Media of University of Babylon | Pre-Submission Seminar for Master’s Student Shahad Raed Hadi at the Software Department, College of Information Technology

Media of University of Babylon - كلية الطب

Pre-Submission Seminar for Master’s Student Shahad Raed Hadi at the Software Department, College of Information Technology

by : Duhaa Fadill Abbas

Date : 05/5/2025 03:22:10 PM

Veiw : 127

Pre-Submission Seminar for Master’s Student Shahad Raed Hadi at the Software Department, College of Information Technology

Duhaa Fadill Abbas
As part of the academic activities for postgraduate students, the Software Department at the College of Information Technology organized a scientific seminar for master s student Shahad Raed Hadi, under the supervision of Asst. Prof. Dr. Sura Zaki Al-Rashid, to present and discuss her thesis entitled:

“Prediction Consensus (Binding Sites) with Transcription Factor Protein from DNA-Seq Data Using Machine Learning”

The seminar was attended by the scientific committee composed of:

Prof. Dr. Iman Saleh Al-Shammari – Chair
Asst. Prof. Dr. Safa Saad Al-Murayeb – Member
Lecturer Dr. Muhannad Jasim Al-Yasiri – Member
Asst. Prof. Dr. Sura Zaki Al-Rashid – Member and Supervisor

During her presentation, the student provided an in-depth explanation of the research problem, which focuses on predicting transcription factor binding sites (TFBSs) within DNA sequences — a critical subject in understanding gene expression regulation. She highlighted the challenges inherent in this domain, particularly due to the complexity and variability of biological data across different organisms.

To address these challenges, the student proposed a scientific solution by developing a predictive model based on a Convolutional Neural Network (CNN). This model is designed to process raw DNA sequence data directly, eliminating the need for extensive preprocessing steps. The model was trained using data extracted from the AGRIS genomic information database. The experimental results demonstrated high prediction accuracy and superior performance compared to conventional statistical methods.

The student presented the model s design phases, evaluation methodology, and the achieved accuracy, emphasizing the growing role of deep learning techniques in the field of bioinformatics. Her work underlines the potential of these approaches to advance future studies in genome regulation and molecular interaction analysis.