Next-Generation Sequencing (NGS) has made it easier to obtain genome-wide sequence data and it has shifted the research focus into genome annotation. The challenging tasks involved in annotation rely on the currently available tools and techniques to decode the information contained in nucleotide sequences. This information will improve our understanding of general aspects of life and evolution and improve our ability to diagnose genetic disorders. Here, we present a summary of both structural and functional annotations, as well as the associated comparative annotation tools and pipelines. We highlight visualization tools that immensely aid the annotation process and the contributions of the scientific community to the annotation. Further, we discuss quality-control practices and the need for re-annotation, and highlight the future of annotation.
17 September 2025 in IEEE Transactions on Artificial Intelligence
Federated Learning enables decentralized model training across distributed devices while preserving data privacy and reducing communication overhead. However, the presence of heterogeneous client data and noisy labels poses significant challenges, often leading to degraded model performance, especially in communication-constrained environments. In this work, we propose FedRFRL, a robust federated learning framework designed to mitigate the adverse effects of label noise by combining feature regularization and a robust loss function. Specifically, FedRFRL introduces a representation regularization strategy that leverages a high-dimensional projection layer to promote the learning of diverse and discriminative features across clients. Additionally, we incorporate adaptive sharpness-aware minimization (ASAM) to encourage flatter minima for improved generalization under non-IID and noisy settings. Extensive experiments on benchmark datasets, including CIFAR-10, CIFAR-100, SVHN, Fashion-MNIST, and the real-world noisy datasets CIFAR-N and Clothing1M, demonstrate that FedRFRL consistently outperforms existing methods, achieving strong robustness against both symmetric and asymmetric label noise. These results highlight the effectiveness and scalability of FedRFRL in real-world federated learning scenarios with imperfect supervision.