BostonGene, a developer of the leading AI foundation model for tumor and immune biology, today announced that 13 abstracts have been selected for presentation at the American Association for Cancer Re...
Autore: Business Wire
Leveraging an AI-powered omnimodal foundation model to accelerate drug discovery, optimize patient stratification, and de-risk clinical development
WALTHAM, Mass.: BostonGene, a developer of the leading AI foundation model for tumor and immune biology, today announced that 13 abstracts have been selected for presentation at the American Association for Cancer Research (AACR) Annual Meeting 2026, held from April 17 - 22, at the San Diego Convention Center in San Diego, CA. BostonGene will be exhibiting at booth #4613.
BostonGene will demonstrate how its leading AI foundation model for tumor and immune biology is redefining the drug development lifecycle by providing biopharma partners with a biologically grounded roadmap from early discovery through late-stage clinical trials. Integrating genomic, transcriptomic, and spatial insights, BostonGene’s presentations highlight a sophisticated suite of AI-driven capabilities designed to accelerate and de-risk the pharmaceutical pipeline. Key research includes the use of ReadyScore and Lymphly for precision patient stratification and target identification, RNA-aware diffusion models to predict drug-induced tissue dynamics, and AI-based image batch correction to ensure trial data integrity by focusing on true biologic signals. Furthermore, in collaboration with leading institutions, BostonGene will showcase how longitudinal multiomic profiling identifies actionable biomarkers and resistance pathways often missed by traditional methods.
Details of BostonGene’s presentations at AACR are below:
Oral presentation
Session: CT012
Title: A phase 2 single-arm open-label trial evaluating zanidatamab in patients with early-stage HER2-positive breast cancer: The NeoZanHER study
Date & time: April 18 | 12:50 PM - 1:00 PM
Presenter: Funda Meric-Bernstam, MD, UT MD Anderson
BostonGene’s integrated whole exome sequencing (WES) and RNA-seq platform was applied to uncover markers of response to HER2-targeting zanidatamab in a small cohort of patients with early-stage HER2-positive breast cancer. Early findings revealed high efficacy and manageable safety profile in select patients, underscoring the feasibility of de-escalating to HER2-targeted therapy alone for this cancer.
Research done in collaboration with UT MD Anderson
Poster presentations
Poster: 114
Title: Unraveling tumor- and tissue-specific gene expression patterns from plasma-derived cfRNA
Date & time: Sunday, April 19 | 2:00 PM - 5:00 PM
Presenter: Desiree Schenk, BostonGene
BostonGene explored the utility of minimally invasive plasma-derived cell-free RNA (cfRNA) profiling for deconvolving tumor- and tissue-specific signals from a single blood draw. We uncovered tumor- and tissue-specific expression patterns in cfRNA that correlated with donor health or cancer status. Our findings support cfRNA signatures as a clinically relevant resource for optimizing patient stratification, trial design, discovery of novel drug targets and plasma-based biomarkers, and disease and treatment response monitoring.
Poster: 0452
Title: Therapeutic potential of AURKA inhibition in ER+ inflammatory breast cancer
Date & time: April 19 | 2:00 PM - 5:00 PM
Presenter: Surbhi Shivhare, PhD, UT MD Anderson
Applying BostonGene’s Tumor PortraitTM to analyze samples from ER+ inflammatory breast cancer (IBC) tumors, researchers at MD Anderson discovered amplified AURKA expression and an inverse relationship between AURKA and SMARCA4 expression. These findings suggest SMARCA4 as a putative synthetic lethality partner of AURKA, where therapeutic targeting of both could lead to cell death. BostonGene’s Tumor PortraitTM integrated genomic and transcriptomic data with clinical data to generate biologically grounded, actionable insights.
