Accurate diagnosis of Alzheimer’s Disease (AD) is essential for early intervention. Traditional methods relying on single-modality data often fail to capture the complexity of the disease, limiting diagnostic accuracy. Integrating multimodal data, such as structural Magnetic Resonance Imaging (sMRI) and Single Nucleotide Polymorphism (SNP) data, can provide a more comprehensive understanding of AD. However, existing multimodal fusion methods often overlook the intricate relationships among different data types, resulting in suboptimal performance. To address these challenges, we propose a novel graph-based multimodal fusion framework for AD prediction. The framework constructs brain and gene ontology networks using domain-specific prior knowledge from sMRI and SNP data. It leverages Graph Convolutional Networks (GCN) to extract deep features from each modality and employs a cross-attention mechanism to dynamically weigh feature importance across modalities. Additionally, a Correlation-Aware Learning (CAL) module explicitly models inter-modal correlations, enhancing the interpretability and robustness of the fusion. We validate the effectiveness of our framework using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Results show that our framework significantly outperforms traditional methods in classification accuracy and feature representation. Our method enables accurate AD diagnosis by integrating multimodal data and explicitly modeling inter-modal correlations. It enhances the interpretability of multimodal integration and provides new insights into the genetic and structural mechanisms underlying AD, serving as a valuable tool for clinical diagnosis and research in neurodegenerative diseases.

Advances in cryo-electron tomography (cryo-ET) have enabled the visualization of molecules within their native cellular environments in three-dimensions (3D). These visualizations are essential for studying the functions of biological entities in their natural conditions. Recently, deep learning techniques have shown significant success in tackling the challenge of particle detection in cryo-ET data. However, accurately identifying and classifying multi-class molecules remain challenging due to factors like low signal-to-noise ratios and the wide range of particle sizes. In this study, we introduce a novel framework CFNPicker for 3D object detection applied to cryo-ET analysis. A major advantage of our method is the design of central feature network (CFN) to integrate central features across multiple scales, allowing for the accurate detection of both small ( $⩽$200) and large ( $⩾$600) molecules. Additionally, we propose an adaptive weighted sampling training strategy to distinguish the complex noise distribution in the background, reducing false positive particles. We also construct the localization label to explicitly utilize the size and position variations of multi-class protein structures. Compared with existing methods, CFN improves the F1 score for classification by 3.6%, 7.3%, 6.6%, and 5.1% for the four smallest molecules tested respectively, while preserving similar or higher F1 scores for other molecules analyzed.

Accurate identification of critical states and their primary driving factors in complex biological processes is crucial for providing early warning signals of catastrophic shifts. Although existing methods based on dynamic network biomarkers (DNBs) have made some progress, they often fall short in fully utilizing the information from single-sample networks and struggle with the computational challenges posed by ultrahigh-dimensional data. Here, we introduce a comprehensive and rapid single-sample DNB method (crsDNB). It introduces a global community detection process and integrates it with a local network perspective to achieve self-adaptive identification of single-sample DNBs. In addition, it proposes targeted parallel optimization strategies to enhance computational efficiency. Validated using six transcriptomic datasets related to male aging and cancer, the crsDNB successfully identified critical states prior to decisive transitions, achieving significant improvements in both computational and biological significance metrics. Consequently, the crsDNB can identify personalized biomarkers for each sample more accurately and efficiently, providing a powerful new tool for determining critical states in complex biological processes.

Kirsten rat sarcoma viral oncogene homolog (namely KRAS) is a key biomarker for prognostic analysis and targeted therapy of colorectal cancer. Recently, the advancement of machine learning, especially deep learning, has greatly promoted the development of KRAS mutation detection from tumor phenotype data, such as pathology slides or radiology images. However, there are still two major problems in existing studies: inadequate single-modal feature learning and lack of multimodal phenotypic feature fusion. In this paper, we propose a Disentangled Representation-based Multimodal Fusion framework integrating Pathomics and Radiomics (DRMF-PaRa) for KRAS mutation detection. Specifically, the DRMF-PaRa model consists of three parts: (1) the pathomics learning module, which introduces a tissue-guided Transformer model to extract more comprehensive and targeted pathological features; (2) the radiomics learning module, which captures the generic hand-crafted radiomics features and the task-specific deep radiomics features; (3) the disentangled representation-based multimodal fusion module, which learns factorized subspaces for each modality and provides a holistic view of the two heterogeneous phenotypic features. The proposed model is developed and evaluated on a multi modality dataset of 111 colorectal cancer patients with whole slide images and contrast-enhanced CT. The experimental results demonstrate the superiority of the proposed DRMF-PaRa model with an accuracy of 0.876 and an AUC of 0.865 for KRAS mutation detection.