npj Precision Oncology

Progress in precision oncology, including biomarker discovery and individualized treatment selection, is limited by the complexity of clinico-genomic data and the scarcity of large multimodal patient cohorts. Here, we introduce PanoraOnc, a pan-cancer artificial intelligence (AI) model pretrained on real-world clinical, genomic, and imaging data from 84,131 patients spanning 66 cancer types. PanoraOnc enables transferable treatment outcome prediction through pan-cancer pretraining and generalizes to unseen cohorts across cancer types, institutions, and therapeutic settings. Evaluation and fine-tuning were performed on cohorts comprising diverse modalities, including clinical features, targeted gene panels, immunofluorescence imaging, whole-exome sequencing, and transcriptomic profiles. Across these settings, PanoraOnc consistently outperforms statistical, machine-learning, survival, and AI baselines, with the largest improvements observed in zero- and few-shot scenarios, demonstrating that large-scale clinico-genomic pretraining enables robust and generalizable outcome predictions across previously unseen conditions. In addition, PanoraOnc supports biomarker discovery through explainable AI, revealing both established and underappreciated features, including tumor-infiltrating clonal hematopoiesis, oncogenic signaling pathways, and DNA damage response mechanisms in immunotherapy-treated melanoma and non-small cell lung cancer. Furthermore, PanoraOnc enables the identification of patient subgroups potentially benefitting from alternative treatments by estimating personalized treatment outcomes across therapeutic scenarios. These findings establish pan-cancer multimodal pretraining as a scalable paradigm for AI-assisted discovery in precision oncology.

1Accurate subtype diagnosis is essential for guiding therapy and predicting patient outcome in malignant mesothelioma. Most computational pathology models are trained on large tissue images from resection specimens, which maximises information for training but limits model relevance in real-world diagnostic settings where small biopsies are the most usual tissue source. In this work, we assembled a large multicentre cohort of HES- and HPS-stained mesothelioma biopsy slides. We used a self-supervised learning model to evaluate the associations of biopsy-driven morphology patterns with histological subtype, molecular markers, and survival. The discovered histomorphology patterns captured a continuum of tissue phenotypes spanning epithelioid, sarcomatoid, and non-tumour morphologies. Also, patient-level HPC representations achieved excellent performance for distinguishing epithelioid from non-epithelioid mesothelioma (AUC = 0.94) and demonstrated predictive value for immunohistochemistry (IHC) markers. Additionally, HPC-derived features alone achieved performance comparable to established clinical and molecular variables (C-index = 0.65), while integration of HPCs with clinical and marker information improved performance to a C-index of 0.69. Several HPCs were significantly associated with favourable or adverse prognosis and reflected known subtype-specific biological patterns. In conclusion, self-supervised learning can discover interpretable histomorphological phenotypes directly from routine mesothelioma biopsies without further training. These AI-derived phenotypes capture clinically and biologically relevant information, linking tissue architecture to molecular characteristics, histological subtypes, and patient outcomes. The proposed framework provides a thorough evaluation of real-world biopsy data using a pre-trained model, without the need for computationally intensive retraining, and addresses the question of whether SSL-based AI can be deployed out of the box in clinical settings.

