What we do
BenevolentAI has capability from early discovery to late stage clinical development. Our platform of computational and experimental technologies and processes, drawing on vast quantities of mined and inferred biomedical data, can advance the entire drug development process. The platform is built and used by our world-class scientists, researchers, and technologists, working side-by-side. Our strength comes from this integrated, end-to-end approach, combined with a relentless pursuit of scientific and technological excellence.
Knowledge and reasoning
The right foundations
The foundation of our platform is a comprehensive bioscience knowledge graph, capable of ingesting any relevant structured and unstructured data. We reason on this data using state-of-the-art bioscience-specific models. We deduce facts, infer new knowledge and generate ranked hypotheses, together with biological evidence or "reasons to believe". This gives scientists a large number of high quality ideas to explore, more quickly than via traditional research methods.
The right disease target
We want to understand a disease and its underlying biology without bias, to arrive at new knowledge. Our Target Identification programmes augment the deep expertise of our scientists with computational and experimental technologies and processes designed to counter bias. BenevolentAI’s Platform enables scientists to determine the right mechanism to modulate, the best targets and how patients may respond to treatment.
Clinical Mechanistic Stratification
The right patient
We need to know the molecular basis for a disease in patients to pre-determine responders and non-responders in patient populations. Anticipating the best responders for specific drug treatments ahead of clinical trials is a fundamental shift in approach - from retrospective to prospective. We are developing new machine learning methods to understand patient endotypes and their response, fundamentally changing our ability to intervene in diseases at the right time.
The right drug
We have found that successful AI-enabled molecular design programmes need the full context of target, mechanism and patient endotype. Even the safest molecule in the world will do nothing to treat disease if it hits the wrong target. Our interdisciplinary squads work in fast, iterative experimental cycles throughout target identification and lead optimisation, building on new and existing experimental data from all stages of drug development, to ensure the drug has the greatest chance of efficacy in patients.