Abdellah Maatallaoui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abdellah Maatallaoui has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Enrique Barrajón-Catalán
Institute of Research, Development and Innovation in Health Biotechnology of Elche (IDiBE), Universitas Miguel Hernández (UMH), 03202 Elche, Spain
1 shared publication - Hicham Touil
SIGL Laboratory, ENSA Tetouan, UAE University., Morocco
1 shared publication - Ibrahim Maattallaoui
Laboratory of Life and Health Sciences, Faculty of Medicine and Pharmacy of Tangier, Abdelmalek Essaadi University, Tetouan 92000, Morocco
1 shared publication - Larbi Setti
Department of Physics, Polydisciplinary Faculty, UAE, Larach, Morocco
1 shared publication - Mahamadou Sakho
Laboratory of Life and Health Sciences, Faculty of Medicine and Pharmacy, University Abdelmalek Essaâdi, Route de Rabat km 15 Gzenaya BP 365 Tanger, Tetouan 90000, Morocco
1 shared publication - Noureddine El Aouad
Research Team on Natural Products Chemistry and Smart Technologies (NPC-ST), Polydisciplinary Faculty of Larache, University Abdelmalek Essaadi, Tetouan 93000, Morocco
1 shared publication
Latest Publications
- Open Access
Development of QSAR Models and Web Applications for Predicting hDHFR Inhibitor Bioactivity Using Machine Learning
Human dihydrofolate reductase (hDHFR) is a crucial cellular enzyme in folate metabolic pathway, where it catalyzes the reduction of dihydrofolate into tetrahydrofolate (THF) and an important cofactor involved in DNA, RNA, protein biosynthesis and cell proliferation. Due to its importance, hDHFR has become a promising target for therapeutic development, particularly in treating cancer, bacterial infections, and autoimmune diseases. Its inhibition has found clinical value in antitumor, antimicrobial and antiprotozoal treatment; however, the emergence of resistance to existing hDHFR inhibitors necessitates the development of new and more potent compounds. In the current study, we propose a cheminformatics-based approach using machine learning to develop predictive models of hDHFR bioactivity. We used three types of molecular descriptors in the form of fingerprints, i.e., PubChem, Substructure, and MACCS, to capture structural properties associated with hDHFR inhibition. Predictive models were built using a random forest algorithm optimized through hyperparameter tuning. Feature selection was performed using Recursive Feature Elimination (RFE), and dataset dimensionality was reduced by removing outliers through Principal Component Analysis (PCA) to optimize model performance and reducing overfitting and weak predictivity. The resulting models are validated through external test sets, domain applicability analysis, and interpretation of influential molecular features via random forest feature importance selection plots and correlation matrix analysis. All three models exhibited strong predictive capabilities, with R-squared (R2) values ranging from 0.9849 to 0.9934 for the training set and 0.9381 to 0.9591 for the test set. These final predictive models were further incorporated into an accessible web application, enabling users to estimate the bioactivity of new compounds targeting hDHFR.
Open AccessDevelopment of QSAR Models and Web Applications for Predicting hDHFR Inhibitor Bioactivity Using Machine Learning
Human dihydrofolate reductase (hDHFR) is a crucial cellular enzyme in folate metabolic pathway, where it catalyzes the reduction of dihydrofolate into tetrahydrofolate (THF) and an important cofactor involved in DNA, RNA, protein biosynthesis and cell proliferation. Due to its importance, hDHFR has become a promising target for therapeutic development, particularly in treating cancer, bacterial infections, and autoimmune diseases. Its inhibition has found clinical value in antitumor, antimicrobial and antiprotozoal treatment; however, the emergence of resistance to existing hDHFR inhibitors necessitates the development of new and more potent compounds. In the current study, we propose a cheminformatics-based approach using machine learning to develop predictive models of hDHFR bioactivity. We used three types of molecular descriptors in the form of fingerprints, i.e., PubChem, Substructure, and MACCS, to capture structural properties associated with hDHFR inhibition. Predictive models were built using a random forest algorithm optimized through hyperparameter tuning. Feature selection was performed using Recursive Feature Elimination (RFE), and dataset dimensionality was reduced by removing outliers through Principal Component Analysis (PCA) to optimize model performance and reducing overfitting and weak predictivity. The resulting models are validated through external test sets, domain applicability analysis, and interpretation of influential molecular features via random forest feature importance selection plots and correlation matrix analysis. All three models exhibited strong predictive capabilities, with R-squared (R2) values ranging from 0.9849 to 0.9934 for the training set and 0.9381 to 0.9591 for the test set. These final predictive models were further incorporated into an accessible web application, enabling users to estimate the bioactivity of new compounds targeting hDHFR.
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-23
The Impact of Radio Frequency (RF) Attacks on Security and Privacy: A Comprehensive Review
With the increasing use of wireless communication technologies, such as Radio Frequency Identification (RFID), Bluetooth Low Energy (BLE), ZigBee, and cellular networks, the risk of Radio Frequency (RF) attacks has become a significant concern for privacy and security. RF attacks can cause severe damage to an individual's privacy by enabling attackers to intercept, modify, or disrupt communication between wireless devices. This paper provides a comprehensive review of the impact of RF attacks on security and privacy. We start by providing an overview of RF attacks and their potential impacts on different types of wireless systems, including RFID/NFC, ADS-B, BLE, ZigBee, cellular networks, satellite communication, and 433/315 MHz communication. We then discuss the factors that determine the risk levels associated with RF attacks, such as the type of attack, the targeted system, and the attacker's resources. Next, we examine the classification of the effects of RF attacks on security and privacy. These effects can be classified into four categories: confidentiality, integrity, availability, and privacy. We discuss the specific effects that RF attacks can have on each of these categories and provide examples of real-world attacks. Finally, we review the potential solutions to address the security and privacy risks associated with RF attacks, including hardware and software-based solutions, as well as best practices for end-users. We also highlight some of the future research directions in this area, such as developing more secure and privacy-preserving wireless protocols and improving the detection and mitigation of RF attacks. Overall, this article aims to provide a comprehensive understanding of the effects of RF attacks on security and privacy and to highlight the importance of addressing these risks in wireless systems.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-23
Open AccessThe Impact of Radio Frequency (RF) Attacks on Security and Privacy: A Comprehensive Review
With the increasing use of wireless communication technologies, such as Radio Frequency Identification (RFID), Bluetooth Low Energy (BLE), ZigBee, and cellular networks, the risk of Radio Frequency (RF) attacks has become a significant concern for privacy and security. RF attacks can cause severe damage to an individual's privacy by enabling attackers to intercept, modify, or disrupt communication between wireless devices. This paper provides a comprehensive review of the impact of RF attacks on security and privacy. We start by providing an overview of RF attacks and their potential impacts on different types of wireless systems, including RFID/NFC, ADS-B, BLE, ZigBee, cellular networks, satellite communication, and 433/315 MHz communication. We then discuss the factors that determine the risk levels associated with RF attacks, such as the type of attack, the targeted system, and the attacker's resources. Next, we examine the classification of the effects of RF attacks on security and privacy. These effects can be classified into four categories: confidentiality, integrity, availability, and privacy. We discuss the specific effects that RF attacks can have on each of these categories and provide examples of real-world attacks. Finally, we review the potential solutions to address the security and privacy risks associated with RF attacks, including hardware and software-based solutions, as well as best practices for end-users. We also highlight some of the future research directions in this area, such as developing more secure and privacy-preserving wireless protocols and improving the detection and mitigation of RF attacks. Overall, this article aims to provide a comprehensive understanding of the effects of RF attacks on security and privacy and to highlight the importance of addressing these risks in wireless systems.