Next-generation sequencing (NGS) for the detection of somatic variants has become the method of choice in a variety of molecular oncology fields and in the clinic. Its use ranges from sequencing entire tumor genomes and transcriptomes to targeted clinical diagnostic gene panels. The NYU Langone Genome PACT (Profiling of Actionable Cancer Targets, LG-PACT) assay is a qualitative in vitro diagnostic test that uses targeted next generation sequencing (NGS) of formalin-fixed paraffin-embedded (FFPE) tumor tissue matched with normal specimens from patients to detect gene alterations in a targeted panel covering 606 genes and the TERT promoter. Indications for testing are cancer (solid tumors and hematological malignancies) where a mutational profile from multiple genes would be informative for disease stratification, prognosis, or treatment options including targeted therapies and eligibility for clinical trials. The test is intended to provide information on somatic mutations including point mutations, small insertions/deletions (indels), and copy number aberrations for diagnostic and treatment decisions. LG-PACT is a United States Food and Drug Administration (FDA) cleared diagnostic test (510K: K202304). The clinical interpretation of sequencing data of molecular tumor markers from NGS encompasses automated variant calling tools with human interpretation. This final mostly manual review of data step is intensive, involving highly trained scientists, encompassing literature review, interpretation and clinical tier classification by pathologists, who then provide a complete molecular diagnostic report to the treating oncologists. We provide analysis of 1339 clinical genomic profiles from 31 different cancers and their subtypes, comprising of central nervous system (CNS) 792 (59%) cases (incl. meningioma, glioma and glioblastoma), with 267 (20%) cases predominantly of lung, pancreatic and colorectal and 280 of others (21%). Here, we present the technical challenges of validating an NGS oncological diagnostic targeted assay for clinical grade accuracy and sensitivity for patient care. We show how copy number alterations provide a more comprehensive description of the tumors genomic profile. We then outline the utility of targeted panel sequencing based on certified pathologist selection of reportable variants for our current patient cohort. Where analysis of variant detection has led to 49.4% (661/1339) of our clinical tumor samples containing mutations in known therapy targeted genes, 35.6% (477/1339) with mutation detected in other genes, and 15% (201/1339) cases being negative.

Tumor cellular composition--including malignant cell states, immune populations, and stromal populations--is increasingly recognized as a determinant of therapeutic response and resistance to anti-cancer agents, yet comprehensive cellular profiling remains largely confined to research settings. Here, we present a clinically compatible sample-to-report workflow for tumor composition profiling from routine formalin-fixed paraffin-embedded (FFPE) clinical specimens. By combining low-input single-nucleus RNA sequencing with foundation model- based automated cell annotation, this workflow enables prospective sample-by-sample analysis without dedicated research material or cohort-based processing. Across 116 clinical specimens representing six cancer types, we generated reproducible measurements of cellular composition and cell-type-specific gene expression, demonstrated high technical reproducibility, and showed concordance with pathological assessment of immune infiltration. The workflow was similarly applicable to archival FFPE material and ultra-low-input biopsy specimens. Together, these findings establish a practical framework for routine single-cell profiling from standard pathology specimens and open the perspective of prospective evaluation of cellular composition as a clinical biomarker in precision oncology.

Patient-derived tumor organoids provide a physiologically relevant 3D disease model for preclinical drug discovery, surpassing the limitations of conventional 2D cell lines. To better capture the dynamic nature of organoid drug responses, we developed a new systematic evaluation method called SCOPE (Systematic Classification of Organoids for Phenotypic Evaluation), harnessing phenotypic assessments from multi-timepoint 3D imaging data. By integrating artificial intelligence (AI)-based image analysis of organoid viability with tracking and mathematical modeling of organoid growth over time, we captured temporal-and dose-dependent dynamics of phenotypic changes, culminating in two novel metrics: a combined growth and viability (GV) score as well as a cytostatic-cytotoxic transition range (CCTR) that separates drug effects on organoid growth and viability. Our approach supports classification of specific drug responses into four distinct phenotypic groups: (1) cytotoxic, (2) cytostatic plus cytotoxic, (3) late cytotoxic, and (4) cytostatic. This novel drug evaluation system can identify previously unknown drug effects or new therapeutic use cases for existing drugs, facilitating the design of alternative therapeutic options to overcome efficacy or drug resistance challenges and improving the clinical applicability of organoid-based drug discovery results.

