Evariste Ltd.

Evariste will be attending the 2025 edition of the AACR Annual Meeting held in Chicago, IL from April 25-30. The company will be presenting a poster detailing the latest progress on EVT-0003023, a potentially best-in-class inhibitor of PKMYT1. Section 21, McCormick Place Convention Center, Chicago, IL | April 28, 9:00 AM - 12:00 PM Authors: Daniel Miller, Alfie Brennan, Jan Lanz, Oliver Vipond, Noah Harrison, James Aaronson, Anna Hercot. Evariste Ltd, London, United Kingdom Title: Discovery and preclinical profiling of a novel PKMYT1 inhibitor, EVT-0003023, with high efficacy in late-stage, post-treatment non-small cell lung cancer models Abstract: Protein kinase membrane-associated tyrosine/threonine 1 (PKMYT1) is a negative regulator of CDK1 activity and has been identified as a putative synthetic lethal target in cancers which up-regulate cyclin E (CCNE1) or harbor mutations in genes such as FBXW7. We used our internal Frobenius platform to identify highly potent and differentiated inhibitors of PKMYT1 with exceptional selectivity over key off targets, including the Raf family and WEE1. Machine learning-driven optimization delivered a preclinical candidate compound, EVT-0003023, with best-in-class selectivity and a significantly improved pharmacokinetic profile in relevant animal models, and in vivo efficacy in CCNE1-high and FBXW7-mutated xenograft models.Compounds from this series were used to validate a differentiated biomarker for sensitivity to PKMYT1 inhibition in cellular and PDX-derived models, expanding the patient population treatable with PKMYT1 inhibitors into non-small cell lung cancer. Using clinical data, we demonstrated that this biomarker is significantly up-regulated in patients who have progressed on existing standard-of-care treatment, and demonstrated exceptional monotherapy activity for EVT-0003023 in PDX models reflecting this patient population, as well as tumor regression when combined with low doses of chemotherapy. ‍

LONDON–(BUSINESSWIRE)–Evariste and the University of Southampton have partnered to generate one of the largest available transcriptomic datasets in oesophageal adenocarcinoma (OAC). This clinically annotated data will allow the identification of novel targets in this extremely hard to treat cancer. In collaboration with the team at Southampton, Evariste will apply its AI-driven discovery engine to identify novel therapeutic targets for OAC patients. Anna Hercot, CEO of Evariste, said “High quality genetic data linked to clinical outcomes is essential for identifying the next generation of precision oncology therapeutics. This data and our collaboration with the outstanding team at Southampton will help accelerate the delivery of medicines to OAC patients, who currently have very few targeted treatment options.” Professor Tim Underwood, Consultant Surgeon and Professor of Gastrointestinal Surgery at the University of Southampton, said “We are really struggling to make meaningful breakthroughs for patients with oesophageal cancer, data like this might just unlock the next generation of targets for treatment.” Fellow Southampton scientist Dr Zoë Walters, Associate Professor in Translational Epigenomics and a member of Evariste’s Scientific Advisory Board, said “Historical strategies have focussed on the perceived low hanging fruit in leveraging cancer mutations as potential therapeutic strategies. However, these have yielded very little in terms of new therapeutic strategies in the context of oesophageal cancer. This collaboration will utilise our extensive transcriptomic dataset to identify new targets for therapy and ultimately novel potential therapeutic strategies for these patients.” Evariste is a TechBio using mathematics and AI to develop small molecule therapeutics for oncology. Their AI-powered platform, Frobenius, identifies novel targets and biomarkers and designs drug candidates at unparalleled speed. Evariste aims to expand the frontiers of cancer treatment by discovering new targets and designing improved molecules. Scientists from the University of Southampton’s School of Cancer Sciences are pioneering new research to better understand the disease and develop more effective treatments for patients. It also trains the next generation of cancer researchers who can understand the disease and develop new and more effective treatments to improve patient treatment. Anna Hercot, CEO: contact@evariste.com

