arXiv Machine Learning
Jun 10
TRAPS: Therapeutic Response Analysis via Pathway-informed Stratification
arXiv:2606. 09898v1 Announce Type: new Abstract: Cancer treatment planning requires decisions across multiple clinical dimensions at once.
CMGL: Confidence-guided Multi-omics Graph Learning for Cancer Subtype Classification
CMGL is a confidence‑guided multi‑omics graph learning framework that first estimates modality confidence for each patient using evidential deep learning, then fuses omics data with fixed confidence values and performs classification on a consistency graph. On four cancer‑subtype tasks and a 32‑class pan‑cancer task, CMGL outperforms the strongest baseline by an average of 4.03% accuracy. Its learned representations recover known breast cancer subtypes and transfer to kidney cancer, enabling prognostically distinct patient stratification.
Related stories
arXiv Machine Learning
Jun 2
Interpretable Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification using Multi-Omics Data
arXiv:2503. 22939v4 Announce Type: replace Abstract: The integration of heterogeneous multi-omics datasets at a systems level remains a central challenge for developing analytical and computational models in precision cancer diagnostics.
arXiv Machine Learning
Sep 23
An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction
arXiv:2609.25088v1 Announce Type: cross Abstract: Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these ob...
arXiv Machine Learning
Sep 15
Multi-Modal Tumor Survival Prediction via Graph-Guided Mixture of Experts
arXiv:2609.14072v1 Announce Type: new Abstract: Large Language Models (LLMs) have displayed impressive capabilities in handling tasks that require few demonstration examples, making them effective fe...
arXiv AI
Jul 7
Graph Representation Learning of Longitudinal Medical Imaging Trajectories for Treatment Response Prediction
arXiv:2607. 04912v1 Announce Type: cross Abstract: In patients with breast cancer, pathological complete response (pCR) has been established as a clinically meaningful surrogate marker for long-term outcomes.
arXiv Machine Learning
Aug 11
TRAPS: Treatment-Assignment Prediction via Pathway-informed Stratification
arXiv:2606. 09898v2 Announce Type: replace Abstract: Cancer treatment involves decisions across multiple clinical outcomes, yet pathway-informed deep learning models are typically evaluated in isolation, making their relative benefits unclear.
arXiv Machine Learning
Jun 2
OgBench: A Framework for Evaluating Graph Neural Networks on Omics Data
arXiv:2605. 15511v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning.
arXiv Machine Learning
5d ago
From WSIs to Bulk, Spatial and Single-Cell Transcriptomics via Multi-Scale Graph Neural Networks
The paper presents a Multi‑Scale Graph Neural Network that predicts bulk, spatial, and single‑cell gene expression directly from whole‑slide histopathology images. It uses a Pathology Foundation Model to extract morphological features and builds spatial graphs at patch and cell levels, training on TCGA, Visium, and Xenium data from lung, kidney, and breast tissues. The model achieves accurate slide‑level predictions, moderate patch‑level accuracy (especially on Xenium), and moderate single‑cell correlation, and its outputs are shown to be useful for survival analysis, spatial hazard mapping, and tumor classification.
arXiv Machine Learning
Jul 7
Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer
arXiv:2607. 05306v1 Announce Type: new Abstract: Integrating complex, multi-omics data presents significant challenges.
arXiv AI
Jul 7
Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations
arXiv:2607. 04557v1 Announce Type: cross Abstract: Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles.
arXiv AI
Sep 25
SMILESGNN: Interpretable Clinical Toxicity Prediction via SMILES-Graph Cross-Attention Fusion
SMILESGNN is a multimodal architecture that fuses a SMILES Transformer encoder with a GATv2 graph encoder through cross‑attention, enabling interpretable clinical toxicity predictions. The model retains an explicit graph branch, allowing GNNExplainer to identify substructures linked to toxicity. On the ClinTox dataset it achieves an AUC‑ROC of 0.987 and F1 of 0.906 with only 0.4 M parameters, while on Tox21 it attains a mean AUC‑ROC of 0.750, comparable to strong single‑modality baselines.
arXiv AI
Oct 16
GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal Cancers
GraphBEAT is a temporal graph representation learning framework that bucketizes clinical events from longitudinal electronic health records into time‑ordered graphs, enabling early risk stratification for gastrointestinal cancers. It uses a time‑decay message‑passing mechanism and multi‑head attention pooling to generate patient‑level representations, and was trained on multi‑site diagnosis codes and laboratory tests to predict pancreatic, liver, and intestinal cancer at 12, 24, and 36‑month lead times. Across all experiments, GraphBEAT outperformed baseline graph neural networks and sequence models while requiring far fewer floating‑point operations and parameters.