Venetoclax and azacitidine (ven-aza) is a standard of care therapy for newly diagnosed acute myeloid leukemia (AML) patients unfit to receive intensive therapy, and may also be appropriate for certain fit patients. Models predicting response to ven-aza currently focus predominantly on genetics. Here, we present two multimodal fusion models: a custom ResNet-34-based model and a pathology foundation model fine-tuned for bone marrow smear (BMS) images that combine clinical and genetic variables with whole slide images. Training on 193 newly diagnosed AML patients who received ven-aza, we obtained an area-under-the-receiver-operating-characteristic (AUROC) of 0.79 and 0.82 for the ResNet-based and fine-tuned foundation models in a heldout test set, and 0.76 and 0.73 in an external validation set, predicting best response to this therapy. Sensitivity analysis showed that fusing image data with clinical and genetic variables outperformed training on either modality alone. In univariable and multivariable analyses, image-based classification was an independent predictive marker, second only in effect size to IDH1/2 mutation status, outperforming other genetic alterations. Image-based explainability showed high model attention on myeloblasts, suggesting previously unrecognized cell-specific patterns associated with response. Our findings suggest BMS images complement genetic biomarkers to refine outcome prediction in ven-aza treatment and incentivize AI-supported outcome prediction, including bone marrow morphology.

Accurate molecular subtyping of individual cancer patients from somatic mutation data remains a challenge in precision oncology research. Existing network-based stratification (NBS) methods treat all mutations equivalently, require full-cohort batch processing, and do not demonstrate generalization to independent datasets without retraining. To address this, we present variant interpretation via the adaptive network pRopagatION (VARION), which integrates population-level variant constraint scoring with protein-protein interaction (PPI) network topology. The Adaptive Topology-aware Random Walk with Restart (ATR-RWR) algorithm weights each mutated gene by {varphi}g = {surd}(GIS(g) x {rho}topo(g)), where GIS (Gene Intolerance Score) reflects population-level functional constraint, propagated across a shared PPI network; subtype assignment then uses cosine similarity to TCGA-derived reference centroids, enabling real-time single-patient classification. Across ten TCGA cancer cohorts (n = 2,417), VARION achieved 77.7% accuracy for ovarian cancer (OV), 69.5% for glioblastoma (GBM), 90.2% for cholangiocarcinoma (CHOL), and 75.4% for gastric cancer (STAD). A controlled benchmark applying two alternative clustering methods (PyNBS; a dense autoencoder) to identical ATR-RWR propagation matrices recovered no significant driver enrichment (OR = 1.79 and 1.52, n.s.), versus OR = 144.29 (p = 1.77x10^-12) for VARION, confirming that the GIS-weighted centroid architecture, not propagation alone, drives performance; generalization without retraining was further confirmed in two independent cohorts (ICGC CCA, n = 396; PCAWG, n = 110; OR = {infty}, p < 5x10^-9). Together, these results indicate that VARION's GIS-weighted centroid architecture enables individual-patient molecular subtyping that outperforms existing NBS and graph-learning clustering approaches, with high sensitivity for clinically actionable rare subtypes and robust cross-platform generalization.

BackgroundOvarian cancer (OvCa) ranks as the most lethal gynecological malignancy in women worldwide. This complex disease, which can develop independently of a womans age, is characterized by late diagnosis, pronounced tumor heterogeneity, and an immunosuppressive tumor microenvironment (TME). Incremental diagnostic tools that could better inform clinicians on potential therapy resistance or subsets of patients that could benefit from new drug modalities represent a critical unmet need to improve patient care and potentially the identification of new biomarkers. ObjectiveThis study aimed to establish a reconfigurable patient-derived OvCa-on-chip platform for longitudinal functional profiling of tumor cell death, immune activation, and patient-specific responses to TIL-mediated killing, PD-L1 blockade, and sequential chemo-immunotherapy. MethodsPatient-derived OvCa microtumors (PDM) were integrated with sequential integration of autologous tumor-infiltrating lymphocytes (TILs) into a perfusable microfluidic chip in the presence of different single and combination treatment regimens of chemotherapy and immune checkpoint inhibitors (ICIs). Treatment responses were assessed by longitudinal quantification of caspase-cleaved cytokeratin 18 (ccCK18) as marker of apoptotic epithelial tumor cell death, as well as cytokine/chemokine release in chip effluents, and multiplex flow cytometry-based characterization of autologous TIL subsets. ResultsThe perfusable OvCa-on-chip platform supported long-term culture of PDM while maintaining key structural and microenvironmental features of the primary tumor. Multidimensional analyses, including time-resolved assessment of tumor cell death, secretome profiling and correlative analysis of autologous TIL subsets revealed patient-specific tumor-immune response patterns and heterogenous sensitivity to TIL-mediated killing, PD-L1 blockade, and sequential chemo-immunotherapy. Correlation analyses identified treatment-dependent associations between specific TIL phenotypes and functional tumor cell killing. PD-1-expressing CD4 TIL subsets correlated with enhanced tumor cell killing, whereas terminally exhausted CD8PD-1Tcf1- TILs negatively correlated with durvalumab responses. In contrast, tumor-reactive CD8CD39 TILs were associated with improved responses under sequential chemo-immunotherapy conditions. ConclusionCollectively, this OvCa-on-chip system represents a complex in vitro model (CIVM) that combines 3D tumor tissue with autologous immune cells in a microfluidic platform. Resembling a physiologically relevant human preclinical platform, it allows for the time-resolved functional assessment of patient-specific responsiveness to OvCa therapies, with direct implications for personalized treatment stratification.

