Browsing by Author "Al-Sadek A.F."

Now showing 1 - 3 of 3

Applying machine learning techniques for classifying cyclin-dependent kinase inhibitors
(Science and Information Organization, 2018) Abdelbaky I.Z.; Al-Sadek A.F.; Badr A.A.; Agricultural Research Center; Cairo; Egypt; Computer Science Department; October University for Modern Sciences and Arts; MSA; Egypt; Computer Science department; Faculty of Computers and Information; Cairo University Cairo; Egypt
The importance of protein kinases made them a target for many drug design studies. They play an essential role in cell cycle development and many other biological processes. Kinases are divided into different subfamilies according to the type and mode of their enzymatic activity. Computational studies targeting kinase inhibitors identification is widely considered for modelling kinase-inhibitor. This modelling is expected to help in solving the selectivity problem arising from the high similarity between kinases and their binding profiles. In this study, we explore the ability of two machine-learning techniques in classifying compounds as inhibitors or non-inhibitors for two members of the cyclin-dependent kinases as a subfamily of protein kinases. Random forest and genetic programming were used to classify CDK5 and CDK2 kinases inhibitors. This classification is based on calculated values of chemical descriptors. In addition, the response of the classifiers to adding prior information about compounds promiscuity was investigated. The results from each classifier for the datasets were analyzed by calculating different accuracy measures and metrics. Confusion matrices, accuracy, ROC curves, AUC values, F1 scores, and Matthews correlation, were obtained for the outputs. The analysis of these accuracy measures showed a better performance for the RF classifier in most of the cases. In addition, the results show that promiscuity information improves the classification accuracy, but its significant effect was notably clear with GP classifiers. � 2018 International Journal of Advanced Computer Science and Applications.
Improving classical scoring functions using random forest: The non-additivity of free energy terms’ contributions in binding
(Blackwell Publishing Ltd, 2018) Afifi K.; Al-Sadek A.F.; Department of Computer Science; Modern Sciences and Arts University; Giza; Egypt; Central Lab for Agricultural Experts Systems; Ministry of Agriculture and Land Reclamation; Giza; Egypt
Despite recent efforts to improve the scoring performance of scoring functions, accurately predicting the binding affinity is still a challenging task. Therefore, different approaches were tried to improve the prediction performance of four scoring functions (x-score, vina, autodock, and rf-score) by substituting the linear regression model of classical scoring function by random forest to examine the performance improvement if an additive functional form is not imposed, and by combining different scoring functions into hybrid ones. The datasets were derived from the PDBbind-CN database version 2016. When evaluating the original scoring functions on the generic dataset, rf-score has outperformed classical scoring functions, which shows the superiority of descriptor-based scoring functions. Substituting linear regression as a linear model by random forest as a nonlinear model had largely improved the scoring performance of autodock and vina while x-score had only a slight performance increase. All hybrid scoring functions had only a slight improvement�if any�on both of the combined scoring functions, which is not worth the slower calculation time. � 2018 John Wiley & Sons A/S
Rule-based approach for enhancing the motion trajectories in human activity recognition
(2010) Hassan S.M.; Al-Sadek A.F.; Hemayed E.E.; Computer Science Dept.; October University for Modern Sciences and Arts; MSA; Egypt; Computer Engineering Dept.; Faculty of Engineering; Cairo University; Giza; Egypt
In this paper, we propose a rule-based system for semantically understanding and analyzing the motion of the trajectories of the human activity. The proposed system can be used as a preprocessing phase for enhancing the object detection process. Detected trajectories are classified into three categories; normal, semi-normal and abnormal trajectories according to the distances between their adjacent points. Abnormal trajectories are removed from the trajectory space. Semi-normal trajectories are broken into small normal trajectories that are linked later to form a longer normal trajectory. The proposed system does not assume a specific trajectory length and hence is more generic than similar trajectory enhancement approaches. The effectiveness of the proposed approach is demonstrated through several experimental results using known human motion datasets. � 2010 IEEE.