TRAPS: Therapeutic Response Analysis via Pathway-informed Stratification

• URL: http://arxiv.org/abs/2606.09898v1
• Date: Fri, 05 Jun 2026 04:59:09 GMT
• Title: TRAPS: Therapeutic Response Analysis via Pathway-informed Stratification
• Abstract summary: We present the first unified benchmark for pathway-guided therapy response modeling.<n>We evaluate BINN, GraphPath, and PATH across five cancer cohorts from The Cancer Genome Atlas.
• Score: 1.2117611469472138
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cancer treatment planning requires decisions across multiple clinical dimensions at once. Clinicians must determine whether a patient should receive targeted molecular therapy, radiation therapy, and whether they are likely to survive beyond six months. Existing pathway-informed deep learning models have been developed and tested in isolation, making fair comparison across architectures impossible. We present the first unified benchmark for pathway-guided therapy response modeling, evaluating three biologically informed architectures, BINN, GraphPath, and PATH, across five cancer cohorts drawn from The Cancer Genome Atlas, representing 2,622 patients encoded using Reactome pathway activity scores. Each model is trained jointly on all three clinical outcomes under identical data and evaluation conditions, the first study to treat pathway-structured deep learning as a combined therapy and survival prediction problem. Our results show that no single architecture wins across all tasks: PATH performs best for targeted molecular therapy prediction overall, BINN is most reliable for survival prediction, and no model produces useful predictions for radiation therapy, as the key drivers of that decision are clinical variables not captured in gene expression data. Most strikingly, GraphPath achieves an AUROC of 0.92 on prostate targeted molecular therapy prediction, the highest score in the entire benchmark, demonstrating that lateral co-regulation structure produces exceptional discriminative power when matched to a cohort with a narrow targetable driver programme, even under conditions of extreme class imbalance at only 11\% positive prevalence.

Related papers

• Graph Representation Learning of Longitudinal Medical Imaging Trajectories for Treatment Response Prediction [2.9823166626381212]
  In patients with breast cancer, pathological complete response (pCR) has been established as a clinically meaningful surrogate marker for long-term outcomes.<n>We propose an imaging-based 3D-temporal framework for treatment response prediction that integrates a state-of-the-art neural graph with temporal modeling.<n>Our study substantiates the utility of clinically meaningful longitudinal medical imagaging modeling for predicting NACT-induced pCR.
  arXiv  Detail & Related papers  (2026-07-06T10:39:14Z)
• PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities [86.63247982275396]
  PRIME is a missing-aware multimodal self-supervised pretraining framework.<n>It learns robust and transferable representations from partially observed cohorts.<n>We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types.
  arXiv  Detail & Related papers  (2026-04-05T21:14:27Z)
• Leveraging Large Language Models and Survival Analysis for Early Prediction of Chemotherapy Outcomes [0.0]
  Chemotherapy for cancer treatment is costly and accompanied by severe side effects.<n> Predictive models for chemotherapy outcomes using real-world data face challenges.<n>This study addresses these challenges by employing Large Language Models (LLMs) and ontology-based techniques.
  arXiv  Detail & Related papers  (2026-03-12T06:25:12Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• AI-based Prediction of Biochemical Recurrence from Biopsy and Prostatectomy Samples [0.012216782333971603]
  Biochemical recurrence (BCR) after radical prostatectomy is a surrogate marker for aggressive prostate cancer.<n>We trained an AI-based model on diagnostic prostate biopsy slides to predict patient-specific risk of BCR.
  arXiv  Detail & Related papers  (2026-01-28T20:33:15Z)
• Boosted Random Forests for Predicting Treatment Failure of Chemotherapy Regimens [0.0]
  We build treatment failure models based on the Real World Evidence (RWE) gathered from patients' profiles.<n>We report our findings on five primary cancer types with the most frequent treatment failures (or discontinuations)
  arXiv  Detail & Related papers  (2025-12-10T13:49:26Z)
• Semi-Supervised Learning for Dose Prediction in Targeted Radionuclide: A Synthetic Data Study [42.75913504373651]
  Targeted Radionuclide Therapy (TRT) is a modern strategy in radiation oncology that aims to administer a potent radiation dose specifically to cancer cells.<n>Deep learning holds promise for personalizing TRT doses.<n>Current methods require large time series of SPECT imaging, which is hardly achievable in routine clinical practice.
  arXiv  Detail & Related papers  (2025-03-07T12:21:09Z)
• A Large Language Model Pipeline for Breast Cancer Oncology [0.0]
  State-of-the-art OpenAI models were fine-tuned on a clinical dataset and clinical guidelines text corpus for two important cancer treatment factors. A high accuracy (0.85+) was achieved in the classification of adjuvant radiation therapy and chemotherapy for breast cancer patients.
  arXiv  Detail & Related papers  (2024-06-10T16:44:48Z)
• Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction [43.1748594898772]
  We propose a multimodal transformer (PathOmics) integrating pathology and genomics insights into colon-related cancer survival prediction. We emphasize the unsupervised pretraining to capture the intrinsic interaction between tissue microenvironments in gigapixel whole slide images. We evaluate our approach on both TCGA colon and rectum cancer cohorts, showing that the proposed approach is competitive and outperforms state-of-the-art studies.
  arXiv  Detail & Related papers  (2023-07-22T00:59:26Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Exploiting segmentation labels and representation learning to forecast therapy response of PDAC patients [60.78505216352878]
  We propose a hybrid deep neural network pipeline to predict tumour response to initial chemotherapy. We leverage a combination of representation transfer from segmentation to classification, as well as localisation and representation learning. Our approach yields a remarkably data-efficient method able to predict treatment response with a ROC-AUC of 63.7% using only 477 datasets in total.
  arXiv  Detail & Related papers  (2022-11-08T11:50:31Z)
• MIA-Prognosis: A Deep Learning Framework to Predict Therapy Response [58.0291320452122]
  This paper aims at a unified deep learning approach to predict patient prognosis and therapy response. We formalize the prognosis modeling as a multi-modal asynchronous time series classification task. Our predictive model could further stratify low-risk and high-risk patients in terms of long-term survival.
  arXiv  Detail & Related papers  (2020-10-08T15:30:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.