Morgillo, F. | bioRxiv Science

bioRxiv2026

Targeting the Tumor-Stroma Crosstalk: An AI-Based Virtual Screening Strategy for Dual MET/SMO Inhibitors in Pancreatic Cancer

Pancreatic ductal adenocarcinoma (PDAC) is an aggressive malignancy characterized by a dense desmoplastic tumor microenvironment (TME) that limits drug penetration and promotes immune evasion. Effective treatment, therefore, requires simultaneous modulation of multiple signaling pathways. Here, we describe a directed polypharmacological strategy to identify dual modulators of c-MET and Smoothened (SMO), aiming to disrupt the protective stroma through SMO inhibition while directly suppressing tumor cell survival via c-MET targeting. An AI-guided virtual screening workflow combining the machine-learning platform PyRMD, trained on known c-MET and SMO ligands, with structure-based molecular docking was applied to a library of over 9 million compounds. This approach led to the identification of compound 21, an aminopyrimidine-benzamide-phenoxyquinoline derivative, as a dual c-MET/SMO inhibitor. Biochemical and cellular studies demonstrated that compound 21 selectively binds the SMO orthosteric site (pKi = 5.60), inhibits agonist-induced GLI (Glioma-associated oncogene) signaling (pIC50 = 5.50), and potently suppresses c-MET kinase activity (pIC50 = 6.94). Western blot analyses further revealed that compound 21 promotes ubiquitin-proteasome-mediated degradation of c-MET, eliminating receptor availability and limiting compensatory resistance signaling. In 3D heterotypic models comprising MIAPaCa2 pancreatic cancer cells and CAF154-hTERT fibroblasts, dual inhibition of SMO-mediated stromal support and c-MET-driven tumor progression resulted in greater cytotoxicity than the combination of the selective inhibitors Sonidegib and PHA-665752. Overall, compound 21 overcomes stromal-mediated resistance, enhances tumor cell death, and validates dual SMO/c-MET targeting as a promising single-agent therapeutic strategy for PDAC. One Sentence SummaryAn AI-identified dual SMO/c-MET inhibitor overcomes stromal resistance and degrades c-MET to suppress pancreatic cancer.

cancer biology↗

bioRxiv2025

Knowledge-informed multimodal cfDNA analysis improves sensitivity and generalization in cancer detection

Liquid biopsy offers a minimally invasive opportunity to detect and monitor cancers through analysis of cell-free DNA (cfDNA). However, current approaches face challenges of limited sensitivity at low tumor fractions, technical variability, and poor generalization across cohorts. Tumor-informed targeted methods offer high specificity but suffer from low sensitivity due to random sampling, tumor evolution and adaptation (including resistance mechanisms), and other sources of heterogeneity. Conversely, tumor-naive genome-wide methods can increase sensitivity but often sacrifice specificity, particularly at low tumor fractions. We developed Fragmentomics Analysis for Tumor Evaluation with AI (Fate-AI), a multimodal framework that integrates fragmentomic and methylation-derived features from low-pass whole-genome sequencing (LPWGS) and cell-free methylated DNA immunoprecipitation and high-throughput sequencing (cfMeDIP-seq). It employs a knowledge-informed strategy to select recurrently altered genomic regions and tissue-specific methylation loci to combine the advantages of tumor-naive approaches with the specificity of tumor-informed approaches. This approach derives robust per-sample normalized features that mitigate batch effects and enhance cross-cohort reproducibility. We evaluated Fate-AI on a total of 1,219 plasma samples spanning ten cancer types and healthy controls from multiple laboratories and sequencing centers, including 432 newly profiled cases (280 with both cfMeDIP-seq and LPWGS) together with 787 samples from four independent public datasets. Fate-AI achieved superior sensitivity and specificity compared to state-of-the-art methods, detecting tumor-derived signals at fractions as low as 10-5 in experimental dilutions. Fate-AI scores correlated with disease stage and tracked longitudinal progression, anticipating relapse months before clinical progression. Furthermore, Fate-AI enabled tissue-of-origin classification, with AUCs ranging from 0.84 to 0.97 across six cancer types. Collectively, our results demonstrate that Fate-AI provides a sensitive, generalizable, and clinically actionable platform for early detection, minimal residual disease monitoring, and tissue-of-origin classification, supporting its potential as a liquid biopsy framework in precision oncology.

cancer biology↗