Despite the rapid advancements of electrocardiogram (ECG) signal diagnosis and analysis methods through deep learning, two major hurdles still limit their clinical adoption: the lack of versatility in processing ECG signals with diverse configurations, and the inadequate detection of risk signals due to sample imbalances. Addressing these challenges, we introduceVersAtile andRisk-Sensitive cardiac diagnosis (VARS), an innovative approach that employs a graph-based representation to uniformly model heterogeneous ECG signals. VARS stands out by transforming ECG signals into versatile graph structures that capture critical diagnostic features, irrespective of signal diversity in the lead count, sampling frequency, and duration. This graph-centric formulation also enhances diagnostic sensitivity, enabling precise localization and identification of abnormal ECG patterns that often elude standard analysis methods. To facilitate representation transformation, our approach integrates denoising reconstruction with contrastive learning to preserve raw ECG information while highlighting pathognomonic patterns. We rigorously evaluate the efficacy of VARS on three distinct ECG datasets, encompassing a range of structural variations. The results demonstrate that VARS not only consistently surpasses existing state-of-the-art models across all these datasets but also exhibits substantial improvement in identifying risk signals. Additionally, VARS offers interpretability by pinpointing the exact waveforms that lead to specific model outputs, thereby assisting clinicians in making informed decisions. These findings suggest that our VARS will likely emerge as an invaluable tool for comprehensive cardiac health assessment.

Cancer survival analysis commonly integrates information across diverse medical modalities to make survival-time predictions. Existing methods primarily focus on extracting different decoupled features of modalities and performing fusion operations such as concatenation, attention, and Mixture-of-Experts (MoE)-based fusion. However, these methods still face two key challenges: 1) fixed fusion schemes (concatenation and attention) can lead to model over-reliance on predefined feature combinations, limiting the dynamic fusion of decoupled features; and 2) in MoE-based fusion methods, each expert network handles separate decoupled features, which limits information interaction among the decoupled features. To address these challenges, we propose a novel Decoupling-Reorganization-Fusion framework (DeReF), which devises a random feature reorganization strategy between modalities decoupling and dynamic MoE fusion modules. Its advantages are: 1) it increases the diversity of feature combinations and granularity, enhancing the generalization ability of the subsequent expert networks; and 2) it overcomes the problem of information closure and helps expert networks better capture information among decoupled features. Additionally, we incorporate a regional cross-attention network within the modality decoupling module to improve the representation quality of decoupled features. Extensive experimental results on our in-house Liver Cancer (LC) and three widely used public datasets from The Cancer Genome Atlas (TCGA) confirm the effectiveness of our proposed method. Codes are available at https://github.com/ZJUMAI/DeReF.

In this paper, we develop a tensor-based joint multi-dimensional (polarization, angle, and time delay) channel parameter estimation algorithm for single-input multiple-output (SIMO) communication systems equipped with an electromagnetic vector sensor (EMVS) linear array. By considering the EMVS array structure and multi-path propagation environment, the received signals at the base station (BS) are constructed into a third-order parallel factor (PARAFAC) tensor model. By decomposing the constructed tensor, we design a joint structured tensor decomposition algorithm (STDA) and bilinear alternating least squares (BALS) fitting algorithm using the Vandermonde structure of the array to estimate the factor matrices containing angles, polarization, and time delay. Based on the estimated factor matrices, we employ a closed-form algorithm to extract the two-dimensional direction of arrival (2D-DoA), polarization parameters, and time delay. In addition, to provide a quantitative assessment of the proposed algorithm’s performance, we calculate the Cramér-Rao bound (CRB) as a benchmark for comparison. Simulation results indicate that the proposed algorithm achieves superior estimation accuracy and is closer to the CRB compared with the existing tri-polarized algorithms.

Zhuoyun Du, LujieZheng LujieZheng, Renjun Hu, Yuyang Xu, Xiawei Li, Ying Sun, Wei Chen, Jian Wu, Haolei Cai, Haochao Ying. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The automatic and accurate extraction of diverse biomedical relations from literature constitutes the core elements of medical knowledge graphs, which are indispensable for healthcare artificial intelligence. Currently, fine-tuning through stacking various neural networks on pre-trained language models (PLMs) represents a common framework for end-to-end resolution of the biomedical relation extraction (RE) problem. Nevertheless, sequence-based PLMs, to a certain extent, fail to fully exploit the connections between semantics and the topological features formed by these connections. In this study, we presented a graph-driven framework named BioGSF for RE from the literature by integrating shortest dependency paths (SDP) with entity-pair graph through the employment of the graph neural network model. Initially, we leveraged dependency relationships to obtain the SDP between entities and incorporated this information into the entity-pair graph. Subsequently, the graph attention network was utilized to acquire the topological information of the entity-pair graph. Ultimately, the obtained topological information was combined with the semantic features of the contextual information for relation classification. Our method was evaluated on two distinct datasets, namely S4 and BioRED. The outcomes reveal that BioGSF not only attains the superior performance among previous models with a micro-F1 score of 96.68% (S4) and 96.03% (BioRED), but also demands the shortest running times. BioGSF emerges as an efficient framework for biomedical RE.

