In this study, we developed an automatic pipeline for molecular dynamics (MD) simulations and a deep learning model for predicting protein-protein binding affinities. The framework will output common post-simulation analyses, including total energy, Root Mean Square Deviation (RMSD), Root Mean Square Fluctuation (RMSF), hydrogen bonds, and salt bridges. It will minimize manual interaction. This tool also integrates a 3D Convolutional Neural Network (CNN) that processes structural features from simulation trajectories to predict binding affinity (pKd and$\Delta G$). We evaluate several model versions with different feature map sizes to balance between predictive accuracy wit hardware requirements. A case study on the human urate transporter GLUT9 (PDB: 8Y65) demonstrates the pipeline's ability to provide rapid, initial insights into protein stability and dynamics. This automated approach serves as a powerful complement to traditional analysis tools. It allows researchers to quickly screen simulation results and identify systems for more detailed investigation.

Deploying multimodal deep learning for Alzheimer's disease (AD) classification in real-world clinical practice remains challenging due to class imbalance, limited data, and computational constraints. We present a robust and efficient CNN-Transformer hybrid framework that integrates cross-modal attention, self-supervised contrastive pretraining, and progressive imbalance mitigation, tailored for clinical neuroimaging. Using the ADNI dataset (744 subjects; CN: 48%, MCI: 34%, AD: 17%), our approach employs adaptive class weighting, label smoothing, and targeted augmentation to address severe imbalance, while an optimized preprocessing pipeline reduces training time by over 97 %. The model achieves 84.3 % accuracy, 88.2 % ROC-AUC, and 85.0 % macro F1, outperforming realistic baselines such as InterFusion$(82.7 \%)$, with sub-2-hour training and 0.05 s inference per case on standard hardware. Extensive ablation confirms the necessity of each component for robust generalization. Limitations include reliance on paired MRI-PET data and single-cohort validation. This study demonstrates that thoughtfully adapted, resource-conscious AI can bridge the gap between research and clinical deployment in neuroimaging.

Molecular Dynamics (MD) simulation is a fundamental exploring approach for numerous scientific fields, including but not limited to drug discovery, biology, material science, and chemistry. Unfortunately, large-scale MD simulation generally requires long-period processing, even in resource-intensive supercomputers. Parallel computing is the primary methodology to accelerate MD simulation. However, parallel computing has a low theoretical improvable ceiling for MD simulation because the atom statuses of one timestep depend on its previous timestep. To unlock the full potential of MD simulation in drug discovery and biology, we propose an AccelMD framework for reducing processing time and computing costs. AccelMD is an AI-enabled framework that accelerates MD simulation while maintaining high predictive accuracy. In order to extend AccelMD's applicability and flexibility, we also developed an extra preprocessing stage, which allows the framework to adapt to various protein inputs automatically. Compared to conventional MD, the AccelMD framework achieves 47.59 X speedup on average (max: 63.78 X, min: 30.61 X). Regarding the prediction accuracy of protein structures, the average Mean Absolute Error (MAE) and TMScore values of AccelMD are 0.0058 and 0.99980, respectively. Our empirical experiments exihibit the robustness of AccelMD framework for the study of complex, long-timescale molecular interactions.

Alzheimer’s disease represents a growing global health concern, emphasizing the need for early diagnosis to mitigate neurocognitive decline. Speech analysis has emerged as a promising, non-invasive approach, yet limited data availability hinders the development of robust Machine Learning (ML) models. To address this challenge, this study exploits the potentialities of Large Language Models (LLMs)—both their ability to generate synthetic data and their capacity to extract complex linguistic features from speech. We employ GPT-4 to generate synthetic transcripts, thus expanding the ADReSS2020 dataset and enhancing its diversity while preserving semantic and structural coherence. Moreover, we propose a novel multilevel feature extraction framework that integrates Bidirectional Encoder Representations from Transformers (BERT) embeddings fine-tuned with linguistic features obtained through Computerized Language Analysis (CLAN). The study involved two experiments: first, to identify the optimal feature extraction strategy and second, to evaluate the impact of synthetic data generated by GPT-4. In both experiments, the performance of five classifiers was evaluated to determine the most effective configuration. Our results demonstrated that fine-tuned BERT embeddings slightly improve classification performance compared to pre-trained models, highlighting the value of domain-specific fine-tuning. Although adding CLAN-like linguistic features yielded limited benefits, GPT-4-generated synthetic data demonstrated promising potential, particularly when combined with sentence embeddings. Classifiers such as Random Forest showed an improvement in accuracy, increasing from 0.79 to 0.88 when using the augmented dataset. This study paves the way for the use of LLMs to expand the diversity of datasets and improve the robustness of ML models in clinical applications.

