Real-Time Segmentation and Classification of Birdsong Syllables for Learning Experiments

Songbirds are essential animal models for studying neuronal and behavioral mechanisms of learned vocalizations. Bengalese finch (Lonchura striata domestica) songs contain a limited number of

Insertion of rare autism variants in synaptic genes induce novel behavioral phenotypes in C. elegans

Neurodevelopmental conditions and disorders, including autism, involve a complex interplay of genetic, environmental, and developmental factors. Despite this complexity, genetic studies have identified more than

Quinazolinone and Phthalazinone Inhibitors of the HDAC6/Ubiquitin Protein-Protein Interaction

Histone deacetylase 6 (HDAC6) is a class IIb histone deacetylase that regulates diverse cytosolic acetylation through its two catalytic deacetylase domains and a C-terminal zinc

5′ RNA Aminoacylation via Interstrand Acyl-Transfer

The catalytic transformations driving coded protein synthesis revolve around linkage of amino acids to molecules of RNA as 2’/3′-aminoacyl esters. This defining molecular species of

Molecular basis for thermoresponsive protein condensation in plants

Plants continuously experience temperature fluctuations that shape their physiology, development, and survival. Yet, how plants sense and adapt to elevated temperatures at the molecular level

IHGAMP: Pan-cancer HRD prediction from routine H&E whole-slide images using foundation models

December 20, 2025

Homologous recombination deficiency (HRD) confers sensitivity to poly (ADP-ribose) polymerase (PARP) inhibitors and platinum-based chemotherapy, representing a critical biomarker for precision oncology across multiple malignancies. Current HRD assessment relies on next-generation sequencing of genomic scar signatures, but specialized infrastructure requirements, high costs, and prolonged turnaround times limit widespread adoption. These barriers restrict access to HRD testing, particularly in resource-constrained settings where the majority of cancer patients receive care. Pan-cancer HRD prediction has been shown, but robustness across histologies and institutions, leak-safe evaluation, and backbone-dependent generalization remain incompletely characterized. Here we show that IHGAMP (Integrative Histopathology-Genomic Analysis for Molecular Phenotyping), a computational framework using vision transformer foundation models, predicts HRD status from H&E images with an AUROC of 0.766 (95% CI 0.727-0.803) on the TCGA held-out test set using OpenCLIP embeddings, and improves to 0.827 with histopathology-pretrained OpenSlideFM embeddings under the same leak-safe protocol. External evaluation on 927 patients (2,718 whole slide images) from seven independent cohorts demonstrated generalization in adenocarcinoma/serous settings (e.g., CPTAC-LUAD AUROC 0.723) and enabled platinum resistance prediction in PTRC-HGSOC (AUROC 0.673), with attenuation in squamous histologies. Systematic comparison of foundation-model embeddings showed that OpenSlideFM outperformed OpenCLIP internally on TCGA (0.827 vs 0.766 AUROC) and improved external generalization in select cohorts (e.g., CPTAC-LUAD), while performance remained attenuated in squamous histologies; TSS-level embedding norm stability across 710 tissue source sites suggested limited site-driven magnitude shifts. Our findings establish that routine histopathology contains morphology associated with HRD that enables moderate, histology-dependent prediction, supporting a potential screening/triage role to prioritize confirmatory molecular testing where appropriate.

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd. dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registeration number 16808844