AI and Cancer Research ── Cancer biology ── 2026-11-16
Cancer molecular biology and AI
- Abstract
Explainable deep survival modeling remains challenging due to the performance-explainability trade-off in prognostic models and the gap between feature importance and biological abduction. To address these limitations, we present HGS-BioAbductor, a framework that first constructs a biologically embedded hypergraph neural network for accurate survival prediction. Then, from predictive biomarkers and pathways identified by eXplainable Artificial Intelligence (XAI), it leverages a multi-agent-based tournament process to derive novel molecular mechanisms, and the plausibility and novelty of all hypotheses are quantitatively assessed with automatically queried literature. Across 18 independent clinical proteomics/transcriptomics datasets, HGS achieved the highest C-index in 16/18 benchmarks compared to seven other baselines and outperformed interpretable counterparts by a large margin (+0.1-0.2 C-index). Furthermore, in a case study of hepatocellular carcinoma (HCC), the system demonstrates its ability to propose new hypotheses about previously underexplored proteins in HCC prognosis, e.g., PFKFB2, with strong plausibility in the literature (>0.8), and knockdown experiments in Huh7 and MHCC-LM3 cell lines confirmed that PFKFB2 promotes HCC cell proliferation and colony formation. This work bridges data-driven omics discovery with biological interpretability supported by literature, offering an automated and end-to-end paradigm for clinical omics analysis.
Journal IF-equivalent: 9.8 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Chen Y, Zhang Q, Jiang P, Xie L. HGS-BioAbductor: hypergraph-based explainable survival modelling and LLM-based biological hypothesis abduction. npj Precis Onc. 2026 Nov 14 [Epub ahead of print]. doi:10.1038/s41698-026-01764-9.Checked: Abstract only - Abstract
Accurate differentiation between benign parotid gland tumors (BPGT) and malignant parotid gland tumors (MPGT) is of paramount importance for clinical decision-making and treatment planning. Early and precise diagnosis can significantly influence the choice of therapeutic strategies, patient prognosis, and overall survival rates. Given the clinical significance of distinguishing between BPGT and MPGT, the present study aims to develop a nomogram model that integrates clinical information, ultrasound parameters, and radiomics features extracted from gray-scale ultrasound images to differentiate between BPGT and MPGT. Furthermore, the model’s performance will be evaluated using Shapley Additive Explanations (SHAP) analysis. This retrospective and prospective study examined grayscale ultrasound images from 425 patients diagnosed with parotid gland tumors. 242 patients from Center1 and Center2 constituted the training cohort (including 197 BPGT and 45 MPGT), while 104 patients from Center3 served as the external validation cohort (including 80 BPGT and 24 MPGT). Additionally, 79 patients were prospectively collected from three centers (including 63 BPGT and 16 MPGT) for the prospective validation cohort. Clinic model was developed using clinical data and ultrasound visual information. Radiomics features were extracted from the grayscale ultrasound images to construct radiomics models and corresponding Rad-score. Integrating the Rad score and clinical factors, through multiple logistic regression analysis, to draw a nomogram. These models’ performance was evaluated utilizing receiver operating characteristic (ROC) curve analysis, calibration curves, decision curve analysis (DCA), and the Hosmer-Lemeshow (HL) test. Additionally, SHAP analysis was employed to enhances interpretability in the Rad mode by quantifying and visualizing the impact of each feature on predictions, providing clear insights into model behavior. Four ultrasound visual features were selected using logistic regression (LR) to develop the clinical model, while nineteen features were ultimately chosen from the grayscale ultrasound images through feature screening to construct the radiomics (Rad) model. In the external and prospective validation cohort, compared with Clinic (ACC = 0.769 and 0.785) and Rad (ACC = 0.827 and 0.810), the nomogram showed the best discriminative ability (ACC = 0.817 and 0.848). The nomogram model integrating clinical features and radiomics features constructed in this study has demonstrated higher accuracy and robustness in differentiating BPGT and MPGT. SHAP analysis has enhanced the transparency and interpretability of the model. The model not only support clinical diagnosis and help reduce unnecessary biopsies and surgeries, but also lay the foundation for future multimodal precise diagnosis of parotid gland tumors.
Journal IF-equivalent: 4.8 (OpenAlex 2-year mean citedness, value as of 2026-11-12, retrieved 2026-11-13; not the official Clarivate IF)Reference: Mao Y, Peng XQ, Jiang LP, Diao YH, Wang JL, Chen FQ, et al. Interpretable machine learning model based on gray-scale ultrasound image for noninvasive prediction of BPGT and MPGT. BMC Cancer. 2026 Nov 14 [Epub ahead of print]. doi:10.1186/s12885-026-17264-9.Checked: Abstract only - Abstract
Nature Cancer, Published online: 13 November 2026; doi:10.1038/s43018-026-01270-8 Fan et al. propose an artificial intelligence model to infer spatial proteomic patterns at the single-cell level from routine hematoxylin and eosin slides to predict molecular biomarkers, prognosis and immunotherapy response in multiple cohorts.
Journal IF-equivalent: 21.7 (OpenAlex 2-year mean citedness, value as of 2026-11-13, retrieved 2026-11-15; not the official Clarivate IF)Reference: Fan J, Yang S, Hu E, An J, Liu Q, Liu N, et al. The deep learning framework Hist2Prot infers single-cell spatial proteomics from histology to predict biomarkers and clinical outcomes. Nat Cancer. 2026 Nov 13 [Epub ahead of print]. doi:10.1038/s43018-026-01270-8.Checked: Abstract only - Abstract
Systematic review and meta-analysis of diagnostic test accuracy of artificial intelligence on routine haematoxylin and eosin slides for homologous recombination deficiency and BRCA1/2 status in ovarian, breast, prostate and pancreatic cancer, the four cancers in which these results decide PARP-inhibitor eligibility. It pools accuracy by reference standard, compares the models with clinical selection criteria, and estimates the carriers found per 1,000 patients when only 10%, 20% or 30% can be tested.
Journal IF: unknown (could not be matched)Reference: [No authors listed]. Artificial intelligence on routine haematoxylin and eosin slides to prioritise BRCA and homologous recombination deficiency testing in ovarian, breast, prostate and pancreatic cancer: a diagnostic accuracy systematic review and meta-analysis. Open Science Framework. [Epub ahead of print]. doi:10.17605/osf.io/xud4t.Checked: Abstract only