Alzheimer’s disease (AD) represents a major public health challenge due to its irreversible progression and increasing prevalence among the aging population. Early diagnosis is crucial, and recent advances in Artificial Intelligence and data analytics have shown promising results in detection methods. This study proposes an approach based on deep neural networks for automatic AD detection from the speech data of the ADReSS2020 dataset, using log-Mel spectrogram representation. To address data limitations and enhance model performance, we applied five data augmentation techniques, which significantly improved accuracy by introducing greater variability in audio characteristics. We evaluated the performance of three models: a CNN-LSTM network and two transfer learning approaches based on ResNet50 and VGG16. Experimental results showed that the CNN-LSTM model performs best, achieving an accuracy of 68%, with a significant improvement of 9.67% over the baseline. ResNet50-LSTM and VGG16-LSTM followed with $\mathbf{6 7} \%$ and $\mathbf{6 6} \%$ accuracy, respectively. This work demonstrates the potential of deep learning-based speech-driven approaches as scalable and noninvasive tools for Alzheimer’s diagnosis and highlights the importance of data enhancement to improve model performance.

While deep-learning-enabled recommender systems demonstrate strong performance benchmarks, many struggle to adapt effectively in real-world environments due to limited use of user-item relationship data and insufficient transparency in recommendation generation. Traditional collaborative filtering approaches fail to integrate multifaceted item attributes, and although Factorization Machines account for item-specific details, they overlook broader relational patterns. Collaborative knowledge graph-based models have progressed by embedding user-item interactions with item-attribute relationships, offering a holistic perspective on interconnected entities. However, these models frequently aggregate attribute and interaction data in an implicit manner, leaving valuable relational nuances underutilized.This study introduces the Knowledge Graph Attention Network with Information Fusion (KGIF), a specialized framework designed to merge entity and relation embeddings explicitly through a tailored self-attention mechanism. The KGIF framework integrates reparameterization via dynamic projection vectors, enabling embeddings to adaptively represent intricate relationships within knowledge graphs. This explicit fusion enhances the interplay between user-item interactions and item-attribute relationships, providing a nuanced balance between user-centric and item-centric representations. An attentive propagation mechanism further optimizes knowledge graph embeddings, capturing multi-layered interaction patterns. The contributions of this work include an innovative method for explicit information fusion, improved robustness for sparse knowledge graphs, and the ability to generate explainable recommendations through interpretable path visualization. The implementation and datasets for this study are publicly available1.

As a special type of Knowledge Graph (KG), Continual Knowledge Graph Learning (CKGL) plays a pivotal role in various areas such as recommendation systems, search engines, and personalized services, where knowledge dynamically evolves. A challenging problem in CKGL is catastrophic forgetting, where models forget previously learned knowledge upon being trained on new data. To overcome the challenge, this study proposes Flexible Memory Rotation (FMR), a dual-level regularization technique that focuses on both parameter level and structural level. Our idea is inspired by the natural human learning process, which tends to memorize correctly learned knowledge, leverage the learned to acquire new knowledge, and refine incorrectly learned knowledge with newly obtained information. Commonly, existing regularization-based methods fail to mimic this human nature by having a fixed constraint strategy for all model parameters. To this end, the proposed FMR offers flexible constraints based on qualities of learned knowledge evaluated by the Fisher Information Matrix (FIM). Additionally, we identified a limitation of FIM in CKGL, which is the assumption of independence of time steps does not always hold. To overcome this, FMR rotates the parameter space to diagonalize the FIM. This work has four major contributions: 1) develop a novel regularization technique, FMR, a flexible regularization technique, 2) reveal the unexpected failure of FIM in CKGL and provides an easy remedy via parameter space rotation, 3) the comparison experiments on four benchmark datasets designed for CKGL demonstrates improvement over various state-of-the-art (SOTA) CKGL models, and 4) a comprehensive ablation study investigates each component of the proposed model. The source code is available at https://github.com/lijingzhu1/FMR.