HER2-directed therapies are expanding across solid tumors, but ERBB2 amplification incompletely captures HER2 expression and pan-tumor IHC lacks standardization. We developed ERBB2 mRNA, bulk HER2 protein and RNA-signature screening benchmarked against IHC/FISH. Screening identified HER2-enriched populations beyond amplification in a pan-tumor discovery cohort of 1,331 tumor biopsies and validated RNA-based screening in an external cohort of 3,898 tumor biopsies. All six objective responses among 51 treated patients in the discovery cohort occurred in tumors positive by ERBB2 mRNA and the combined RNA-signature. In the external dataset (n=102), ERBB2 mRNA positivity was associated with longer time on treatment (hazard ratio 0.42, 95% confidence interval 0.27-0.64) and overall survival (0.41, 0.25-0.65), with concordant associations for the combined RNA signature. Spatial proteomics comprising 2,721 tiles across 88 samples captured HER2 hetero-geneity and identified HER2-enriched profiles below bulk thresholds. These findings support prospective evaluation of RNA and proteomic screening for treatment selection.

Triple-Negative Breast Cancer (TNBC) is characterized by high heterogeneity, poor prognosis, and limited targeted treatment options. Bridging the gap between molecular alterations and histopathological morphology remains a major challenge in precision oncology. We propose an interpretable, multi-modal framework that integrates histopathological image analysis with multi-omics profiling (somatic mutations, DNA methylation, copy number alterations), leveraging U-Net-based nuclei segmentation, vision-language models (BLIP), biomedical language models (BioGPT), and explainable AI (SHAP, LIME). Our framework achieves strong predictive performance (AUC = 0.989) and provides transparent, biologically grounded interpretations by integrating morphological features with genomically prioritized biomarkers. Cross-modal analysis confirms established TNBC drivers and generates novel, testable hypotheses associating specific epigenetic alterations with distinct morphological phenotypes. While causal validation requires future wet-lab experiments, our framework accelerates hypothesis-driven biomarker discovery by integrating complementary data modalities with language-based reasoning, providing a transparent foundation for hypothesis generation and clinical translation.