The increasing popularity of online food blogs and food ordering services has made personalized recipe recommendation a vital aspect of our emotional well-being. However, existing solutions, mainly based on graph neural networks, still face significant challenges, such as (a) focusing on exploiting the user-recipe interactions while neglecting other crucial pairwise and high-order relationships, and (b) failing to explicitly distinguish the distinct factors, e.g., hedonic and healthy, that influence recipe selection. To address these issues, we propose a progressively-passing-then-disentangling approach named P2D. Our approach utilizes a three-stage progressive message-passing mechanism for better representation learning. Specifically, we incorporate the extra pairwise relationships between recipes and nutrients, ingredients, and visual contents to create fine-grained and multimodal recipe representations. We next refine these representations via message passing between high-order recipe relationships to learn people's shared food preferences. Based on them, we could derive comprehensive user representations, which are subsequently transformed into disentangled forms that correspond to various decision factors through contrastive and mutual information regularization. Experimental results demonstrate both the superiority and the rationality of our method: (a) P2D outperforms the state-of-the-art recipe recommendation methods by a large margin under various metrics, (b) ablation studies confirm the positive impact of each of its components, and (c) our visualization analysis empirically supports the advantage of explicitly disentangling decision factors.

Drug Target Interaction (DTI) prediction plays a crucial role in in-silico drug discovery, especially for deep learning (DL) models. Along this line, existing methods usually first extract features from drugs and target proteins, and use drug-target pairs to train DL models. However, these DL-based methods essentially rely on similar structures and patterns defined by the homologous proteins from a large amount of data. When few drug-target interactions are known for a newly discovered protein and its homologous proteins, prediction performance can suffer notable reduction. In this paper, we propose a novel Protein-Context enhanced Master/Slave Framework (PCMS), for zero-shot DTI prediction. This framework facilitates the efficient discovery of ligands for newly discovered target proteins, addressing the challenge of predicting interactions without prior data. Specifically, the PCMS framework consists of two main components: a Master Learner and a Slave Learner. The Master Learner first learns the target protein context information, and then adaptively generates the corresponding parameters for the Slave Learner. The Slave Learner then perform zero-shot DTI prediction in different protein contexts. Extensive experiments verify the effectiveness of our PCMS compared to state-of-the-art methods in various metrics on two public datasets.

BACKGROUND: Large-scale multi-ethnic DNA sequencing data is increasingly available owing to decreasing cost of modern sequencing technologies. Inference of the population structure with such sequencing data is fundamentally important. However, the ultra-dimensionality and complicated linkage disequilibrium patterns across the whole genome make it challenging to infer population structure using traditional principal component analysis based methods and software. RESULTS: We present the ERStruct Python Package, which enables the inference of population structure using whole-genome sequencing data. By leveraging parallel computing and GPU acceleration, our package achieves significant improvements in the speed of matrix operations for large-scale data. Additionally, our package features adaptive data splitting capabilities to facilitate computation on GPUs with limited memory. CONCLUSION: Our Python package ERStruct is an efficient and user-friendly tool for estimating the number of top informative principal components that capture population structure from whole genome sequencing data.

Clinical risk prediction based on Electronic Health Records (EHR) can assist doctors in better judgment and can make sense of early diagnosis. However, the prediction performance heavily relies on effective representations from multi-dimensional time-series EHR data. Existing solutions usually focus on temporal features or inherent relations between clinical event variables or extract both information in two separate phases. This usually leads to insufficient patient feature information and results in poor prediction performance. Moreover, existing methods based on Heterogeneous Graph Neural Network usually require manual selection of proper Meta-Paths. To solve these problems, we propose the Time-aware Context-Gated Graph Attention Network (T-ContextGGAN). Specifically, we design a GNN based module with Time-aware Meta-Paths and self-attention mechanism to extract both temporal semantic information and inherent relations of EHR data simultaneously and perform automatic Meta-Path selection. To evaluate the proposed model, we extract the first 48 hour EHR data in the first Intensive Care Unit (ICU) admission of three different tasks from two open-source datasets and model various clinical variables on the proposed EHRGraph. Extensive experimental results show the proposed model can effectively extract informative features, and outperform existing state-of-art models in terms of various prediction measures. Our code is available in https://github.com/OwlCitizen/TContext-GGAN.

MOTIVATION: DNA methylation is a biological process impacting the gene functions without changing the underlying DNA sequence. The DNA methylation machinery usually attaches methyl groups to some specific cytosine residues, which modify the chromatin architectures. Such modifications in the promoter regions will inactivate some tumor-suppressor genes. DNA methylation within the coding region may significantly reduce the transcription elongation efficiency. The gene function may be tuned through some cytosines are methylated. METHODS: This study hypothesizes that the overall methylation level across a gene may have a better association with the sample labels like diseases than the methylations of individual cytosines. The gene methylation level is formulated as a regression model using the methylation levels of all the cytosines within this gene. A comprehensive evaluation of various feature selection algorithms and classification algorithms is carried out between the gene-level and residue-level methylation levels. RESULTS: A comprehensive evaluation was conducted to compare the gene and cytosine methylation levels for their associations with the sample labels and classification performances. The unsupervised clustering was also improved using the gene methylation levels. Some genes demonstrated statistically significant associations with the class label, even when no residue-level methylation features have statistically significant associations with the class label. So in summary, the trained gene methylation levels improved various methylome-based machine learning models. Both methodology development of regression algorithms and experimental validation of the gene-level methylation biomarkers are worth of further investigations in the future studies. The source code, example data files and manual are available at http://www.healthinformaticslab.org/supp/.