Expanding the frontiers of synthetic lethality
Better molecules, by design
Evariste is an AI-enabled Drug Discovery company
We develop small molecule therapeutics targeting
synthetic lethal pathways in oncology
Novel Targets
We discover novel synthetic lethal targets and biomarkers, tailoring treatment to underserved patients in an industry fixated on the same old approaches
Better Molecules
Our automated modeling designs high quality, differentiated small molecule candidates at unprecedented scale, speed, and efficiency
Frobenius is Evariste's AI drug discovery platform
Using Frobenius, we de-risk and progress projects with unrivaled efficiency
Each stage of our platform has been validated in challenging internal and collaborative projects
Frobenius Target
Biomarker-led approaches to target discovery significantly increase the chance of clinical success. At Evariste, we apply our platform to identify novel targets and new biomarkers for known targets by integrating multi-modal data using AI-driven approaches.
Our proprietary algorithms are able to parse through large noisy multi-omic biological and chemical datasets – including proprietary and public data – and discover novel, druggable, and mechanistically actionable targets.
We have chosen to focus our work on identifying novel synthetic lethal relationships, exploiting an untapped resource in oncology.
Targets discovered by Evariste are validated in disease-relevant models to ensure their clinical applicability, and patient populations are deduced to determine which groups will benefit the most.
We have already found multiple completely novel synthetic lethal targets that have received early in vitro validation, as well as novel biomarkers for clinically validated targets that provide differentiated patient populations.
Frobenius Discovery
We begin by using various hit finding techniques ranging from trillion compound virtual screens to covalent fragments to identify novel hits, including for previously undrugged target families.
Our proprietary algorithms massively accelerate the identification of the most promising hit matter and downstream development. In contrast to conventional deep learning approaches, our machine learning models excel at working with small, noisy datasets.
After finding successful hits, we design and score novel small molecules on a scale beyond human capability.
We use probabilistic modeling for multi-parameter optimization across potency, selectivity, and pharmacokinetics. This allows us to prioritize drug candidates for testing and thus de-risks preclinical discovery.
Combining wet-lab and in silico data, we generate novel structures and use statistical techniques to prioritize candidates, achieving a 10-fold potency increase for every 30 compounds tested.
Our platform efficiently designs synthetically accessible molecules, achieving best-in-class potency and selectivity in under 50 compounds for one of our projects.
Using Frobenius, we have developed a pipeline of precision oncology therapeutics
Our pipeline features best-in-class inhibitors of validated synthetic lethal targets expanded to new indications, and first-in-class inhibitors of novel targets
PKMYT1
Targeting PKMYT1 drives synthetic lethality in cancer cells with high replication stress. We have identified and validated a novel biomarker for PKMYT1 inhibition sensitivity, with a potential for a significantly expanded and differentiated patient population, and designed novel inhibitors with high potency and selectivity.
Novel Target 1
Undisclosed metabolic enzyme target for heavily pretreated hematological malignancies. We have identified a new synthetic lethal target present in a subset of acute myeloid leukemia and diffuse large B-cell lymphoma patients, as well as in HR-deficient solid tumors. We have designed the first ever inhibitors for this target.
Novel Target 2
Undisclosed kinase target for CNS tumors. We have identified and validated this synthetic lethal relationship as a highly ranked target for glioblastoma and neuroblastoma. There are no clinical competitors for this target, and we have designed potent inhibitors optimized for CNS permeability.
Discovery
Optimization
Enabling
We are an exceptional team with expertise spanning drug discovery, mathematics and AI
We are advised by a board of world-class scientists and visionary leaders, each bringing unparalleled expertise and commitment to Evariste
Mike Waring is Chair of Medicinal Chemistry at Newcastle University and Head of Chemistry for the Cancer Research UK Newcastle Drug Discovery Unit and Director of the EPSRC Centre for Doctoral Training in Molecular Sciences. He was Principal Scientist in Medicinal Chemistry at AstraZeneca, where he led the TagrissoⓇ chemistry teams. He is a highly experienced medicinal chemist with a track record of delivering drug-discovery projects through the clinic.
.png)
Mike Waring
SCIENTIFIC DIRECTOR
Olivia Rossanese is Director of Drug Discovery and Head of Division for Cancer Therapeutics at the Institute of Cancer Research (ICR), and was previously a member of GSK’s TafinlarⓇ discovery team. Olivia has extensive experience leading and contributing to discovery and target validation programmes, as well as identification of tool molecules, lead compounds, clinical candidates.
.png)
Olivia Rossanese
SCIENTIFIC DIRECTOR
Ollie Watson received his PhD in Number Theory from University of Pennsylvania and has since worked in finance at D. E. Shaw and Tudor Capital, where he led a quantitative research team. He is an expert on optimization and statistical modeling in low signal-to-noise environments, and has taught courses on fitting predictive Bayesian models on noisy data.
Oliver Watson
CHAIRMAN OF THE BOARD
Xavier Jacq currently serves as the CSO of Moa Technology. He was Co-founder of Mission Therapeutics, former VP of Biology at Almac Discovery, and former SVP at Dunad Therapeutics. With over 20 years of experience in the biotech industry, Xavier has been instrumental in driving innovative research and development in the field of therapeutic discovery.
.jpg)
Xavier Jacq
SCIENTIFIC DIRECTOR
Zoë Walters is a lecturer in translational epigenomics in the school of Cancer Sciences and is a Module Lead on the MSc Genomics course within the Faculty of Medicine at the University of Southampton. Zoë is a highly experienced cancer biologist whose expertise lies in target identification and validation in cancer and developmental disorders. Zoë has 18+ years' experience in molecular genetics, developmental biology, and cancer biology.
Zoë Walters
SCIENTIFIC DIRECTOR
Nicholas Firth studied for his PhD in Chemoinformatics at the Institute of Cancer Research, where he developed de novo design software that implemented a fragment-based approach to explore chemical space. Nick has a deep understanding of many computational chemistry algorithms, feature engineering and machine learning for molecules.
Nicholas Firth
DIRECTOR
News
Contact us
News & updates
Stay updated with Evariste's blogposts
.png)
