Federated graph learning (FGL) is a distributive framework for graph representation learning that prioritizes privacy preservation. The right to be forgotten embodies the ethical principle of prioritizing user autonomy over data usage. In the context of FGL, upholding this right requires the method to remove specific entities and their associated knowledge within local subgraphs (Meta Unlearning) and the complete erasure of the entire client (Client Unlearning). We are the first to systematically define the above two unlearn requests in federated graph unlearning. Several studies have attempted to address this challenge, but key limitations persist: incomplete unlearning support and residual knowledge permeation. To this end, we propose a Prototype-guided Adversarial Graph Eraser for universal federated graph unlearning (PAGE), the first unified federated graph unlearning framework that extend to comprehensive unlearning requests. For meta unlearning, we employ the prototype gradients guide initial local unlearn, while adversarial graphs eliminate residual knowledge across the influenced clients. For client unlearning, PAGE exclusively utilizes adversarial graph generation to purge a departed client's influence from the remaining participants. PAGE outperforms existing methods on 8 benchmark datasets. It improves prediction accuracy by 5.08% (client unlearn) and 1.50% (meta-unlearn), with up to 11.84% gain on large-scale graphs. Furthermore, ablation studies confirm its efficacy as a plug-in for other meta unlearn methods, boosting prediction performance up to 4.49% and unlearning performance up to 7.22%.

Graph Neural Networks (GNNs) have become a pivotal framework for modeling graph-structured data, enabling a wide range of applications from social network analysis to molecular chemistry. By integrating large language models (LLMs), text-attributed graphs (TAGs) enhance node representations with rich textual semantics, significantly boosting the expressive power of graph-based learning. However, this synergy introduces critical vulnerabilities in both topology and text. Although specialized attack methods have been designed for each of these aspects, no work has yet unified them into a comprehensive approach. In this work, we propose the Interpretable Multi-Dimensional Graph Attack (IMDGA), a human-centric framework orchestrating multi-level perturbations across graph structure and textual features. IMDGA utilizes three tightly integrated modules to craft attacks that balance interpretability and impact, enabling a deeper understanding of Graph-LLM vulnerabilities. Through rigorous theoretical analysis and comprehensive empirical evaluations on diverse datasets and architectures, IMDGA demonstrates superior interpretability, attack effectiveness, stealthiness, and robustness compared to existing methods. By exposing these underexplored semantic vulnerabilities, our work offers valuable insights for improving Graph-LLM resilience. Our code is available at https://github.com/bwfan-bit/IMDGA.

MOTIVATION: The integration of tumour imaging data and molecular sequencing information can advance our understanding of cancer biology by combining complementary perspectives of tumour phenotype and genotype. However, integrating multi-modal data across heterogeneous and high-dimensional data domains remains a significant computational challenge. RESULTS: Here, we introduce an unsupervised manifold alignment approach for real-world data integration based on Joint Multidimensional Scaling (Joint MDS) and extend it to a three-modality framework (Joint MDS3). We apply this method to integrate radiomic features from magnetic resonance imaging (MRI) with transcriptomic, epigenomic, and copy number variation (CNV) data from patients with glioblastoma multiforme (GBM) and lower-grade gliomas (LGG). Compared to baselines such as Pamona and single-cell optimal transport (SCOTv2), Joint MDS consistently outperforms baseline Pamona in cases and achieves competitive performance relative to baseline SCOTv2, outperforming its fraction of samples closer to an incorrect match (FOSCTTM) in four out of six cases. Joint MDS attains an average label transfer accuracy of 74.8%, approximately 4% higher than that of Pamona and SCOTv2, and reduces FOSCTTM to 51% or less across real-world datasets. We further demonstrate our extension JointMDS3 on both synthetic and real-world examples. Our results highlight the potential of Joint MDS to enhance the integration of diverse data types into a unified representation, ultimately advancing computational approaches in complex diseases. AVAILABILITY AND IMPLEMENTATION: The implementation of our work is available at gitlab.ethz.ch/BMDSlab/publications/oncology/joint-representation-learning-for-oncology-applications and archived at doi.org/10.5281/zenodo.17219404.

Graph Machine Learning is essential for understanding and analyzing relational data. However, privacy-sensitive applications demand the ability to efficiently remove sensitive information from trained graph neural networks (GNNs), avoiding the unnecessary time and space overhead caused by retraining models from scratch.To address this issue, Graph Unlearning (GU) has emerged as a critical solution to support dynamic graph updates while ensuring privacy compliance. Unlike machine unlearning in computer vision or other fields, GU faces unique difficulties due to the non-Euclidean nature of graph data and the recursive message-passing mechanism of GNNs. Additionally, the diversity of downstream tasks and the complexity of unlearning requests further amplify these challenges. Despite the proliferation of diverse GU strategies, the absence of a benchmark providing fair comparisons for GU, and the limited flexibility in combining downstream tasks and unlearning requests, have yielded inconsistencies in evaluations, hindering the development of this domain. To fill this gap, we present OpenGU, the first GU benchmark, where 16 SOTA GU algorithms and 37 multi-domain datasets are integrated, enabling various downstream tasks with 13 GNN backbones when responding to flexible unlearning requests. Through extensive experimentation, we have drawn $10$ crucial conclusions about existing GU methods, while also gaining valuable insights into their limitations, shedding light on potential avenues for future research. Our code is available at \href{https://github.com/bwfan-bit/OpenGU}{https://github.com/bwfan-bit/OpenGU}.