Background: Liquid biopsy-based monitoring of circulating tumor DNA (ctDNA) holds promises for real-time assessment of tumor burden and treatment response in precision oncology. However, mutation-based approaches alone show limited sensitivity, particularly in low-shedding tumors. We evaluated whether integrating epigenomic biomarkers (specifically LINE-1 retrotransposon (L1PA) hypomethylation and copy number variation (CNV)) with standard mutation-based ctDNA analysis could improve cancer detection and longitudinal monitoring in patients enrolled in the SHIVA02 precision oncology trial. Methods: We performed a retrospective analysis of 32 patients with advanced or metastatic solid tumors who received molecularly matched targeted therapies within the SHIVA02 trial (NCT03084757). Plasma samples were collected at baseline and longitudinally every two months and at progression. Multimodal ctDNA profiling was performed using the DRAGON targeted NGS panel covering SNVs, indels and focal CNVs in 571 genes and the DIAMOND assay profiling L1PA methylation and genome-wide CNV. A three-step classification algorithm integrating maximum variant allele frequency (MaxVAF), L1PA methylation-based cancer probability (MethPCancer), and genome-wide CNV scores was developed to maximize ctDNA detectability. Results: At baseline, mutation-based profiling detected ctDNA in 62.5% of patients. L1PA hypomethylation alone identified ctDNA in 78.1% of patients, including cases with undetectable mutations. The three-step integrative model increased overall detectability to 93.8%. Concordance analyses between tumor tissue and plasma revealed that 80.6% of mutations and 60% of CNVs identified in tumor biopsies were detectable in matched ctDNA. The three modalities showed limited pairwise correlation at baseline, supporting their complementarity. Longitudinal analysis demonstrated that changes in MaxVAF, MethPCancer, and L1PA CNV scores over time were informative on treatment response across tumor types, with ctDNA detected in 94.5% of samples collected at disease progression. In selected patients, ctDNA alterations preceded radiological progression by four months. Conclusions: Multimodal ctDNA profiling integrating mutation analysis, CNV profiling, and LINE-1 hypomethylation substantially improves ctDNA detection at baseline and during treatment in a pan-cancer precision oncology setting. These complementary genomic and epigenomic biomarkers provide a more comprehensive and dynamic assessment of tumor burden than single-modality approaches, supporting prospective validation in larger cohorts for integration into precision oncology workflows.

Introduction: Tumors are known to develop genomic heterogeneity over time, particularly in metastatic disease, raising concerns that a single-site biopsy may be insufficient to accurately predict response to medications. Methods: We used our 3D microtumor functional profiling platform that preserves key features of the native tumor microenvironment. We tested (i) six split samples from primary tumors and (ii) seven samples from primary tumors (ovarian, colon, and breast cancer) matched with their locoregional or distant metastases. Fresh tissue specimens were processed within 24 hours after surgery and treated with NCCN guideline-recommended chemo or targeted therapies at concentrations over four orders of magnitude. Cytotoxicity was evaluated after three days to generate dose response curves. The response correlations between the split sample or between the two matched sites were quantified using the concordance correlation coefficient ({rho}c) for the drug efficacy metrics. Results: We compared a total of 275 drug responses. The six split samples resulted in a strong correlation between the two tumor areas ({rho}c=0.95, p<0.001), supporting high assay reproducibility across distinct regions of the same tumor. Locoregional metastases were highly correlated with their primaries (ovarian to omentum {rho}c=0.97, p<0.001; ovarian to liver capsule {rho}c=0.93, p<0.001; colon to peritoneum {rho}c=0.91, p<0.001). A lesser correlation was observed with lymphogenic metastases (breast to axilla {rho}c=0.87, p<0.001), and the correlations of hematogenic metastases were even lower (colon to lung {rho}c=0.69 p<0.001; ovarian to soft tissue/colon {rho}c=0.58, p<0.001). No correlation was observed among specimens that were resistant to all tested medications. Conclusion: Tumor drug responses were highly preserved in locoregional metastases, whereas somewhat greater divergence was observed in lymphogenic or hematogenic metastases. Single-site functional profiling may remain informative for identifying treatment resistance and might reduce the risk of ineffective therapy selection in metastatic disease.

Prognostic models in oncology are developed one cancer at a time, from that cancer's own labelled outcomes, and fail where prognostic information is scarcest. Rare cancers account for roughly a fifth of diagnoses and most paediatric malignancies, yet seldom supply enough events for a reliable time-to-event model. We therefore asked whether a representation learned without outcome labels can supply what those cohorts cannot. A Transformer encoder was pretrained by masked field-value modelling on 9425135 tumour records from the SEER 17 registries, diagnosed in 2000 to 2023. Only diagnosis-time fields passing a fail-closed coding-verification gate were admitted, and each record was emitted as an era-specific and a harmonised view, keeping two decades of recoding auditable. The encoder was then frozen and read by a linear Cox head for overall survival. Nine rare cancers were removed from the pretraining corpus entirely, each requiring an independent pretraining run. On a sealed test partition, all nine exceeded an architecture-identical random frozen encoder in Harrell concordance by +0.0034 to +0.0368, every lower confidence limit above zero. At 256 labelled patients, all 67 cancers favoured the pretrained representation over budget-matched Cox regression, median difference +0.0283. The advantage was bounded: given the entire training set, Cox regression was favoured in seven of nine rare cancers. The encoder did not outperform a field-frequency baseline on its own objective, so upstream reconstruction did not predict downstream transfer. Outcome-agnostic registry pretraining carries prognostic signal into cancers it has never seen, and is most useful where labels are fewest, without establishing clinical utility.