‍Over the past decade, machine learning models have cemented themselves as one of the cornerstones underpinning the computational revolution in drug discovery. Despite substantial progress, several challenges remain and machine learning methods have yet to achieve their full transformative potential. One of the most pressing issues lies in the availability of high quality, uniformly-sourced experimental data that covers diverse chemical space. Without such data, AI models are limited in quality and generalisability. Enter physics-based simulations. These simulations, specifically free energy calculations, can predict highly accurate binding data for potential drug molecules at a fraction of the time and cost of real-world experiments. By modelling how molecules interact with protein targets at the atomic level, simulation-based methods massively outperform simpler approaches to binding energy prediction, such as molecular docking. In particular, they are able to account for the flexibility of both the drug and the protein as well as how water molecule dynamics influence binding. However, free energy calculations have traditionally been difficult to set up and require access to substantial amounts of computational resources. At Evariste, we have developed an incredibly fast and highly automated free energy pipeline that can generate huge swathes of uniformly sourced binding data on the fly. Integrating this data into Frobenius Discovery allows our models to reach even greater predictive accuracies and better navigate sparsely explored chemical landscapes, focussing on the most promising areas of search. ‍As mentioned, the predictive power of traditional approaches to free energy calculations comes at a hefty computational cost. The mainstay of these calculations, relative binding free energy perturbations (FEP) demand a large number of lengthy simulations to be performed. Furthermore, setting up these simulations often requires laborious planning and careful execution by domain experts, with rigorous testing and meticulous strategy adjustments necessary to avoid incorrect or misleading results. Non-Equilibrium Switching (NES) offers a powerful, cost-efficient alternative. To briefly summarise, NES leverages short (80x100picosecond), non-equilibrium transitions between two equilibrated end states of a protein-ligand system[4]. Critically, this approach is both accurate and significantly faster than standard equilibrium FEP methodologies. Where conventional methods might often consume at least 50 nanoseconds of simulation time per calculation (minimally 5ns simulations at 10 different lambda windows[2, 3]), NES can achieve comparable accuracy in roughly 20 nanoseconds—a reduction of about 60%. Implementing Evariste’s “Node-based NES” protocol further enhances both the speed and accuracy of the calculations and will be the subject of a future blog post. These calculations are massively parallelisable as each of the 100ps transitions can be run as an independent simulation. Evariste’s acceptance into Google Cloud and NVIDIA’s startup programs has provided us with access to extensive on-demand cloud computing resources, making NES's parallelisability a game-changer for accelerating our workflows. ‍ A common challenge in free energy calculations is the reliance on high-quality starting structures, typically sourced from experimentally determined protein-ligand crystal complexes. Without these crystal structures, users often resort to docking each new compound individually, hoping the predicted pose resembles the true binding mode. This process can be both time-consuming and error-prone, and suffers from poor ligand-receptor complementarity as well as non-optimised water networks in the binding site, leading to worse estimates of binding energy. To overcome this hurdle and ensure the robust generation of ligand poses without crystal structures, we developed an approach called the Dynamic Pose Database (PoseDB). The PoseDB stores a library of protein-ligand complex snapshots generated via an extensive simulation pipeline. This pipeline successfully captures conformational sampling and water dynamics, effectively mimicking the protein-ligand interactions one may observe in vivo and captured via crystal structures. For any new target molecule, our platform selects the best-matching entry from the PoseDB and aligns the new compound to the pre-validated pose. This eliminates the need to perform individual pose generation for new target molecules, reducing setup time. More importantly, it enables accurate free energy calculations even in the absence of crystal structures. In backtests on our lead project where we compare this method to utilising publicly available crystal structures, the enhanced pipeline improves the experimental vs predicted Pearson r value from 0.28 to 0.65 and reduces the RMSE from 3.13 kcal/mol to 2.12 kcal/mol. The data generated by these rapid free energy calculations is stored in a database used to train our machine learning models. Traditional ML models, often limited to 2D ligand data, can overlook critical structural insights. By integrating free energy data, Frobenius Discovery incorporates dynamic, structural information of protein-ligand complexes, enhancing predictive accuracy. Top predictions seamlessly feed back into the NES pipeline to refine and confirm our predictions. Thanks to this integration, we can evaluate millions of potential compounds in seconds using Frobenius Discovery and rapidly prioritise the most promising of candidates. ‍