PD Surrogate Biomarker Identification and Validation Using DART
Executive Summary
A leading biopharmaceutical clinical development company with a strong monoclonal antibody (mAb) portfolio needed to streamline bioequivalence studies by identifying predictive pharmacodynamic (PD) surrogate biomarkers. Traditional clinical trials were expensive, slow, and required large patient populations to demonstrate efficacy equivalence.
By adopting Quantiphi’s DART platform, powered by human microphysiological models and AI/ML-driven biomarker analytics, the company successfully validated PD surrogate biomarkers ex vivo, shortening clinical trial timelines and reducing overall costs—while ensuring scientific rigor and regulatory compliance.
About the Client
The client specializes in developing monoclonal antibodies for solid tumors and neurodegenerative diseases, with a focus on advancing human-relevant clinical programs through innovative biomarker strategies.
- Industry: Life Sciences (Small molecule drug discovery)
- Size: ~1,000+ employees
- Country: India and Europe
Problem Statement
The client, a biopharmaceutical clinical development company with a strong portfolio of monoclonal antibodies (mAbs) targeting solid tumors and neurodegenerative diseases, needed to accelerate its bioequivalence and efficacy studies. Traditional clinical trials were costly, lengthy, and required large patient cohorts to establish comparative effectiveness between candidate and reference drugs. The company sought a human-relevant, scientifically validated solution capable of identifying predictive pharmacodynamic (PD) biomarkers early in the development cycle to shorten clinical timelines, reduce costs, and ensure regulatory alignment through mechanistically supported surrogate endpoints.
Challenges
- Animal model-based data provided ambiguous efficacy outcomes.
- Potential buyers required human-relevant clinical trial-grade insights.
- Conducting early-phase clinical studies was too costly and resource-intensive.
- Lack of validated preclinical surrogates hindered confident IND decision-making.
The Solution
DART introduced a non-animal, AI-powered biomarker validation strategy that combines human microphysiological models with machine learning-based analytics to identify and validate PD biomarker signatures under ex vivo conditions.
Key solution highlights:
- Human-relevant biomarker detection: Leveraged microphysiological models to replicate in-vitro biological responses for accurate PD signature identification.
- AI/ML-enabled quantification: Utilized validated PD surrogate biomarker measurements to predict clinical efficacy without the need for full-scale trials.
- Ex vivo trial simulation: Provided rapid, mechanistic insights into drug efficacy and bioequivalence.
- Regulatory-ready validation: Ensured data credibility aligned with global bioequivalence standards.
Through DART’s integrated analytics and biology-driven modeling, the client established a robust, reproducible framework for PD biomarker validation—enhancing the efficiency and predictive power of their clinical development process.
Customer’s Testimonial
“We could track clinical surrogate endpoints by utilizing the validated PD biomarker signature measurements in the ex vivo trial. Based on the ex vivo trial data, we could design the most efficient clinical trial for our program.”
Director, Clinical Development
Impacts
- Validated PD surrogate biomarkers supporting bioequivalence demonstration.
- Shortened clinical trial duration and reduced participant size.
- Generated human-relevant efficacy signatures with ex vivo precision.
- Improved regulatory alignment through scientifically validated surrogate endpoints.
- Enhanced R&D efficiency and clinical strategy optimization.
Technologies Used
Quantiphi’s DART Platform
Human Microphysiological Models
AI/ML Analytical Pipelines
PD Biomarker Signature Validation Tools
Results
- The validated PD surrogate biomarker signature was established as a proprietary intellectual asset for ongoing and future programs.
- Delivered rapid comparative profiling of three monoclonal antibody candidates against reference drugs.
- Reduced trial complexity and duration through early efficacy prediction using ex vivo data.
- Strengthened regulatory confidence and scientific credibility for bioequivalence submissions.