6 November، 2023

 Alaa. A. Razzaq Mahdi Saleh ‘s master’s thesis

Discussion of a master’s thesis in the College of Computer Science and Mathematics – Department of Mathematics Sciences entitled:

(        prediction of secondary structures of protein by combining hidden markov model and artificial neural networks  )

In continuation of the scientific research movement and with the follow-up and presence of the Dean of the College of Computer Science and Mathematics

   Prof. Dr. Duha Bashir Abdullah The esteemed

It was discussed in the discussion room at the Faculty of Computer Science and Mathematics at the University of Mosul on Monday  6-11 – 2023

Master’s thesis by student  Alaa. A. Razzaq Mahdi Saleh

under the Professor Dr. Omar .S. Qasim and Dr .Fatima .M. Hasan

 Protein structure analysis is of utmost importance in understanding the intricate arrangements of the three-dimensional structures of proteins. Accurate determination of the tertiary structures heavily relies on knowledge of the secondary structures. In this master’s thesis, a proposed algorithm called Combining Hidden Neural (CHN) is presented, which combines Hidden Markov Models (HMM) and Artificial Neural Networks (ANN) to predict the protein’s secondary structure (PSSP). The processing mechanism of the CHN method involves merging the emission matrix of the HMM model with the encoding schemes of the ANN to generate common features between HMM and ANN, thereby enhancing the training process. Zero values in the emission matrix are preprocessed using Fuzzy Logic concepts. Experimental results demonstrate that the CHN algorithm outperforms traditional methods and exhibits remarkable flexibility in handling diverse datasets, achieving notable accuracy with prediction rates of up to 80% when applied to the Intersect-Pieces and Rots-Sander datasets. Furthermore, the algorithm achieves a prediction rate of 90% when evaluated using the RS126 dataset, surpassing some previous studies. These results shed light on the significant advancements offered by the CHN algorithm in the field of protein structure prediction, contributing to a deeper understanding of protein structures and their associated functions.

The scientific committee included the following members :

 Prof. Dr. Ban Ahmed Hassan   – Chairman

Prof. Dr. Abdul Ghafour Jassim Salim  – Member

Assistant Professor Muthana Subhi Suleiman – Member

Prof. Dr. Omar .S. Qasim –   member and supervisor

Dr .Fatima .M. Hasan –   member and supervisor

Share

Share