Major Depressive Disorder (MDD) is a common mental disorder, and making an early and accurate diagnosis is crucial for effective treatment. Functional Connectivity Network (FCN) constructed based on functional Magnetic Resonance Imaging (fMRI) have demonstrated the potential to reveal the mechanisms underlying brain abnormalities. Deep learning has been widely employed to extract features from FCN, but existing methods typically operate directly on the network, failing to fully exploit their deep information. Although graph coarsening techniques offer certain advantages in extracting the brain's complex structure, they may also result in the loss of critical information. To address this issue, we propose the Multi-Granularity Brain Networks Fusion (MGBNF) framework. MGBNF models brain networks through multi-granularity analysis and constructs combinatorial modules to enhance feature extraction. Finally, the Constrained Attention Pooling (CAP) mechanism is employed to achieve the effective integration of multi-channel features. In the feature extraction stage, the parameter sharing mechanism is introduced and applied to multiple channels to capture similar connectivity patterns between different channels while reducing the number of parameters. We validate the effectiveness of the MGBNF model on multiple classification tasks and various brain atlases. The results demonstrate that MGBNF outperforms baseline models in terms of classification performance. Ablation experiments further validate its effectiveness. In addition, we conducted a thorough analysis of the variability of different subtypes of MDD by multiple classification tasks, and the results support further clinical applications.

Developing generalizable seizure prediction models across patients is clinically imperative but challenged by significant inter-subject EEG variability. Prevailing methods still yield poor cross-patient accuracy, failing to overcome this barrier. To address this, we propose dual attention learning on crossfrequency phase-amplitude coupling networks (CFPAC-DAL) for generalized seizure prediction. Firstly, cross-frequency PAC brain networks were constructed to quantify neurodynamic couplings; next, a dual-attention mechanism for spatial extraction: intra-graph attention learns node interactions within individual networks, and inter-graph attention captures cross-frequency dependencies between distinct PAC graphs; Finally, temporal dynamics are modeled to capture long-range dependencies in EEG sequences. Evaluations on CHB-MIT and Siena datasets show 98.27%/98.24% patient-specific accuracy and 86.28%/81.15% cross-patient accuracy, outperforming the existing state-of-the-art methods, substantiating that dual-attention on cross-frequency PAC networks encodes neural signatures resilient to individual differences, establishing a new paradigm for clinical-ready prediction.

Magnetic resonance imaging (MRI) is of great value in clinical diagnosis due to its ability to present tissue structure and functional information of the brain. However, the acquisition of high-resolution MRI images remains challenging due to constraints in scanning time and hardware limitations. In response, multi-contrast super-resolution (SR) reconstruction has emerged as a promising technique for enhancing image quality. The effectiveness of this approach largely depends on the ability to fully leverage the complementary information across different modalities and to achieve accurate structure matching. To address this challenge, we propose a Mamba-enhanced large-window Transformer network (MC-MambaTrans), which effectively improves the reconstruction accuracy through multi-modal deep feature extraction and structure-guided matching. Specifically, MC-MambaTrans employs the large-window Transformer to model cross-modal multiscale global contextual information, and at the same time introduces the Mamba mechanism-driven coarse-to-fine matching strategy to enhance the guidance of structural information from the reference image slice-by-slice. Ultimately, high-quality SR images are recovered by the multi-scale feature fusion and up-sampling module. Experiments on several publicly available multi-contrast brain MRI datasets show that the method in this paper significantly outperforms the existing state-of-theart methods in terms of reconstruction quality, demonstrating its broad application prospects in medical image reconstruction tasks.

