BostonGene to Present Seven Studies Unveiling Novel AI-Driven Breast Cancer Breakthroughs at SABCS 2025

Presentations showcase the power of omnimodal profiling to identify predictive immune signatures, comprehensively profile the tumor microenvironment and reveal novel therapeutic targets for optimized treatment for breast cancers

WALTHAM, Mass.--(BUSINESS WIRE)--BostonGene, developer of the leading AI foundation model for cancer and the immune system, today announced seven abstracts have been accepted for presentation at the San Antonio Breast Cancer Symposium (SABCS) 2025, taking place from December 9–12, 2025, in San Antonio, Texas. The research, conducted in collaboration with leading cancer centers, demonstrates the power of the BostonGene platform to uncover complex breast cancer tumor biology and drive informed, personalized treatment strategies. BostonGene will exhibit at booth #1352.

Poster spotlight discussions:

Poster spotlight number: PD7-03
Title: Circulating immune correlates of pathological response to neoadjuvant pembrolizumab plus chemotherapy in high-risk, early-stage triple-negative breast cancer
Date & time: December 11, 2025; 7:36 AM - 7:39 AM
Presenter: Clinton Yam, MD, MS, The University of Texas MD Anderson Cancer Center

Using BostonGene’s multi-parameter immune phenotyping platform and immunotype signature scores, clinicians at MD Anderson profiled peripheral blood from patients with triple-negative breast cancer (TNBC) undergoing the KEYNOTE-522 regimen. This study showed immune cells in the blood were significantly associated with improved response to KEYNOTE-522. Identified through BostonGene’s natively omnimodal AI model, these immune signatures show promise as minimally invasive biomarkers to identify patients most likely to respond to immune-based neoadjuvant approaches, supporting patient stratification and optimization of therapy in TNBC.

Research done in collaboration with MD Anderson Cancer Center

Poster spotlight number: PD7-09
Title: Feasibility of a machine learning (ML)-based peripheral blood immunoprofiling platform to stratify patients (pts) with early-stage triple-negative breast cancer
Date & time: December 11, 2025; 8:06 AM - 8:09 AM
Presenter: Chiara Corti, MD, Dana-Farber Cancer Institute

BostonGene’s machine learning-based immune phenotyping platform was used to examine blood samples of early-stage triple-negative breast cancer (TNBC). BostonGene’s platform assessed how immune profiles differed between chemotherapy alone and chemotherapy plus immunotherapy, and how they evolved during treatment. Immunotype distribution varied significantly by therapy type and showed dynamic changes, particularly in patients receiving chemo-immunotherapy. These findings support the feasibility of capturing immune dynamics in peripheral blood as a minimally invasive approach to refine patient stratification, improve trial design and inform treatment optimization in early-stage TNBC.

Research done in collaboration with Brigham and Women’s Hospital

Poster presentations:

Presentation number: PS1-09-12
Title: TROP2 expression and therapeutic opportunities in inflammatory breast cancer
Date & time: December 10, 2025; 12:30 PM - 2:00 PM
Presenter: Shayla Murray, MD Anderson Cancer Center

Collaborative research utilizing BostonGene’s foundation AI platform revealed that TROP2 RNA expression alone does not predict antibody-drug conjugate response in inflammatory breast cancers, underscoring the limitations of single-marker approaches. These findings demonstrate the necessity of BostonGene’s AI-driven omnimodal analysis built to uncover complex tumor biology and optimize clinical trial design for next-generation precision oncology therapies.

Research done in collaboration with MD Anderson Cancer Center

Presentation number: PS2-10-30
Title: Tumor-associated macrophage (TAMs) and cancer-associated fibroblasts (CAFs) profiles in invasive lobular carcinoma (ILC) vs no special type (NST)
Date & time: December 10, 2025; 5:00 PM - 6:30 PM
Presenter: Jason Mouabbi, MD, MD Anderson Cancer Center

BostonGene performed a large-scale analysis of 617 ILC and NST breast cancers, leveraging its AI-driven Kassandra^TM algorithm to deconvolve hundreds of cell subtypes and activation states from RNA data within the tumor microenvironment (TME). Similar to NST, ILC samples harbored immunosuppressive, stroma-rich TMEs dominated by FAP⁺ myofibroblastic CAFs and M1/M2 TAMs, identifying previously unknown opportunities for targeted therapeutics and novel immune strategies in this often understudied cancer.

Research done in collaboration with MD Anderson Cancer Center

Presentation number: PS2-10-16
Title: Distinct immune landscapes in inflammatory and metaplastic breast cancer: Insights from transcriptomic profiling
Date & time: December 10, 2025; 5:00 PM - 6:30 PM
Presenter: Elyse R. Lopez, MD Anderson Cancer Center

BostonGene’s multimodal model, which integrates genomic, transcriptomic, and immunologic data, was used to analyze 444 invasive, inflammatory and metaplastic breast cancer samples. The analysis revealed distinct clinically relevant immune landscapes in both cancers, illustrating BostonGene’s ability to deliver reliable insights for treatment decision-making and optimal trial design.

Research done in collaboration with MD Anderson Cancer Center

Presentation number: PS2-09-24
Title: Aurora kinase A (AURKA) A new druggable target in ER+ inflammatory breast cancer
Date & time: Wednesday, December 10, 2025; 5:00 PM - 6:30 PM
Presenter: Tanu Sharma, PhD, MD Anderson Cancer Center

Researchers at MD Anderson applied BostonGene’s comprehensive pipeline to analyze RNA and DNA samples from ER+ inflammatory breast cancer (IBC) tumors, revealing amplified expression of AURKA in IBC tumors and the potential for synthetic lethality, where therapeutic targeting of AURKA alongside another target could lead to cell death. These findings demonstrate BostonGene’s capability in integrating genomic and transcriptomic data with clinical outcomes to generate biologically grounded, actionable insights.

Research done in collaboration with MD Anderson Cancer Center

Presentation number: PS4-01-10
Title: Characterizing CCR7 gene amplification and protein expression in inflammatory and non-inflammatory breast cancer
Date & time: Thursday, December 11, 2025: 5:00 PM - 6:30 PM
Presenter: Surbhi Shivhare, PhD, MD Anderson Cancer Center

BostonGene, in collaboration with MD Anderson, applied its multimodal model to examine both CCR7 copy number alterations and gene expression in inflammatory breast cancer. This comprehensive study uncovered discordance across CCR7 copy numbers and RNA levels and pointed to the potential impact of membranous CCR7 protein toward disease status. Highlighting BostonGene’s target discovery applications, this study identified CCR7 as a promising therapeutic target for aggressive breast cancer.

Research done in collaboration with MD Anderson Cancer Center

To learn more or schedule a meeting with BostonGene during SABCS, please contact Hannah Oman at [e-mail].

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 of cancer and the immune system 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.