learning techniques to identify patterns in genetic data, enabling the development of accurate predictive models for various applications such as disease risk assessment or forensic analysis. The methodology aims to enhance the understanding of genetic information and improve the precision of predictions based on complex DNA datasets. AtomNet®, an AI platform that Atomwise uses, swiftly screens vast chemical databases, identifying potential drug candidates in a fraction of traditional time. This work further explores the pivotal role of AI in drug discovery, genomics, and protein structure prediction by presenting a case study on Atomwise that showcases Convolutional Neural Networks (CNNs) in action. 

Keywords

Artificial Intelligence, DNA Analysis , Machine Learning

Research Area

Artificial Intelligence

SIMILAR ABSTRACTS (BY KEYWORD)