Research done in collaboration with UT MD Anderson
Poster: 2437
Title: A comparative scoring framework for BCMA-, GPRC5D- and CD38-targeted therapies in multiple myeloma
Date & time: Monday, April 20 | 9:00 AM - 12:00 PM
Presenter: Konstantin Chernyshov, PhD, BostonGene
BostonGene leveraged ReadyScore, a proprietary, next-generation sequencing-based scoring framework for BCMA-, GPRC5D-, and CD38-targeted therapies in multiple myeloma. This molecular stratification tool integrates tumor and microenvironment features to provide a comprehensive readiness profile to predict CAR-T response, T-cell engagers and monoclonal antibodies. By highlighting target readiness and treatment resistance pathways, the framework enables more precise biomarker-driven patient selection, informs therapeutic prioritization, and offers potential utility for optimizing trial design and translational decision-making.
Poster: 1451
Title: Visualizing the genotype–phenotype link: Predicting drug-induced tissue dynamics with RNA-based diffusion models
Date & time: Monday, April 20 | 9:00 AM - 12:00 PM
Presenter: Alexander Bagaev, PhD, BostonGene
BostonGene presents an RNA-aware diffusion model that predicts tissue morphology from gene expression to better understand genotype–phenotype relationships in cancer. The model integrates RNA embeddings from over 20,000 genes with histological image generation, trained on extensive paired RNA and H&E datasets. It produced realistic tissue images and successfully simulated drug-induced gene expression changes, capturing biologically meaningful tissue dynamics such as tertiary lymphoid structures and B-cell signatures. The approach helps predict how drugs affect tissue architecture, improving drug candidate selection, guiding early trial design, and reducing risks in drug development.
Poster: 3877
Title: Integrative application of Lymphly reveals shared molecular landscape across B-cell lymphomas
Date & time: Monday, April 20 | 2:00 PM - 5:00 PM
Presenter: Konstantin Chernyshov, PhD, BostonGene
BostonGene applied Lymphly, a unique, stable genetic classification framework for diffuse large B-cell lymphoma (DLBCL). When applied to ~3,500 samples, it uncovered previously unrecognized molecular relationships between DLBCL subtypes and other B-cell lymphomas. The analysis identified distinct subtype–disease links and shared genetic patterns, improving understanding of how lymphomas may transform into DLBCL and highlighting potential therapeutic targets across the B-cell lymphoma landscape.
Poster: 1468
Title: Germline whole exome sequencing implicates homologous recombination repair pathway genes as risk factors in SMARCB1 deficient renal medullary phenotypes without sickle hemoglobinopathies
Date & time: April 20 | 9:00 AM - 12:00 PM
Presenter: Pankaj Kumar Chauhan, PhD, UT MD Anderson
BostonGene’s genomic analysis explored two rare and aggressive kidney cancers: renal medullary carcinoma (RMC) and renal cell carcinoma with medullary phenotype (RCCU-MP). The study found that while both cancers showed similar immune-rich tumor environments, distinct genomic alterations were present in RCCU-MP that were absent in RMC. These results point to new genetic risk factors in RCCU-MP and support broader germline testing for patients with RCCU-MP.
Research done in collaboration with UT MD Anderson
Poster: 3763
Title: CCR7 expression and spatial distribution in inflammatory breast cancer: A baseline characterization for therapeutic targeting
Date & time: April 20 | 2:00 PM - 5:00 PM
Presenter: Surbhi Shivhare, PhD, UT MD Anderson
In collaboration with The University of Texas MD Anderson Cancer Center, BostonGene applied its multimodal molecular profiling platform to advance target discovery in inflammatory breast cancer. By integrating genomic, transcriptomic, and spatial data, BostonGene uncovered key biological features of CCR7 that support its therapeutic relevance. This work highlights BostonGene’s ability to generate clinically actionable insights to prioritize targets, refine patient selection strategies, and accelerate oncology drug development.
Research done in collaboration with UT MD Anderson
Poster: 5251
Title: Precise description of metabolomic states using NGS uncover new potential biomarkers of response to TKIs in ccRCC
Date & time: Tuesday, April 21 | 9:00 AM - 12:00 PM
Presenter: Nikita Kotlov, PhD, BostonGene
BostonGene developed specific metabolic gene signatures to inform prediction of tyrosine kinase inhibitor (TKI) response in patients with clear cell renal cell carcinoma (ccRCC). Our refined metabolic signatures uniquely integrate transcriptomic and metabolic data to reveal strong associations with TKI response, overall survival and tumor microenvironment subtypes, representing potent candidate biomarkers for early-phase clinical trial design and patient stratification aimed at overcoming TKI resistance.
