Empowering scientists to discover new ways to treat disease
We build technology that empowers scientists to explore interconnected disease networks - accessing an ever expanding data landscape - to understand the complexities of biology, derive novel insights, and ultimately discover new and better treatments.
The Benevolent Platform™
The Benevolent Platform™ is our powerful computational R&D platform. At its core sits our Knowledge Graph, which captures the interconnectivity of all relevant available data and scientific literature. Our suite of exploratory and predictive AI tools allow scientists to interrogate the data and disease networks within the graph, ask biological questions, surface novel insights and triage hypotheses. This allows scientists to visualise the key differentiators between health and disease and pinpoint dysregulated pathways and mechanisms enabling them to identify optimal treatment interventions.
Knowledge foundations
Our Knowledge Graph serves as a data engine for our end-to-end platform and drug discovery programmes. It is built on the foundations of all publicly available biomedical data mined from structured sources, information extracted from scientific literature and internally generated experimental findings.
The Knowledge Graph is constantly enriched and supplies a complete and unbiased representation of biomedical data. Our exploratory tools and predictive models empower scientists to explore relationships in the graph between biological entities and disease networks.
Case study
Leveraging our Knowledge Graph and AI tools to identify a leading COVID-19 treatment
In January 2020, we uncovered baricitinib as a potential COVID-19 treatment in just 48 hours using our Biomedical Knowledge Graph and AI tools. Nine months later, the FDA granted Emergency Use Authorisation for baricitinib to treat COVID-19 patients.
Data-driven target identification
Paragraph: We leverage data at scale, using machine learning models to predict and validate the most biologically relevant, progressible target hypotheses.
Our platform focuses on mechanistic-based drug discovery and combines our knowledge foundations, rapid experimentation, and feedback loops from our in-house labs to improve the quality of our target predictions.
Our machine learning infrastructure powers large scale predictions for disease targets, and provides the evidence behind predicted targets from multiple and disparate data sources, enabling data-driven decisions in target triage.
Case study
Discovering novel targets for Chronic Kidney Disease with AstraZeneca
We are collaborating with AstraZeneca to identify novel drugs for Chronic Kidney Disease (CKD) and have so far delivered the first novel AI-generated CKD target from the collaboration to AstraZeneca’s portfolio.
Precision medicine for endotype-specific drug discovery
Diseases are commonly defined by symptoms or location in the body, not by their underlying patient-specific molecular mechanisms or pathways. We leverage multimodal patient-level data to enable data-driven and endotype-specific drug discovery to inform our personalised target identification process.
Our precision medicine workflows empower drug discoverers to identify patient subgroups that could respond similarly to a particular treatment to inform the design of clinical trials.
Case study
Identifying unique GBM patient subgroups
GBM has defied conventional research efforts due to the complexity, diversity and rapid growth of GBM tumours. Our specialist team are applying precision medicine techniques to identify more effective therapeutic targets that modulate tumour generating GBM stem cells.
Molecular Design
The space for chemical exploration is infinitely vast, but only a fraction of it can potentially be made into medicines. In chemistry, we combine automation, predictive modelling - including feedback loops from our in-house labs - and structure-based drug discovery methods.
Our AI tools are designed to empower chemists to reach high-quality clinical candidates in fewer iterations, to score and rapidly triage millions of generated compounds following complex molecular profiles defined by drug discoverers, and design better drugs in fewer cycles.
Case study
Novel target discovery and compound design in Ulcerative Colitis
Our UC programme combines machine learning models, generative design and novel 3D methodology to computationally model complex endpoints and then optimise the molecular structure to achieve the best possible multi-parameter profile.
Our R&D Pipeline
Through our unique approach, we have created a growing pipeline of over 25 drug programmes at various development stages across a range of therapeutic areas.