Binding affinity (BA) prediction is important for drug discovery and protein engineering. It seeks to understand the interaction strength between proteins and their ligands (or proteins). This information assists in the design of proteins with enhanced or novel functions, as well as understanding the molecular mechanisms of drug action. This paper presents the development and comparative analysis of two deep learning models, a convolutional neural network (CNN) and a transformer model. Many variants of models in this research were developed using TensorFlow. One model that utilizes ProteinBERT was developed using PyTorch. The CNN model captures local sequence features effectively, while the Transformer model leverages self-attention mechanisms to learn long-range dependencies within the sequences. Protein sequences are the inputs for the models. The sequences are processed using various encoders, like One-hot encoding, Sequence-Statistics-Content, and Position Specific Scoring Matrix. The predicted outputs are Gibbs free energy changes, a key indicator of binding affinity. From this study, both the CNN and transformer models can achieve the same level of accuracy under different conditions. For the CNN model, it can handle full data without sacrificing performance, but it takes much more time to preprocess the features from the protein sequences. The transformer model can achieve the same level of accuracy as the CNN model with no big predictive errors for each protein, but it requires the model to run on less data, which removes some rarely long protein sequences. This study emphasizes the potential of advanced deep learning architectures to enhance the predictive strengths of binding affinity models.

Residue Number Systems (RNS) demonstrate the fascinating potential to serve integer addition/ multiplication-intensive applications. The complexity of Artificial Intelligence (AI) models has grown enormously in recent years. From a computer system’s perspective, ensuring the training of these large-scale AI models within an adequate time and energy consumption has become a big concern. Matrix multiplication is a dominant subroutine in many prevailing AI models, with an addition/multiplication-intensive attribute. However, the data type of matrix multiplication within machine learning training typically requires real numbers, which indicates that RNS benefits for integer applications cannot be directly gained by AI training. The state-of-the-art RNS real-number encodings, including floating-point and fixed-point, have defects and can be further enhanced. To transform default RNS benefits to the efficiency of large-scale AI training, we propose a low-cost and high-accuracy RNS fixed-point representation: Single RNS Logical Partition (S-RNS-Logic-P) representation with Scaling-down Postprocessing Multiplication (SD-Post-Mul) . Moreover, we extend the implementation details of the other two RNS fixed-point methods: Double RNS Concatenation and S-RNS-Logic-P representation with Scaling-down Preprocessing Multiplication . We also design the architectures of these three fixed-point multipliers. In empirical experiments, our S-RNS-Logic-P representation with SD-Post-Mul method achieves less latency and energy overhead while maintaining good accuracy. Furthermore, this method can easily extend to the Redundant Residue Number System to raise the efficiency of error-tolerant domains, such as improving the error correction efficiency of quantum computing.

Heart disease is a leading cause of morbidity and mortality worldwide, necessitating the development of innovative diagnostic methodologies for early detection. This study presents a novel deep convolutional neural network model that leverages Mel-spectrograms to accurately classify heart sounds. Our approach demonstrates significant advancements in heart disease detection, achieving high accuracy, specificity, and unweighted average recall scores (UAR), which are critical factors for practical clinical applications. The comparison of our proposed model's performance with a PANN-based model from a previous study highlights the strengths of our approach, particularly in terms of specificity and UAR. The successful application of Mel-spectrograms in conjunction with deep learning techniques illustrates the potential for widespread clinical adoption of our model, ultimately contributing to early detection and improved patient outcomes. Furthermore, we discuss potential avenues for future research to enhance the model's effectiveness, such as incorporating additional features and exploring alternative deep learning architectures. In conclusion, our deep convolutional neural network model, combined with Mel-spectrograms, offers a significant step forward in the field of heart sound classification and the early detection of heart diseases, demonstrating its potential for real-world clinical applications and improved patient outcomes.

Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving applications. The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples. In this work, we introduce the DG-Labeler and DGL-MOTS dataset to facilitate the training data annotation for the MOTS task and accordingly improve network training accuracy and efficiency. DG-Labeler uses the novel Depth-Granularity Module to depict the instance spatial relations and produce fine-grained instance masks. Annotated by DG-Labeler, our DGL-MOTS dataset exceeds the prior effort (i.e., KITTI MOTS and BDD100K) in data diversity, annotation quality, and temporal representations. Results on extensive cross-dataset evaluations indicate significant performance improvements for several state-of-the-art methods trained on our DGL-MOTS dataset. We believe our DGL-MOTS Dataset and DG-Labeler hold the valuable potential to boost the visual perception of future transportation. Our dataset and code are available here1.