Hematologic diagnostics and especially cytomorphologic assessment are time-intensive and require high levels of expertise. Vision Language Models (VLM) show promise in medical image analysis in radiology and histopathology, while an evaluation on detecting acute myeloid leukemia (AML) is lacking. Our goal was to evaluate three Vision Language Models regarding their diagnostic accuracy and safety in clinical decision support in detecting AML from digitized bone marrow smears (BMS). Whole slide images were obtained from bone marrow smears of 50 AML patients and 50 bone marrow donors. Ten representative fields of view per sample were extracted manually. Three VLMs were used, two of which are considered generalist models (Qwen3.5-397B-A17B-FP8, GLM-4.6V-FP8), while the other one is a medically adapted model (Medgemma-27b-it). All models performed zero-shot analysis using two prompting strategies: First, a context-rich prompt requesting reporting of WHO/FAB diagnostic criteria in a structured manner, and secondly a minimal prompt without specific hematologic context. Overall diagnostic accuracy was poor for all models as they exhibited the overwhelming tendency to classify most samples as leukemic: With context-rich prompts, GLM4.6 identified 90% of leukemic samples while also labeling 92% of bone marrow donors as AML. The medical specialist model MedGemma-27b showed similar failure, misclassifying 86% of healthy donors and correctly detecting AML in only 66% of cases. Qwen3.5 performed best under detailed prompting, achieving a specificity of 0.26 and accuracy of 0.51. Accuracy of all models improved with context-free prompts (accuracies range 0.47-0.79), yet they still lacked the ability to correctly distinguish between leukemia and healthy bone marrow. Qwen3.5 was the only model to maintain meaningful specificity (0.64) and correctly identified 94% of AML, yielding an overall accuracy of 0.79. Morphologic feature-level agreement with human expert reports was poor across all models, indicating poor recognition of cell-level morphologies. This failure is likely driven by the fact that pathology imaging archives are vastly scraped during model training while hematological samples are not as widely available and therefore, hematology is an out-of-bounds use-case for these models, rendering them currently unsuitable for clinical decision support in hematology.

ABSTRACT BACKGROUND: Next-generation sequencing (NGS) and the development of targeted therapies have revolutionized cancer treatment. Molecular Tumour Boards (MTB) serve as collaborative platforms to integrate individual clinical and molecular information to make recommendations for personalized treatment. METHOD: This is a single-center, retrospective cohort study of patients presented at the Jewish General Hospital (JGH) MTB between July 2018 and Dec 2022. Clinical, molecular/pathologic data, MTB recommendations, and treatment details were collected. Treatment response was determined by radiological evaluation and physician clinical assessment. Fishers exact test and Log-rank tests were used to assess differences between groups. RESULTS: A total of 328 patients were presented to the MTB, including 23 with repeat presentations, resulting in 355 case reviews. Tumour-agnostic biomarkers were detected in 18.9% of cases, most commonly high tumour mutational burden (TMB, 9.5%) and HER2 amplification (4.3%). The most frequent actionable mutations were PIK3CA (19.8%) and PTEN (13.1%), often leading to recommendations for mTOR inhibitor therapy (26.0%). Overall, therapeutic recommendations were issued in 84.5% (300/355) of cases, and implemented in 43.3% (130/300). Patients who received MTB-recommended therapies achieved significantly higher objective response rates (ORR) (14.2% vs. 4.2%; P = 0.047), longer real-world progression-free survival (rwPFS) (5.6 vs. 3.5 months; HR 0.57; 95% CI 0.390 - 0.828; P = 0.003), and improved median overall survival (OS) (12.8 vs. 5.2 months; HR 0.60, 95% CI 0.452 - 0.793; P < 0.001) compared with those treated without MTB guidance. CONCLUSION: MTB is effective in identifying biomarker-matched therapeutic recommendations for advanced malignancies where limited standard-of-care treatment option is available.