Abstract Background Sarcoidosis is a complex, multisystem inflammatory disease with variable organ involvement and course1. 18F-FDG PET/CT is the gold standard for activity assessment but is costly, scarce, and operator-dependent. Methods We present a fully automated deep-learning pipeline for multi-organ PET/CT quantification, applied to 180 patients with 770 longitudinal scans linked to clinical and laboratory data. Based on contrast-enhanced CT, the lungs, myocardium, spleen, and liver are segmented using TotalSegmentator2; co-registered PET images provide organ-level SUVmax values and metabolic activity scores. Results Pipeline-derived metrics showed strong agreement with clinician assessments of cardiac involvement (for activity, r = 0.93; for SUVmax, r = 0.95, both p < 0.001). Organ-resolved analyses revealed significant correlations between PET metrics and inflammatory biomarkers, particularly in lung involvement (e.g., serum TNF-α, r = 0.39, FDR < 0.05). Using repeated measurements of disease activity and biomarker concentrations, longitudinal modeling captured flare–remission dynamics. Biomarker trajectories paralleled PET activity, supporting their potential as non-invasive surrogate markers when PET/CT is unavailable; in practice, routine lab tests between imaging visits could flag incoming flares and guide early treatment adjustments. Conclusion This automated, organ-resolved PET/CT pipeline, paired with routine labs, enables objective, scalable sarcoidosis profiling beyond tertiary clinics, facilitating early and precise treatment response monitoring and prognostication. References 1. Grunewald J., Grutters J.C., Arkema E.V., Saketkoo L.A., Moller D.R., Müller-Quernheim J. ‘Sarcoidosis.’ Nature Reviews Disease Primers 2019;5(1):45. 2. Wasserthal J., Breit H.C., Meyer M.T., Pradella M., Hinck D., et al. ‘TotalSegmentator: robust segmentation of 104 anatomic structures in CT images.’ Radiology: Artificial Intelligence 2023;5(5):e230024.

MOTIVATION: Acute kidney injury (AKI) is a syndrome that affects a large fraction of all critically ill patients, and early diagnosis to receive adequate treatment is as imperative as it is challenging to make early. Consequently, machine learning approaches have been developed to predict AKI ahead of time. However, the prevalence of AKI is often underestimated in state-of-the-art approaches, as they rely on an AKI event annotation solely based on creatinine, ignoring urine output. We construct and evaluate early warning systems for AKI in a multi-disciplinary ICU setting, using the complete KDIGO definition of AKI. We propose several variants of gradient-boosted decision tree (GBDT)-based models, including a novel time-stacking based approach. A state-of-the-art LSTM-based model previously proposed for AKI prediction is used as a comparison, which was not specifically evaluated in ICU settings yet. RESULTS: We find that optimal performance is achieved by using GBDT with the time-based stacking technique (AUPRC = 65.7%, compared with the LSTM-based model's AUPRC = 62.6%), which is motivated by the high relevance of time since ICU admission for this task. Both models show mildly reduced performance in the limited training data setting, perform fairly across different subcohorts, and exhibit no issues in gender transfer. Following the official KDIGO definition substantially increases the number of annotated AKI events. In our study GBDTs outperform LSTM models for AKI prediction. Generally, we find that both model types are robust in a variety of challenging settings arising for ICU data. AVAILABILITY AND IMPLEMENTATION: The code to reproduce the findings of our manuscript can be found at: https://github.com/ratschlab/AKI-EWS.

Diversified recommendation systems have gained increasing popularity in recent years. Nowadays, the emerged graph neural networks (GNNs) have been used to improve the diversity performance. Although some progresses have been made, existing works purely focus on the user–item interactions and overlook the category information, which limits the capability to capture complex diversification among users or items and leads to poor performance. In this article, our target is to integrate full category information into user and item embeddings. To this end, we propose a diversified GNN-based recommendation systems diversified graph recommendation with contrastive learning (DCL). Specifically, we design three key components in our model: 1) the user–item interaction with category-related sampling enhances the interaction of unpopular items; 2) contrastive learning between users and categories shortens the distance of representations between users and their uninteracted categories; and 3) contrastive learning between items and categories diverges the distance of representations between items and their corresponding categories. By applying these three modules, we build a multitask training framework to achieve a balance between accuracy and diversity. Experiments on real-world datasets show that our proposed DCL achieves optimal diversity while paying a little price for accuracy.

MOTIVATION: Sepsis is a leading cause of death and disability in children globally, accounting for ∼3 million childhood deaths per year. In pediatric sepsis patients, the multiple organ dysfunction syndrome (MODS) is considered a significant risk factor for adverse clinical outcomes characterized by high mortality and morbidity in the pediatric intensive care unit. The recent rapidly growing availability of electronic health records (EHRs) has allowed researchers to vastly develop data-driven approaches like machine learning in healthcare and achieved great successes. However, effective machine learning models which could make the accurate early prediction of the recovery in pediatric sepsis patients from MODS to a mild state and thus assist the clinicians in the decision-making process is still lacking. RESULTS: This study develops a machine learning-based approach to predict the recovery from MODS to zero or single organ dysfunction by 1 week in advance in the Swiss Pediatric Sepsis Study cohort of children with blood-culture confirmed bacteremia. Our model achieves internal validation performance on the SPSS cohort with an area under the receiver operating characteristic (AUROC) of 79.1% and area under the precision-recall curve (AUPRC) of 73.6%, and it was also externally validated on another pediatric sepsis patients cohort collected in the USA, yielding an AUROC of 76.4% and AUPRC of 72.4%. These results indicate that our model has the potential to be included into the EHRs system and contribute to patient assessment and triage in pediatric sepsis patient care. AVAILABILITY AND IMPLEMENTATION: Code available at https://github.com/BorgwardtLab/MODS-recovery. The data underlying this article is not publicly available for the privacy of individuals that participated in the study. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.