MOTIVATION: Protein-protein interactions (PPIs) are central to cellular functions, and predicting mutation-induced changes in binding affinity (ΔΔG) remains challenging. Although existing computational methods integrate sequence- and structure-derived features and thus implicitly capture certain sequence-structure relationships, they typically fuse these modalities through simple concatenation, without explicitly modeling their multidimensional and multiscale interdependencies. RESULTS: Here, we introduce IGMI, an interpretable graph-based model that explicitly encodes multi-level feature interactions across 1D sequences, 2D contact maps, 3D structures, and residue- and atom-level representations. By recalibrating cross-dimensional and cross-scale dependencies, IGMI enables more accurate estimation of both local and long-range mutation effects. Across multiple benchmark datasets, IGMI consistently outperforms state-of-the-art methods in accuracy, robustness, and interpretability. Macro- and micro-level analyses further reveal biologically plausible patterns, distinguishing direct interface perturbations from indirect structural reorganizations. Complementary analyses under different data splitting strategies indicate that the model learns generalizable affinity-related interaction patterns, rather than relying on split-specific information. IGMI provides a reliable and interpretable framework for modeling mutation-induced affinity changes, supporting applications in protein engineering and therapeutic design. AVAILABILITY AND IMPLEMENTATION: IGMI is implemented in PyTorch and released under an open-source license. The full codebase, training scripts, and evaluation utilities are available at https://github.com/ShiweiWu-545/IGMI.git. An archival snapshot containing all source code, pre-trained weights, processed datasets, and reproducibility scripts is available on Zenodo (https://doi.org/10.5281/zenodo.17563574). CONTACT: [email protected]; [email protected]; [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The control problems are investigated for a stochastic reaction–diffusion system (SRDS) cascaded with an ordinary differential system (ODS). We propose a novel hybrid control strategy that combines boundary control for the SRDS with state feedback control for the ODS. The primary objective is to ensure the cascaded system achieves mean-square exponential stability (MSES). Our research offers a flexible framework for stability analysis and control synthesis in cascaded systems, applicable regardless of the ODS’s inherent stability. We further explore the system’s robust stabilization with uncertainties and its$H_{\infty } $performance to quantify disturbance-rejection capabilities. The key innovations include the development of a unified control framework that accommodates both stable and unstable ODE subsystems, the design of boundary control inputs that ensure MSES even in the presence of parameter uncertainties, and the application of matrix inequality techniques to simplify controller design. The effectiveness of the proposed control strategies is demonstrated by three numerical examples.

Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Lei Li. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This study investigates the stability of reaction-diffusion systems (RDSs) under impulsive disturbances using an event-triggered impulsive control method. Our key contribution is providing Zeno-free conditions for the event-triggered mechanism (ETM), which is crucial due to the potential for impulsive disturbances to trigger the sampling threshold earlier than expected, leading to Zeno behavior. We address this challenge by deriving conditions that ensure the ETM operates without Zeno behavior, essential for practical control implementation. We further derive several sufficient conditions for the asymptotic stability of RDSs based on impulsive control theory. Special cases with specific disturbance rules are also discussed, offering a broader understanding of system stability under various conditions. To demonstrate the applicability of our theoretical findings, we apply our control strategies to an atmospheric pollution model. A numerical example is provided to validate the effectiveness of our approach and to offer theoretical guidance for real-world environmental pollution control.

This article applies output-based event-triggered control (ETC) strategies to nonlinear systems involving impulses and investigates the problem for globally exponential stability (GES). The impulses are not directly related to events and two kinds of control schemes (static and dynamic ETC) are fully considered, respectively. Moreover, the stabilizing and destabilizing impulses can coexist (i.e., hybrid impulses). By employing properties of impulsive system theory and Lyapunov conditions, some theoretical conditions for GES and non-Zeno behavior are derived under static and dynamic event-triggered mechanism, respectively. And the results for stability are different but complementary to each other. Based on the linear matrix inequality, the design criteria of expected triggered mechanism and control gains are derived. Finally, two numerical examples containing simulations are given to demonstrate the effectiveness of the proposed control strategy.

To enhance the effectiveness of metric learning, many methods weight pairs by hard pair mining. Coarsely, hard pair mining consists of two steps. In the first step, it measures the hardness of each pair. After that, in the second step, it assigns higher weights to hard pairs when constructing the loss function. Existing deep metric learning methods focus on the second step. A variety of methods have been developed to weight each pair based on the measured hardness. In contrast, the first step is rarely exploited. We believe that the measurement of hardness in the first step is the foundation for weighting in the second step. Without a reliable hardness measurement, even the best weighting method cannot achieve the optimal performance. The hardness of a pair in existing metric learning methods is simply measured by the distance between two samples' features in the pair, which we believe may not be reliable. In this work, we propose a sensitivity-aware distance measurement (SDM) to enhance the reliability of hardness measurement. SDM augments each sample into a set of samples, and the hardness of a pair is determined by the distance between two samples' augmented sets. The proposed SDM is simple and orthogonal to hard pair mining strategies. It can be plugged in existing methods to improve their effectiveness. Systematic experiments are conducted by plugging SDM in several mainstream distance metric learning methods on three benchmarks for two retrieval tasks. The improvement achieved by SDM demonstrates its effectiveness and versatility.

By exploiting the cross-modal attention, cross-BERT methods have achieved state-of-the-art accuracy in cross-modal retrieval.Nevertheless, the heavy text-image interactions in the cross-BERT model are prohibitively slow for large-scale retrieval.Late-interaction methods trade off retrieval accuracy and efficiency by exploiting cross-modal interaction only in the late stage, attaining a satisfactory retrieval speed.In this work, we propose an inflating and shrinking approach to further boost the efficiency and accuracy of late-interaction methods.The inflating operation plugs several codes in the input of the encoder to exploit the text-image interactions more thoroughly for higher retrieval accuracy.Then the shrinking operation gradually reduces the text-image interactions through knowledge distilling for higher efficiency.Through an inflating operation followed by a shrinking operation, both efficiency and accuracy of a late-interaction model are boosted.Systematic experiments on public benchmarks demonstrate the effectiveness of our inflating and shrinking approach.