Home

Cellworks’ Study Predicts Immune Checkpoint Inhibitor Resistance in Patients with High Microsatellite Instability

via Business Wire

Novel Genomic Signatures Linked to Poor ICI Response in MSI-H Cancer Patients Enable Personalized Treatment Strategies

Cellworks Group Inc., a leader in Personalized Therapy Decision Support and Best-in-Class PTRS, today announced compelling results from a new study demonstrating the ability of the Cellworks Platform to identify patients with high microsatellite instability (MSI-H) who may not respond to immune checkpoint inhibitors (ICIs), despite MSI-H status. Results from the study were showcased in a poster presentation titled, Use of Biosimulation to Predict Immune Checkpoint Inhibitor Resistance in Patients with High Microsatellite Instability as part of the AACR Annual Meeting 2025 taking place April 25-30, 2025 at the McCormick Place Convention Center in Chicago.

While immune checkpoint inhibitors (ICIs) such as pembrolizumab are considered a standard-of-care for MSI-H cancers, MSI-H status alone is not a definitive predictor of treatment success. In this study, Cellworks applied its unique mechanistic Computational Biology Model (CBM) to biosimulate patient-specific responses to ICIs. The computational biosimulation process in the study uncovered molecular signatures of resistance in MSI-H patients who were predicted to have poor response to ICIs, providing a deeper understanding of why some MSI-H patients fail to benefit from immunotherapy.

Key Findings

  • Efficacy Scores Significantly Higher in MSI-H Patients. MSI-H patients demonstrated significantly higher pembrolizumab efficacy scores compared to microsatellite stable (MSS) patients in both STAD (average ES: 20.5 vs. 3.2, p < 0.001) and CRC (average ES: 13.4 vs. 2.4, p < 0.001).
  • Large Subset of MSI-H Patients Predicted to Have Low ICI Response. Despite being MSI-H, 59% of STAD and 81% of CRC patients were identified as low pembrolizumab responders.
  • Molecular Drivers of Resistance Identified. In MSI-H patients classified as low pembrolizumab responders, higher rates of NOTCH2, EGFR, and EZH2 amplifications, along with TP53 loss-of-function mutations, were identified. In MSI-H/ES-L CRC patients, MYC amplification was significantly enriched (p < 0.05).

“These findings highlight the power of using patient-specific drug response methods to move beyond MSI-H status and identify critical molecular drivers of immune checkpoint inhibitor resistance,” said Dr. James Wingrove, Chief Development Officer at Cellworks and presenting author of the study. “By identifying patients unlikely to respond to ICIs, we can help oncologists personalize treatment strategies and improve outcomes for MSI-H patients who may otherwise receive ineffective therapies.”

“This study demonstrates the importance of looking beyond MSI status to understand immune checkpoint inhibitor resistance at a molecular level,” said Dr. Michael Castro, Chief Medical Officer at Cellworks. “Our biosimulation revealed that MSI-H patients with low predicted response to pembrolizumab frequently harbored alterations such as NOTCH2, EGFR, and EZH2 amplifications, as well as TP53 loss-of-function mutations in STAD, and MYC amplifications in CRC. Identifying these resistance-associated biomarkers can help guide clinicians in selecting more effective, personalized treatment strategies for MSI-H patients who may not benefit from ICIs alone.”

Study Design

Cellworks developed a mechanistic Computational Biology Model (CBM) that can be personalized based on a patient’s tumor-based genomic profile, revealing signaling pathway dysregulation and patient-specific drug response. Output from the model was used to identify MSI-H patients who may have a poorer response to ICIs. Computational biosimulation was performed using real-world retrospective cohorts of 423 STAD patients and 534 CRC patients (TCGA). MSI measurements were provided by TCGA. Efficacy scores based on biosimulated composite cell growth in response to disease and therapy were generated on all patients for pembrolizumab. Molecular rationales for ICI resistance were identified for MSI-H patients with low pembrolizumab efficacy scores.

The Cellworks Platform

The Cellworks Platform performs computational biosimulation of protein-protein interactions, enabling in silico modeling of tumor behavior using comprehensive genomic data. This allows for the evaluation of how personalized treatment strategies interact with the patient’s unique tumor network. Multi-omic data from an individual patient or cohort is used as input to the in silico Cellworks Computational Biology Model (CBM) to generate a personalized or cohort-specific disease model.

The CBM is a highly curated mechanistic network of 6,000+ human genes, 30,000 molecular species and 600,000 molecular interactions. This model along with associated drug models are used to biosimulate the impact of specific compounds or combinations of drugs on the patient or cohort and produce therapy response predictions, which are statistically modeled to produce a qualitative therapy response score for a specific therapy. The Cellworks CBM has been tested and applied against various clinical datasets with results provided in over 125 presentations and publications with global collaborators.

About Cellworks Group

Cellworks Group, Inc. is a leader in Personalized Therapy Decision Support and Precision Drug Development. The Cellworks Platform predicts therapy response for individual patients and patient cohorts using a breakthrough Computational Biology Model (CBM) and biosimulation technology. Backed by Artiman Ventures, Bering Capital, Sequoia Capital, UnitedHealth Group and Agilent Ventures, Cellworks has the world’s strongest trans-disciplinary team of molecular biologists, cellular pathway modelers and software engineers working toward a common goal – attacking serious diseases to improve the lives of patients. The company is based in South San Francisco, California with a CLIA-certified computational laboratory in Franklin, Tennessee and a research and development facility in Bangalore, India. For more information, visit www.cellworks.life.

All trademarks and registered trademarks in this document are the properties of their respective owners.

Contacts