Molecular property prediction is a fundamental yet crucial task. It relies on molecular representation, which involves transforming molecular structures and features into a form that can be processed by computers. Common representation methods can be divided into two perspectives: global and local. However, using molecular representations from a single perspective leads to the problem of models focusing excessively on certain features while neglecting other important information, which limits the model’s generalization ability and accuracy. To address this issue, this paper proposes a Multi-Representation Local-Global Molecular Property Prediction Model (MRLG). This model adopts a multi-branch architecture, deeply integrating SMILES, molecular fingerprints, molecular graphs, and molecular substructure information. First, a Global-Local Fusion (GLF) module is designed, which can integrate multiple representations and generate new, more comprehensive representations. Second, a detailed feature extraction module, Double-Cross Convolution Mould(DCC), is designed for the generated representations. Experiments conducted on various real-world datasets fully validate the effectiveness of the MRLG model. Moreover, results from branch and module ablation experiments further confirm the effectiveness of the proposed method. Overall, our model demonstrates a promising ability to accurately predict molecular properties, offering valuable insights for the design and optimization of novel compounds in various fields of material science and drug development.

The specific binding between antibodies (Ab) and antigens (Ag) is crucial for developing drugs and vaccines to treat major diseases. Therefore, accurate identification of antibody-antigen interactions (AAI) is crucial for a comprehensive understanding of antibody therapeutic mechanisms. While wet-lab methods accurately characterize AAI, they require significant human, financial, and time costs. Traditional computational methods help to reduce the resource consumption of AAI identification, but suffer from several problems, such as (1) they rely solely on sequence data, ignoring critical 3D structural determinants; (2) the scarcity of data on antibody-antigen interactions severely limits existing methods' ability to represent unseen antibodies; (3) they focus narrowly on paratope-epitope residues, overlooking the contextual information provided by distal non-binding regions that can influence interaction patterns. To address these issues, we present an innovative model that learns sequence and structural representations to predict antibody-antigen interactions (SSRAAI). We extracted structural features by constructing contact maps from predicted PDB 3D structures. Additionally, the integration of sequence features based on adaptive relational graphs led to enhanced prediction outcomes. Our approach offers a unique integration of 3D structural information from PDB with sequence data, applied directly to Ab and Ag. Comparative results on two datasets, HIV and SARS-CoV-2, demonstrate the validity of our approach in identifying AAIs.

Integrating multicenter resting-state functional magnetic resonance imaging (fMRI) datasets is essential for computer-aided diagnosis of brain diseases. However, differences in scanners and acquisition protocols lead to heterogeneity of data from different centers. To address this problem, we introduce a novel Centralized Limited Data Sharing (CLDS) framework for multicenter fMRI-based classification, which contains a centralized server and multiple local models, and propose three mechanisms to improve the classification performance. First, aiming at coordinating the global data without favoring any center, an adversarial network is introduced in the centralized server with limited noise-added data uploaded from each center. Second, a Gradient Adaptive Strategy based on the Tasks Association (GASTA) is proposed to restrict the gradient to a desirable direction. Third, a Correction Factor based on the Cosine Similarity (CFCS) is proposed to reduce the impact of non-independent and identically distributed (non-IID) of data on models. The experimental results show that CLDS exhibits superior classification performance to other related methods on the ADHD-200 dataset, with an accuracy of 70.4%. We also extend CLDS to the ABIDE-I dataset with an accuracy of 73.4%, demonstrating that CLDS has the potential for generalizability of other brain diseases and more centers.

This paper focuses on heuristics retrieval in human problem solvingby combining computational cognitive modeling and neuro imaging. An event-related fMRI (functional Magnetic Resonance Imaging) experiment was conducted on a simplified Sudoku puzzle problem solving and an ACT-R (Adaptive Control of Thought-Rational) cognitive model was developed to simulate the information processing processes of heuristics retrieval to solve the problems. We assume that when participants retrieve heuristics, they may conform to a principle of maximizing the information effectiveness and minimizing the cognitive cost. Based on the assumption, the model was built to predict both behavioral performance and neurophysiologic activities. Compared ACT-R predictions with fMRI results, the difference on response time is 0.287 and the average correlation of BOLD (Blood Oxygenation Level-Dependent) response between them is about 0.95. The high fitness supports our assumption. This study shows that heuristics retrieving in human problem solving is an optimizing process in which appropriate information is selected actively through visual selective attention based on goal-oriented to minimize the cost of time and energy. It may shed light on developing a new heuristic search model based on cognition for Web intelligence.