Context-based Offline Meta Reinforcement Learning (COMRL) has shown promising results in improving the cross-task generalization ability of meta-policies. However, current methods often lead to entangled task representations, in which each latent dimension is influenced by multiple causal factors that govern variations in environment dynamics and reward mechanisms. This entanglement can degrade generalization performance, particularly when multiple causal factors vary simultaneously across tasks. To address this limitation, we propose CAusally disentangled TAsk representation Learning (CATAL) method for COMRL that aims to improve the generalization ability of the meta-policy, where each latent dimension in the task representations aligns to a single causal factor.Theoretically, we show that under mild conditions, the task representations learned by CATAL are causally disentangled. Empirically, extensive results on multi-task MuJoCo benchmarks show that CATAL consistently outperforms existing COMRL baselines in both in-distribution and out-of-distribution generalization.

Deep learning has become an essential tool for classifying medical images. However, label noise remains pervasive in medical datasets and can severely compromise model robustness and generalization, To address this challenge, we propose Dual-channel Generalized Cross Entropy (DC-GCE), a robust optimization strategy that integrates the standard Generalized Cross Entropy (GCE), which prioritizes the target class, with a newly formulated Reverse Generalized Cross Entropy (RGCE) emphasizing non-target classes. This dual-channel design enables the model to suppress predictions on low-probability incorrect classes (non-target suppression) while concurrently mitigating overfitting to mislabeled samples, thereby enhancing robustness to label noise in medical image classification. We comprehensively evaluate DC-GCE on challenging biomedical microscopy benchmarks (PathMNIST and TissueMNIST from MedMNIST v2) across a wide range of symmetric and asymmetric label noise conditions, simulating both random annotation errors and systematic biases. Experimental results demonstrate that DC-GCE consistently outperforms state-of-theart robust learning methods, achieving superior classification accuracy even under extreme noise (e.g., a 2.89 % improvement over the best baseline at 80 % noise), thereby demonstrating state-of-the-art performance in robust medical image classification.

Large language models have shown promise in biomedical natural language processing, yet their use in extracting structured knowledge from medical scales remains limited. This study introduces MedScaleRE-PF, a novel prompting framework designed for relation extraction in Chinese medical scale texts. The framework combines few-shot in-context learning with retrieval-augmented generation, chain-of-thought prompting, and self-verification strategies to improve contextual understanding and factual consistency. We constructed the CMedS-RE dataset, consisting of 606 full-text articles with 19,051 sentences, 29,359 annotated entities, and 7217 relation instances. Experiments were conducted on two tasks: relational triple extraction (RTE) and relation classification (RC). We evaluated both single-step and multi-step prompting, along with four self-verification strategies: direct (D-SV), stepwise (S-CoT-SV), relation-specific (R-CoT-SV), and stepwise relation-specific (SR-CoT-SV). The best results were achieved with single-step prompting and the R-CoT-SV strategy, yielding F1 scores of 42.58 % for RTE under the 32-shot setting and 65.42 % for RC under the 8-shot setting. Compared to a RAG-only baseline, this configuration improved F1 by 7.59 % on RTE and 1.07 % on RC. Additional experiments demonstrated strong performance under annotation-scarce conditions, achieving 46.99 % F1 on RTE with 20 training articles and 59.87 % on RC with 50 articles. Ablation and error analyses further confirmed that task-specific prompt structure and verification design significantly impact performance under few-shot conditions. MedScaleRE-PF also showed consistent results across multiple LLMs, confirming its stability and generalizability. These findings highlight the effectiveness of combining simple prompting and CoT-inspired verification in domain-specific information extraction. MedScaleRE-PF offers a flexible and structured approach for mining medical scale knowledge and supports prompt-based development in biomedical applications.

Brain transcriptomics provides insights into the molecular mechanisms by which the brain coordinates its functions and processes. However, existing multimodal methods for predicting Alzheimer’s disease (AD) primarily rely on imaging and sometimes genetic data, often neglecting the transcriptomic basis of brain. Furthermore, while striving to integrate complementary information between modalities, most studies overlook the informativeness disparities between modalities. Here, we propose TMM, a trusted multiview multimodal graph attention framework for AD diagnosis, using extensive brain-wide transcriptomics and imaging data. First, we construct view-specific brain regional co-function networks (RRIs) from transcriptomics and multimodal radiomics data to incorporate interaction information from both biomolecular and imaging perspectives. Next, we apply graph attention (GAT) processing to each RRI network to produce graph embeddings and employ cross-modal attention to fuse transcriptomics-derived embedding with each imaging-derived embedding. Finally, a novel true-false-harmonized class probability (TFCP) strategy is designed to assess and adaptively adjust the prediction confidence of each modality for AD diagnosis. We evaluate TMM using the AHBA database with brain-wide transcriptomics data and the ADNI database with three imaging modalities (AV45-PET, FDG-PET, and VBM-MRI). The results demonstrate the superiority of our method in identifying AD, EMCI, and LMCI compared to state-of-the-arts. Code and data are available at https://github.com/Yaolab-fantastic/TMM.

The distinct characteristics of multiomics data, including complex interactions within and across biological layers and disease heterogeneity (e.g., heterogeneity in etiology and clinical symptoms), drive us to develop novel designs to address unique challenges in multiomics prediction. In this paper, we propose the multi-view knowledge transfer learning (MVKTrans) framework, which transfers intra- and inter-omics knowledge in an adaptive manner by reviewing data heterogeneity and suppressing bias transfer, thereby enhancing classification performance. Specifically, we design a graph contrastive module that is trained on unlabeled data to effectively learn and transfer the underlying intra-omics patterns to the supervised task. This unsupervised pretraining promotes learning general and unbiased representations for each modality, regardless of the downstream tasks. In light of the varying discriminative capacities of modalities across different diseases and/or samples, we introduce an adaptive and bi-directional cross-omics distillation module. This module automatically identifies richer modalities and facilitates dynamic knowledge transfer from more informative to less informative omics, thereby enabling a more robust and generalized integration. Extensive experiments on four real biomedical datasets demonstrate the superior performance and robustness of MVKTrans compared to the state-of-theart. Code and data are available at https://github.com/Yaolabfantastic/MVKTrans.

