Real-world problems often exhibit complex relationships and dependencies, which can be effectively captured by graph learning systems. Graph attention networks (GATs) have emerged as a powerful and versatile framework in this direction, inspiring numerous extensions and applications in several areas. In this review, we present a thorough examination of GATs, covering both diverse approaches and a wide range of applications. We examine the principal GAT-based categories, including Global Attention Networks, Multi-Layer Architectures, graph-embedding techniques, Spatial Approaches, and Variational Models. Furthermore, we delve into the diverse applications of GATs in various systems such as recommendation systems, image analysis, medical domain, sentiment analysis, and anomaly detection. This review seeks to act as a navigational reference for researchers and practitioners aiming to emphasize the capabilities and prospects of GATs.

Alzheimer’s disease (AD) is now classified as a silent pandemic due to concerning current statistics and future predictions. Despite this, no effective treatment or accurate diagnosis currently exists. The negative impacts of invasive techniques and the failure of clinical trials have prompted a shift in research towards non-invasive treatments. In light of this, there is a growing need for early detection of AD through non-invasive approaches. The abundance of data generated by non-invasive techniques such as blood component monitoring, imaging, wearable sensors, and bio-sensors not only offers a platform for more accurate and reliable bio-marker developments but also significantly reduces patient pain, psychological impact, risk of complications, and cost. Nevertheless, there are challenges concerning the computational analysis of the large quantities of data generated, which can provide crucial information for the early diagnosis of AD. Hence, the integration of artificial intelligence and deep learning is critical to addressing these challenges. This work attempts to examine some of the facts and the current situation of these approaches to AD diagnosis by leveraging the potential of these tools and utilizing the vast amount of non-invasive data in order to revolutionize the early detection of AD according to the principles of a new non-invasive medicine era.

AlphaFold3, the latest release of AlphaFold developed by Google DeepMind and Isomorphic Labs, was designed to predict protein structures with remarkable accuracy. AlphaFold3 enhances our ability to model not only single protein structures but also complex biomolecular interactions, including protein–protein interactions, protein–ligand docking, and protein-nucleic acid complexes. Herein, we provide a detailed examination of AlphaFold3’s capabilities, emphasizing its applications across diverse biological fields and its effectiveness in complex biological systems. The strengths of the new AI model are also highlighted, including its ability to predict protein structures in dynamic systems, multi-chain assemblies, and complicated biomolecular complexes that were previously challenging to depict. We explore its role in advancing drug discovery, epitope prediction, and the study of disease-related mutations. Despite its significant improvements, the present review also addresses ongoing obstacles, particularly in modeling disordered regions, alternative protein folds, and multi-state conformations. The limitations and future directions of AlphaFold3 are discussed as well, with an emphasis on its potential integration with experimental techniques to further refine predictions. Lastly, the work underscores the transformative contribution of the new model to computational biology, providing new insights into molecular interactions and revolutionizing the fields of accelerated drug design and genomic research.

Since December 2019, the coronavirus disease has significantly affected millions of people. Given the effect this disease has on the pulmonary systems of humans, there is a need for chest radiographic imaging (CXR) for monitoring the disease and preventing further deaths. Several studies have been shown that Deep Learning models can achieve promising results for COVID-19 diagnosis towards the CXR perspective. In this study, five deep learning models were analyzed and evaluated with the aim of identifying COVID-19 from chest X-ray images. The scope of this study is to highlight the significance and potential of individual deep learning models in COVID-19 CXR images. More specifically, we utilized the ResNet50, ResNet101, DenseNet121, DenseNet169 and InceptionV3 using Transfer Learning. All models were trained and validated on the largest publicly available repository for COVID-19 CXR images. Furthermore, they were evaluated on unknown data that was not used for training or validation, authenticating their performance and clarifying their usage in a medical scenario. All models achieved satisfactory performance where ResNet101 was the superior model achieving 96% in Precision, Recall and Accuracy, respectively. Our outcomes show the potential of deep learning models on COVID-19 medical offering a promising way for the deeper understanding of COVID-19.

As data become increasingly abundant and diverse, their potential to fuel machine learning models is increasingly vast. However, traditional centralized learning approaches, which require aggregating data into a single location, face significant challenges. Privacy concerns, stringent data protection regulations like GDPR, and the high cost of data transmission hinder the feasibility of centralizing sensitive data from disparate sources such as hospitals, financial institutions, and personal devices. Federated Learning addresses these issues by enabling collaborative model training without requiring raw data to leave its origin. This decentralized approach ensures data privacy, reduces transmission costs, and allows organizations to harness the collective intelligence of distributed data while maintaining compliance with ethical and legal standards. This review delves into FL’s current applications and its potential to reshape IoT systems into more collaborative, privacy-centric, and flexible frameworks, aiming to enlighten and motivate those navigating the confluence of machine learning and IoT advancements.

The integration of human judgment into artificial intelligence (AI) systems has emerged as a key research direction, particularly for high-stakes applications where full automation remains insufficient. Human-in-the-Loop (HITL) AI represents a field that combines machine learning capabilities with human oversight, feedback, and decision-making at various stages of the AI pipeline. This survey provides a systematic review of HITL approaches, covering theoretical foundations, technical methods, ethical considerations, and domain-specific applications. We propose a unified taxonomy that categorizes HITL systems based on loop placement, interaction granularity, and temporal characteristics. This review synthesizes findings from healthcare, autonomous systems, cybersecurity, and other high-risk domains where human oversight is essential. We also examine the challenges of scalability, cognitive load, and trust calibration that affect the practical deployment of HITL systems. The final section outlines open research directions and introduces a framework for designing effective human–AI collaborative systems.