Precision oncology seeks to match each tumor with the most effective anti-cancer therapy. Advances in pharmacogenomics and machine learning enabled drug response prediction models with strong performance in cancer cell lines. Nonetheless, patient-centric evaluation of drug prioritization and systematic assessment of model generalization in patient-derived systems across cancer types remain largely absent. Here we introduce a translational framework combining patient-centric benchmarking with a pan-cancer pharmacogenomic atlas of patient-derived organoids, together with NELLY, a deep learning model integrating transcriptomic and chemical information to predict drug response and prioritize therapies. NELLY outperformed existing methods for patient-specific drug prioritization across cancer cell lines and patient-derived organoids, including under out-of-distribution evaluation. Its dynamic weighting mechanism provided patient-specific gene attributions, offering a route to connect predicted drug response to molecular programs associated with drug resistance. Our results support NELLY as a promising framework for translationally relevant and interpretable drug response prediction in precision oncology.

DNA methylation-based classification is increasingly a cornerstone of CNS tumor diagnostics. Recently,nanopore sequencing enables very rapid methylation profiling to support surgical decision making. Time-constrained sequencing yields sparse methylation profiles, necessitating specialized classifiers for accurate predictions. All publicly available sparse-profile classifiers rely on a single reference set of only 2,801 samples published in 2018 and its accompanying classification system. Here we present Sturgeon V2, trained on nearly 10,000 methylation profiles assembled from a range of public repositories and collaborations. To harmonize differences in tumor class labels, we developed an iterative semi-supervised relabeling strategy with a two-tiered concordance filter. We demonstrate that this filtering is essential for optimal performance. Compared to Sturgeon V1, we further redesigned the classifier architecture to provide more stable, and consistent confidence estimates while accumulating sequencing data and we introduce an updated class system including new classes, such as meningioma subtypes, PATZ- fusion neuroepithelial tumors and PLAG1/2-amplified embryonal tumors. In a retrospective intraoperative cohort of 94 pediatric cases, Sturgeon V2 was confidently correct in 85 cases (Sturgeon V1: 78) with one confident misclassification, and in simulated sequencing runs (n=1880) reduced the error rate among confident calls from 7.1% to 2.8%, outperforming publicly available alternatives. Sturgeon V2 is the first openly available, locally executable classifier for sparse methylation profiles trained beyond the 2018 reference era.

Pathologic diagnoses of hematopoietic diseases require immunohistochemistry (IHC) stains selected by pathologists upon preview of H&E-stained slides. This multi-step workflow can delay diagnostic turnaround time by days. Hence, we developed the Hematopathology Automatic Triaging System (HATS), which automates IHC panel ordering directly from H&E whole-slide images using pretrained pathology foundation model representations combined with attention-based multiple-instance learning. After the most comprehensive evaluation of pathology foundation models for hematologic malignancy classification to date, encompassing seven publicly available models, we trained HATS on 4,996 whole-slide images from 1,607 patients spanning the ten most common lymphoma diagnostic categories. HATS achieves 84% case-level subtype classification accuracy (0.962 ROC-AUC), translating to 92% IHC panel ordering accuracy. In a blinded reader study, HATS outperforms practicing pathologists at predicting lymphoma subtypes from morphology alone (85% vs 65%). In an independent real-world validation of 230 clinical cases, after directing 7 cases with scant tissue for manual review, HATS-ordered IHC panels were sufficient for diagnosis in 72.6% of cases. By automating the triaging step while preserving full pathologist oversight, HATS offers a safe and practical entry point for clinical AI adoption in pathology.

