We design vaccine from analysis of patient OMICs data: genomics and transcriptomics from patient tumor (e.g. RNA seq & WES NGS) and urine proteomics. Molecular profile is projected onto knowledgebase of molecular interactions & functional associations and on mechanistic cancer models compiled under cancer hallmarks paradigm. Knowledgebase was constructed by extracting information from entire biomedical literature using deep reading AI NLP technology. Our proprietary algorithms rank neoantigens and self-antigens by significance in patient OMICs data and literature-described function.
We intend to make cancer vaccine affordable to middle class as out-of-pocket expense that can be purchased without health insurance. To achieve this goal, we design short peptides necessary for CD8+ NK cells activation and plan to setup our own cGMP manufacturing facility in USA and later in other developed countries. Vaccine cost is also controlled by increased precision of peptide design allowing smaller number of peptides in vaccine.
We plan to send vaccine to interested physicians worldwide willing to administer it into a patient along with suggested protocols for handling and vaccination. Vaccine efficacy will be improved by collecting feedback from physicians and developing training sets for artificial intelligence. Machine learning algorithms developed with these training sets will increase design precision even further reducing its cost and efficacy.
Precision and personalization are pivotal in creating diverse, novel approaches unique to the patient in an expanding adaptation against disease. As Dr. Catanzaro so succinctly states, “the focus on the individual patient is key. It’s not about discovering a new drug for the disease, it's about creating the unique solution for the patient.”