Location
https://ccse.kennesaw.edu/computing-showcase/cday-programs/fall23program.php
Document Type
Event
Start Date
30-11-2023 4:00 PM
Description
The two main goals of this research are to apply machine learning models in computational biology to classify DNA sequences from different species and to create synthetic DNA sequences using GANs. Generative Adversarial Networks (GANs) synthesize DNA sequences while preserving key characteristics like sequence length and GC content. The dataset is enhanced by these artificial sequences, which makes classification jobs better. The classification accuracy of black rat and human genome sequences is evaluated using machine learning models, including Random Forest, SVM, and Logistic Regression. Notably, when trained with synthetic data, all models perform better.
Included in
GR-504 Synthetic DNA Sequence Generation and Classification for Species Discrimination
https://ccse.kennesaw.edu/computing-showcase/cday-programs/fall23program.php
The two main goals of this research are to apply machine learning models in computational biology to classify DNA sequences from different species and to create synthetic DNA sequences using GANs. Generative Adversarial Networks (GANs) synthesize DNA sequences while preserving key characteristics like sequence length and GC content. The dataset is enhanced by these artificial sequences, which makes classification jobs better. The classification accuracy of black rat and human genome sequences is evaluated using machine learning models, including Random Forest, SVM, and Logistic Regression. Notably, when trained with synthetic data, all models perform better.