النشر العلمي

  • Multiple Logistic Regression Model for Beta-Turns Prediction

Beta-turns comprise on average of 25% of the residues in all the protein sequence, their formation
plays an important role in protein folding, protein stability and molecular recognition processes. In
this work we have developed a method based on logistic regression (LR) model that uses multiple
sequence alignment or protein profile data for Beta-turns prediction. Using this method we achieved a
Qtotal of 79.8% on BT426 dataset, which is excellent compared to the available successful methods that
are based on either neural network or support vector machine, which are black box predictors. Our LR
model achieved good performance as measured by the Matthews correlation coefficient (MCC = 0.35).
LR also has th

published in Journal of Convergence Information Technology

  • Predicting 𝛽-Turns in Protein Using Kernel Logistic Regression

A 𝛽-turn is a secondary protein structure type that plays a significant role in protein configuration and function. On average 25%
of amino acids in protein structures are located in 𝛽-turns. It is very important to develope an accurate and efficient method for
𝛽-turns prediction. Most of the current successful 𝛽-turns prediction methods use support vector machines (SVMs) or neural
networks (NNs). The kernel logistic regression (KLR) is a powerful classification technique that has been applied successfully in
many classification problems.However, it is often not found in 𝛽-turns classification,mainly because it is computationally expensive.
In this paper, we used KLR to obtain sparse 𝛽-turns prediction in short evolution time. Secondary structure information and
position-specific scoring matrices (PSSMs) are utilized as input features.We achieved 𝑄total of 80.7% and MCC of 50% on BT426
dataset.These results show that KLRmethod with the right algorithmcan yield performance equivalent to or even better than NNs
and SVMs in 𝛽-turns prediction. In addition, KLR yields probabilistic outcome and has a well-defined extension tomulticlass case.

published in BioMed Research International

  • Kernel Logistic Regression Algorithm for Large- Scale Data Classification

Abstract: Kernel Logistic Regression (KLR) is a powerful classification technique that has been applied successfully in many
classification problems. However, it is often not found in large-scale data classification problems and this is mainly because it
is computationally expensive. In this paper, we present a new KLR algorithm based on Truncated Regularized Iteratively Reweighted
Least Squares(TR-IRLS) algorithm to obtain sparse large-scale data classification in short evolution time. This new
algorithm is called Nystrom Truncated Kernel Logistic Regression (NTR-KLR). The performance achieved using NTR-KLR
algorithm is comparable to that of Support Vector Machines (SVMs) methods. The advantage is NTR-KLR can yield
probabilistic outputs and its extension to the multi class case is well defined. In addition, its computational complexity is lower
than that of SVMs methods and it is easy to implement.

published in The International Arab Journal of Information Technology

  • Predicting beta-turns in proteins using support vector machines with fractional polynomials

Abstract
Background: β-turns are secondary structure type that have essential role in molecular recognition, protein
folding, and stability. They are found to be the most common type of non-repetitive structures since 25% of amino
acids in protein structures are situated on them. Their prediction is considered to be one of the crucial problems in
bioinformatics and molecular biology, which can provide valuable insights and inputs for the fold recognition and
drug design.
Results: We propose an approach that combines support vector machines (SVMs) and logistic regression (LR) in a
hybrid prediction method, which we call (H-SVM-LR) to predict β-turns in proteins. Fractional polynomials are used
for LR modeling. We utilize position specific scoring matrices (PSSMs) and predicted secondary structure (PSS) as
features. Our simulation studies show that H-SVM-LR achieves Qtotal of 82.87%, 82.84%, and 82.32% on the BT426,
BT547, and BT823 datasets respectively. These values are the highest among other β-turns prediction methods that
are based on PSSMs and secondary structure information. H-SVM-LR also achieves favorable performance in
predicting β-turns as measured by the Matthew’s correlation coefficient (MCC) on these datasets. Furthermore,
H-SVM-LR shows good performance when considering shape strings as additional features.
Conclusions: In this paper, we present a comprehensive approach for β-turns prediction. Experiments show that
our proposed approach achieves better performance compared to other competing prediction methods.

published in Proteome Science

  • Design & Implementation of a Single-ASIC Based Low cost automatic liquids level control system

Water and liquids tanks had been introduced to us since past centuries ,it has an important and increased role in our daily life .it had been developed and improved across time , and an automated liquids tanks had been manufactured . This paper introduces a design of a low cost automatic liquids level control system that can be used in domestic water tanks , petroleum and industrial tanks .This design is based on using few , small , and low cost electronic components ; it composed from a simple discrete level sensors and a single inverted Set input S-R flip-flop (IS-R FF) Integrated Circuit (IC) . This design is presenting a unique and effective automation model of level control systems ,and it can easily be upgraded to perform more sophisticated tasks ,and also can be integrated with other different systems .

published in International Journal of Computer and Mathematical Sciences

© 2016 University Of Gezira. All rights reserved | Design by Informatics Administration