Cancer is a disease of the genome and thanks to the advancements in DNA sequencing, we now have access to whole-genome data from real patients. We use this data, alongside other data modalities to discover new biological insights using artificial intelligence.
Tumor biopsy:
Clinical data
Response data
Whole genomes
Transcriptomics
The understanding of molecular data is hidden under a lot of noise. In order to extract it, we infuse data with biological knowledge. We do it by building descriptors (a piece of software extracting information about data (i.e. presence of deletions) and adding biological information (i.e. defect in Homologous Recombination) to it.
variants + descriptors
Precision AI is a fusion of machine learning and biological knowledge. We have developed a platform designed to infuse machine learning models with biological knowledge. Precision AI allows extracting complex biological insights from molecular data to construct a model of tumor biology. Models get better with more data, but most importantly, models improve as we inject more biological knowledge.
Traditional AI: more data = better models
Precision AI: more knowledge = better models
Novel AI architecture for biology infused data & powering multimodal learning.
The model helps us truly understand the processes taking place in cancer and lets us verify various hypotheses regarding both existing and potential therapies. First, we are able to identify patients who will respond to known therapies, boosting the effective efficacy of the drugs which are already in use or are entering clinical trials. Second, we can observe cohorts of patients who would benefit from different therapies than those they were originally assigned to, finding other indications for existing drugs and facilitating drug repurposing. Finally, the model shows us cohorts of patients for whom there are no right therapies available, allowing us to pursue and validate new drug target candidates.
This is how we find the right therapy for every cancer patient.
New drug targets
- first program preclinically validated
Predictive algorithms
- already in clinics