Poster: 4164
Title: Implementation of a diffusion-based color checker for histological image batch correction
Date & time: Tuesday, April 21 | 9:00 AM - 12:00 PM
Presenter: Alexander Bagaev, PhD, BostonGene
BostonGene will present a novel AI-powered tool to enhance histological image analysis through batch correction. Leveraging stable diffusion models, the tool standardizes whole slide images collected on different scanners by mitigating technical variations and artifacts. The diffusion-based framework optimizes AI-driven image analysis workflows, offering a scalable solution for harmonizing large multi-site histological datasets.
Poster: 5421
Title: Determining the benefit of comprehensive molecular testing in advanced cancers: BostonGene and Exigent Genomic INsight (BEGIN) study
Date & time: Tuesday, April 21 | 9:00 AM - 12:00 PM
Presenter: Sibel Blau, MD, Northwest Medical Specialties
The BEGIN study, a collaboration between BostonGene and the Exigent Research Network, evaluated integrated DNA/RNA genomic profiling in community oncology practices. Among patients with advanced cancers, 93% had actionable findings, with many identified through RNA sequencing only. Comprehensive results influenced treatment decisions, including matching patients to standard of care and ongoing trial options, highlighting the patient-level impact of combined DNA/RNA testing in expanding precision oncology options in community settings.
Research done in collaboration with Exigent Research Network Investigators
Poster: CT277
Title: IvoLoC trial: A phase II trial evaluating the efficacy of ivonescimab in metastatic endocrine refractory HR-positive HER2-negative or triple negative invasive lobular carcinoma (ILC)
Date & time: Tuesday, April 21 | 2:00 PM - 5:00 PM
Presenter: Jason Mouabbi, MD, UT MD Anderson
In an ongoing clinical trial with MD Anderson Cancer Center, BostonGene performed multimodal longitudinal blood and tissue analysis of metastatic invasive lobular carcinoma patients receiving the bispecific antibody targeting PD-1 and VEGF, ivonescimab. Beyond efficacy and durability, this study evaluated the molecular correlates linking clinical outcomes with tumor microenvironment subtypes while assessing circulating tumor DNA dynamics, biomarkers of response and resistance, and predictive responder scores.
Research done in collaboration with UT MD Anderson
Poster: 7935
Title: Multimodal immunotherapy remodels the tumor microenvironment in hepatocellular carcinoma: Integrative spatial and transcriptomic profiling from a Phase II trial
Date & time: April 22 | 9:00 AM - 12:00 PM
Presenter: Lionel Aurelien Kankeu Fonkoua, MD, Mayo Clinic Cancer Center
BostonGene’s spatial and transcriptomic analysis was used in a Phase II trial to show that combining radiotherapy, dendritic cell vaccination, PD-L1 blockade, and VEGF inhibition could reshape the tumor environment in hepatocellular carcinoma (HCC). This multimodal approach helped turn immune-resistant “cold” tumors into immune-active states, improving T-cell responses and vascular health. The findings highlight promising strategies to overcome treatment resistance in HCC and reinforce BostonGene’s role in advancing precision immunotherapy.
Research done in collaboration with Mayo Clinic
The abstracts will be published in an online-only Proceedings supplement to the AACR journal Cancer Research.
To learn more or to schedule a meeting with BostonGene during AACR, please contact Hannah Oman at events@bostongene.com.
About BostonGene Corporation
BostonGene is redefining cancer patient care and drug development through the integration of omnimodal data and artificial intelligence. Built and validated through an extensive real-world clinical testing network, BostonGene’s foundation model for tumor and immune biology integrates genomic, transcriptomic, and immune data with clinical outcomes to generate biologically grounded, actionable insights. These insights enable biopharma partners to design and de-risk trials, identify novel targets, and optimize therapeutic response prediction across all stages of development while simultaneously improving patient care through clinically integrated innovation. For more information, visit www.BostonGene.com.
Fonte: Business Wire