AI-Driven Oncology Drug Discovery
The first and only validated AI/ML platform that identifies complex, gene expression signatures that correlate with drug response.
This proprietary predictive AI platform can eliminate the need for many preclinical studies through better-informed early decision-making—saving time in early development, and improving translation to the clinic. By understanding predictive biomarkers earlier, cancer therapeutics companies can reduce the number of unproductive studies, save money, and help achieve their three-Rs goals.
AI-enabled Efficacy Predictions for Drug Discovery and Development
CertisAI can guide you to the right preclinical models for both in vitro and in vivo studies—or help inform which indications and patient populations are most likely to respond to your novel compound and home in on predictive biomarker strategy.
START A CONVERATION
Learn how AI-enabled insights can bring greater precision to your program.
WHY CHOOSE CERTISAI™ Predictive AI?
CertisAI™ predictions incorporate the full range of gene expression data, providing an unbiased, more precise biomarker-based approach to understanding drivers of drug response compared to strategies that rely on the mutation of one or more genes.
Reduce Cancer Drug Discovery Missteps with Predictive AI Modeling
In internal, hold-out cross-validation studies, CertisAI was shown to be 90%+ accurate for monotherapy predictions and nearly 80% accurate for combination therapies. AI-enabled predictive modeling provides real data-driven insights into predictive biomarkers that bring confidence to decision-making and help researchers avoid costly missteps.
Accuracy of AI Predictions Has Been Externally Validated
Leveraging extensive experience performing pharmacology studies, Certis scientists have externally validated our predictive AI/ML platform performance using well-characterized, low-passage patient-derived xenografts (PDX) and PDX-derived 3D cell cultures. Those studies demonstrate a strong Pearson correlation between actual observed tumor growth inhibition (TGI) and predicted TGI.
Pre-trained or Custom Predictive Modeling
Researchers tap into the power of CertisAI two ways. Pre-trained CertisAI models predict efficacy using a small molecule's SMILES string as an input. Custom CertisAI models use data from early screening studies to identify the gene expression profiles (predictive biomarkers) that correlate with favorable drug response for almost any type of molecule—as a monotherapy or in combination with other drugs.
Rapid AI Modeling of Drug Combinations
With CertisAI, you can efficiently evaluate how your novel compound will likely perform in combination with thousands of marketed drugs. CertisAI synergy predictions are based on not just one—but four—synergy reference models (BLISS, Loewe, HSA, ZIP). Bring AI-enabled insights to your combination therapy or label expansion efforts.
CONTACT US
About Us
Certis Oncology Solutions is the only translational science partner that combines the predictive power of AI and deep expertise in cancer model development to reliably answer complex questions about therapeutic effects. CertisAI Predictive Oncology Intelligence® uses multivariate machine learning algorithms to capture the nuance of biomarker interactions and bring AI-enabled accuracy to model selection, predictions of drug efficacy, and biomarker identification. Its proprietary in silico platform utilizes big data, statistical algorithms, and machine learning to predict drug efficacy based on gene expression biomarkers. This pan-cancer solution can accelerate drug discovery and companion diagnostics development.