Applying AI to Drug Discovery

Mission Statement

Evariste Technologies aims to increase productivity in drug discovery using automated molecular design, integrating bespoke modelling solutions into its proprietary software platform to perform molecular evolution. Using multiobjective optimization scoring functions Evariste is able to arrive at candidate molecules more quickly than the traditional design cycle.

Drug Discovery Suite

Image by Michael Dziedzic

Using machine learning models embedded in a probabilistic framework, Frobenius accelerates the hit-to-candidate stage of drug discovery projects.

Multiobjective Optimization Platform
Image by Michael Dziedzic

With access to inhibition data against a range of proteins, Hecke identifies novel hits for understudied targets and allows for principled target prioritization.

Target Prioritization Platform

Our Approach

At Evariste Technologies we use mathematics to enhance drug discovery. Using machine learning, Bayesian statistics, and game theory we have developed a robust optimization cycle to expedite drug discovery.


Our platform attains high quality candidate compounds in fewer optimization cycles than traditional drug discovery.

Ongoing Assessment

Our modelling supports ongoing validation feedback to analyse our process, eliminate waste and alert us to project termination criteria.


Our multidisciplinary team consists of domain experts motivated to solve problems  and advance our projects.


Our platform and team accelerates the optimization stage of drug development bringing drugs to market faster.


Our team has multiple ongoing programs with the ability to onboard more, and the potential to scale rapidly.


Our team leverages AI to minimise project costs through buying and testing fewer compounds in development. 

The team at Evariste uses our drug discovery suite to develop a pipeline of proprietary assets and shared assets with collaborators. If you are interested in accelerating your discovery campaigns using our tools, we have scope to onboard new collaborators.