Our Solution

Cellgen is developing a non-amplified, bio-fluid based therapeutic guidance platform that incorporates machine learning to deliver intelligent, quantitative and actionable results to oncologists.

Designed to detect all DNA, RNA, and Proteins, Cellgen's platform features a proprietary on-chipenrichment and detection workflow perfectly suited to be installed as the premier companion diagnostic testing system within leading oncology clinics. Running on Cellgen's proprietaryplatform, each disposable assay will yield inclusion / exclusion data, while also leveraging proprietary machine learning algorithms to intelligently monitor and predict therapeutic response.

This information will help inform patients, physicians, oncologists, and others on how best to simplify and optimize life-saving clinical protocols. Physicians will also be able to query predicted response outcomes based on avariety of parameters like gender, race, and geography. The final IVD system will befully-automated to decrease operator hands-on time, increase reproducibility and decrease test turnaround time to under 2.5 hours.

Cellgen's companion diagnostics platform will provide 2 outputs:

  • A Yes or No answer for a patient/drug genetic match decision
  • If yes, a predictive therapeutic outcome value »» Cellgen will quantify a signature of miRNA expression levels and place those expression levels into a set of machine learning algorithms that will classify the patients likely response to the given medicine. With every new patient, the deep learning algorithms more specifically predict the therapeutic outcome of each patient.

Cellgen's EVAP platform will be capable of performing near-patient companion diagnostic assays, while at the same time, sharing real-time data, across various clinical settings to enhance clinic decisions

  • Greatly improve patient outcomes by eliminating delays in therapy selection, improving turnaround time from days to hours
  • Creates a significant new revenue opportunity for physicians due to reimbursement attainment
  • Drives increased commercial adoption of therapeutics, particularly those from smaller Rx companies
  • Incorporates machine learning to dynamically improve prediction of therapeutic response