Creating the next generation of protein-based drugs powered by machine learning and quantum computing.
Menten AI creates new drugs for indications with high unmet medical need.
Our hybrid quantum-classical computing approach allows us to access an unexplored chemical space, create new biology, and overcome the scalability challenges that limit classical approaches.
Machine Learning
Traditional methods for protein and peptide design require computationally expensive simulations. We develop new deep learning techniques that substitute these expensive calculations with fast and efficient computations that improve the accuracy of the molecules.
The Menten GCN library was developed to allow protein design using Graph Convolutional Neural Network, allowing encoding of edge attributes and showing superior performance over traditional GCN’s. Learn more...
These methods significantly accelerate the timeline for protein design on quantum computers allowing us generate hit molecules in weeks not years. Learn more...
Quantum Optimization
Menten AI created the first protein design algorithm for current and near-term quantum computers and created the world’s first protein designed on a quantum computer.
The major advantage of a quantum computing approach is the massive parallelism that can be achieved by modelling many solutions simultaneously. The number of solutions that can be modelled simultaneously doubles with each additional quantum bit, or qubit, added to the system, allowing exponential scaling far beyond anything achievable with classical computers for certain classes of search problems. We are developing quantum algorithms for both near-term NISQ and fault-tolerant quantum computers for tackling these problems.
Our qPacker algorithm demonstrates that near-term quantum computers can be leveraged for complex real-world design tasks. Learn more...
Send us an email to learn about our partnership and career opportunities or for additional questions.
contact us
