The startup develops an AI-enabled platform that identifies novel synthetic lethal targets and biomarkers for cancer treatment. By creating small molecule therapeutic drug candidates, the platform facilitates the discovery and development of targeted therapies for specific cancer types.
Funding
$7.9M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
The discovery of effective cancer treatments is often hindered by the limited number of validated drug targets and the slow pace of traditional drug discovery methods. Existing approaches may not fully leverage the potential of synthetic lethality, where the inhibition of one gene is lethal only when another gene is already inactive, leading to a more targeted approach with fewer side effects.
Solution
Evariste is an AI-enabled drug discovery company focused on developing small molecule therapeutics that target synthetic lethal pathways in oncology. The company's AI-powered platform, Frobenius, integrates multi-modal data to identify novel drug targets and biomarkers, particularly focusing on synthetic lethal relationships. Frobenius uses advanced hit-finding techniques, from trillion-compound virtual screens to covalent fragments, combined with proprietary algorithms to identify novel hits, including for undrugged target families. Machine learning models excel at working with small, noisy datasets, enabling efficient design and scoring of small molecules at an unparalleled scale. The platform also incorporates a dynamic Pose Database (PoseDB) and rapid free energy calculations using Non-Equilibrium Switching (NES) to enhance predictive accuracy and navigate sparsely explored chemical landscapes.
Target Audience
Evariste's primary customers are pharmaceutical companies and research institutions seeking to accelerate their drug discovery process and develop more effective, targeted cancer therapies.
Features
- Frobenius Target: Identification of novel synthetic lethal targets and biomarkers using multi-omic data analysis and disease-relevant models.
- Frobenius Discovery: Small molecule drug design using advanced hit-finding techniques and machine learning models for efficient design and scoring.
- Dynamic Pose Database (PoseDB): Generates protein-ligand complex snapshots via an extensive simulation pipeline to capture conformational sampling and water dynamics.
- Rapid and Scalable Non-Equilibrium Switching (NES): Cost-efficient alternative to traditional free energy calculations, leveraging short, non-equilibrium transitions between two equilibrated end states of a protein-ligand system.
- Evariste Synthetic Accessibility (ESA) Scoring: Assesses compound accessibility dynamically, enabling rapid decision-making for medicinal chemistry efforts.
- PKMYT1 Inhibitor Program: Targeting PKMYT1 drives synthetic lethality in cancer cells with high replication stress.
- VRK1 Inhibitor Program: VRK1 inhibition is synthetic lethal with VRK2 under-expression, implicating VRK1 as a highly ranked target in glioblastoma and neuroblastoma.
- Novel SL Target Program: Undisclosed metabolic enzyme target for heavily pretreated hematological malignancies.