Background Immune checkpoint inhibitor (ICI) therapies have revolutionized oncology, but identifying patients who benefit remains a challenge, particularly in populations where ICIs are not the standard of care, including microsatellite stable colorectal cancer (MSS CRC) and rare solid cancers. We evaluated real-world performance of the Immune Profile Score (IPS), a validated DNA- and RNA-based molecular signature, in these cohorts. Methods In an exploratory analysis, we analyzed two real-world cohorts: 1) MSS CRC; and 2) MSS, tumor mutational burden-low rare solid cancers treated with off-label ICI. IPS-High and IPS-Low were calculated using a previously validated threshold. Cox proportional hazards models were fit to demonstrate prognostic utility for real-world overall survival (rwOS). In MSS CRC, time-to-next-treatment (TTNT) on prior non-ICI therapy was compared to rwOS on subsequent ICI therapy. Results In MSS CRC (n=46), IPS-High patients (13%) demonstrated clinically meaningful improvement in rwOS versus IPS-Low (Median OS: not reached vs 7.3 months; HR = 0.22, 90% CI 0.04-1.16). While IPS was not associated with TTNT on the preceding non-ICI line (HR = 1.07, 90% CI 0.60-1.91), it was associated with OS in patients receiving later line ICI (HR 0.21, 90% CI 0.04-1.22). In the rare cancers cohort (n=90; 26 unique malignancies), IPS-High (17.8%) was associated with longer OS to ICI therapy (HR = 0.26, 90% CI 0.11-0.61), even when restricted to histologies represented in both IPS groups (HR = 0.18, 90%, CI 0.05-0.62). Conclusions Preliminary evidence suggests that IPS may serve as a generalizable, pan-cancer biomarker capable of stratifying outcomes for ICI treatment in populations traditionally excluded from immunotherapy benefit.

Background Colorectal cancer (CRC) remains a leading cause of cancer-related mortality, and emerging T cell engager (TCE) immunotherapies require predictive preclinical models that capture patient-specific tumour biology and tumour-immune interactions. Although patient-derived organoid (PDO)-immune co-culture systems show promise for evaluating immunotherapy responses, many rely on matrix-embedded cultures that limit scalability and reproducibility. We therefore developed and validated a low-matrix organoid-T cell co-culture platform for functional assessment of TCE activity in patient-derived CRC models. Methods Patient-derived CRC organoids representing diverse molecular and genetic backgrounds were co-cultured with activated allogeneic CD3+ T cells in a suspension low-matrix format. Matrix concentration, medium composition, T cell activation status, and assay duration were optimized. Tumour killing, T cells activation, cytokine secretion, apoptosis, and motility were assessed using flow cytometry, live-cell imaging, cytokine profiling, and immunofluorescence. The platform was evaluated using EGFR- and HER2-targeting bispecific T cell engagers across 21 CRC organoid models and multiple healthy donor-derived T cell populations. Results Optimization identified 1% matrix and a 1:1 organoid: T cell medium that preserved organoid integrity while maintaining T cell viability, activation, and motility. The final workflow enabled reproducible co-culture of 5-day mature organoids with 7-day activated T cells for 72 hours. EGFR-targeting TCEs induced tumour killing, T cell activation, and IFN-{gamma} secretion across donor-organoid combinations. Screening of 21 CRC organoid models revealed substantial inter-patient heterogeneity, with 12 models maintaining [&ge;]50% baseline viability and supporting functional TCE evaluation. EGFR- and HER2-targeting TCEs produced potent dose-dependent cytotoxicity, with IC50 values ranging from 0.0188 to 54.77 nM across responsive models and up to 75%-85% tumour killing in the most sensitive organoids. These responses were accompanied by increased effector cytokine secretion. Real-time imaging confirmed dynamic T cell engagement and apoptosis-driven organoid destruction following TCE treatment. Conclusions We establish a robust, scalable, human-relevant low-matrix organoid-T cell co-culture platform for functional screening of T cell engagers in patient-derived CRC models. By enabling integrated assessment of tumour killing, immune activation, cytokine responses, and tumour-immune interactions while preserving inter-patient heterogeneity, this system provides a translational framework for immunotherapy development. The platform may support candidate prioritisation, biomarker discovery, patient stratification, and preclinical evaluation of immune-engaging therapeutics.