At BioAI, we are accelerating biomarker discovery and development using novel machine learning technology — identify and understand novel drug targets, advance diagnostic accuracy, and improve drug efficacy with BioAI’s custom biomarker services. We also offer biobanking services — gain access to archival and prospective sample collections for FFPE, PBMC, Plasma, and samples for rare indications.

BioAI service offerings include:

Biospecimen Procurement
—Gain access to human biospecimen samples for rare indications or custom collections for your specific research needs, oncology and beyond

AI Biomarker Services
— Predictive AI models for known genetic mutations or novel biomarkers: BioAI has a strong experience and track record in developing H&E-based AI models for known genetic mutations in various cancer indications. A major use case is applying H&E-based digital biomarkers to screen or pre-screen patient eligibility for clinical trials in order to expand the access to patients suited and to significantly reduce overall testing costs.
Special Capabilities:
-Developing AI models for broad bandwidth of cancer indications, such as lung, breast, melanoma, and more
-Developing AI models to predict the status of genetic mutations, e.g. RET, EGFR, ROS1, ALK, NTRK, BRAF
-Different measures and novel approach working towards high generalizability of AI algorithms
-High performance of AI models; with sensitivity and specificity modeled according to the specific needs
-Determination of pathological and molecular factors that might play a role in patient response to therapy and drug resistance
-Novel biomarker development in the form of AI models for outcome prediction: predict treatment outcomes, disease resistance factors, adverse events, and long-term patient responses
-Identification of patient subgroups likely to respond to specific therapies, enabling more targeted treatment strategies

Leverage our AI Platform for Clinical Research
—Our technology integrates complex data sets from translational studies and clinical trials and develops machine learning models on multi-omic data that can help predict patient response to therapy & drug resistance