High detail and fast magnetic resonance imaging (MRI) sequences are highly demanded in clinical settings, as inadequate imaging information can lead to diagnostic difficulties. MR image super-resolution (SR) is a promising way to address this issue, but its performance is limited due to the practical difficulty of acquiring paired low- and high-resolution (LR and HR) images. Most existing methods generate these pairs by down-sampling HR images, a process that often fails to capture complex degradations and domain-specific variations. In this study, we propose a domain-distance adapted SR framework (DDASR), which includes two stages: the domain-distance adapted down-sampling network (DSN) and the GAN-based super-resolution network (SRN). The DSN incorporates characteristics from unpaired LR images during down-sampling process, enabling the generation of domain-adapted LR images. Additionally, we present a novel GAN with enhanced attention U-Net and multi-layer perceptual loss. The proposed approach yields visually convincing textures and successfully restores outdated MRI data from the ADNI1 dataset, outperforming state-of-the-art SR approaches in both perceptual and quantitative evaluations. Code is available at https://github.com/Yaolab-fantastic/DDASR.

Multi-omics integration has demonstrated promising performance in complex disease prediction. However, existing research typically focuses on maximizing prediction accuracy, while often neglecting the essential task of discovering meaningful biomarkers. This issue is particularly important in biomedicine, as molecules often interact rather than function individually to influence disease outcomes. To this end, we propose a two-phase framework named GREMI to assist multi-omics classification and explanation. In the prediction phase, we propose to improve prediction performance by employing a graph attention architecture on sample-wise co-functional networks to incorporate biomolecular interaction information for enhanced feature representation, followed by the integration of a joint-late mixed strategy and the true-class-probability block to adaptively evaluate classification confidence at both feature and omics levels. In the interpretation phase, we propose a multi-view approach to explain disease outcomes from the interaction module perspective, providing a more intuitive understanding and biomedical rationale. We incorporate Monte Carlo tree search (MCTS) to explore local-view subgraphs and pinpoint modules that highly contribute to disease characterization from the global-view. Extensive experiments demonstrate that the proposed framework outperforms state-of-the-art methods in seven different classification tasks, and our model effectively addresses data mutual interference when the number of omics types increases. We further illustrate the functional- and disease-relevance of the identified modules, as well as validate the classification performance of discovered modules using an independent cohort.

Brain disease propagation is associated with characteristic alterations in the structural and functional connectivity networks of the brain. To identify disease-specific network representations, graph convolutional networks (GCNs) have been used because of their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks. However, existing GCNs generally focus on learning the discriminative region of interest (ROI) features, often ignoring important topological information that enables the integration of connectome patterns of brain activity. In addition, most methods fail to consider the vulnerability of GCNs to perturbations in network properties of the brain, which considerably degrades the reliability of diagnosis results. In this study, we propose an adversarially trained persistent homology-based graph convolutional network (ATPGCN) to capture disease-specific brain connectome patterns and classify brain diseases. First, the brain functional/structural connectivity is constructed using different neuroimaging modalities. Then, we develop a novel strategy that concatenates the persistent homology features from a brain algebraic topology analysis with readout features of the global pooling layer of a GCN model to collaboratively learn the individual-level representation. Finally, we simulate the adversarial perturbations by targeting the risk ROIs from clinical prior, and incorporate them into a training loop to evaluate the robustness of the model. The experimental results on three independent datasets demonstrate that ATPGCN outperforms existing classification methods in disease identification and is robust to minor perturbations in network architecture. Our code is available at https://github.com/CYB08/ATPGCN.

MOTIVATION: Brain imaging genetics aims to reveal genetic effects on brain phenotypes, where most studies examine phenotypes defined on anatomical or functional regions of interest (ROIs) given their biologically meaningful interpretation and modest dimensionality compared with voxelwise approaches. Typical ROI-level measures used in these studies are summary statistics from voxelwise measures in the region, without making full use of individual voxel signals. RESULTS: In this article, we propose a flexible and powerful framework for mining regional imaging genetic associations via voxelwise enrichment analysis, which embraces the collective effect of weak voxel-level signals and integrates brain anatomical annotation information. Our proposed method achieves three goals at the same time: (i) increase the statistical power by substantially reducing the burden of multiple comparison correction; (ii) employ brain annotation information to enable biologically meaningful interpretation and (iii) make full use of fine-grained voxelwise signals. We demonstrate our method on an imaging genetic analysis using data from the Alzheimer's Disease Neuroimaging Initiative, where we assess the collective regional genetic effects of voxelwise FDG-positron emission tomography measures between 116 ROIs and 565 373 single-nucleotide polymorphisms. Compared with traditional ROI-wise and voxelwise approaches, our method identified 2946 novel imaging genetic associations in addition to 33 ones overlapping with the two benchmark methods. In particular, two newly reported variants were further supported by transcriptome evidences from region-specific expression analysis. This demonstrates the promise of the proposed method as a flexible and powerful framework for exploring imaging genetic effects on the brain. AVAILABILITY AND IMPLEMENTATION: The R code and sample data are freely available at https://github.com/lshen/RIGEA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.