The startup develops a computational platform utilizing proprietary molecular AI technology for the discovery of small-molecule drugs aimed at treating severe diseases. This approach enhances the efficiency of drug development processes, ultimately improving clinical outcomes for patients.
Funding
$327.4M 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
Traditional drug discovery methods for small-molecule therapeutics targeting severe diseases are often inefficient and struggle with chemically complex or previously undruggable targets. This can lead to delays in identifying viable drug candidates and ultimately impact clinical outcomes for patients.
Solution
Genesis Therapeutics has developed GEMS, an advanced molecular AI platform that integrates generative and predictive AI models to accelerate the discovery of small-molecule drugs. GEMS utilizes language models for molecular generation, diffusion models for predicting protein-ligand structures, and physical machine learning to predict potency and selectivity. The platform enables the generation of millions of drug-like molecules, predicts 3D structures of protein-ligand complexes, and integrates physical simulation with deep learning to predict potency and selectivity. Genesis's Nucleus interface allows chemists to deploy GEMS in their daily work, streamlining the drug discovery process and enabling the identification of highly potent and selective candidates.
Target Audience
The primary target audience includes pharmaceutical companies and research institutions focused on discovering small-molecule drugs for severe diseases, particularly those with difficult or previously undruggable targets.
Features
- GEMS AI platform integrates language models, diffusion models, and physical ML for molecular generation and property prediction.
- ADME-conditioned language models generate new drug candidate ideas.
- Diffusion models predict protein-ligand structures for potency predictions.
- Physical ML integrates structure-based deep learning with physical simulation for potency and selectivity predictions.
- Nucleus interface allows chemists to control molecule generation and review results.
- The platform is used to generate first-in-class small molecules for validated and novel immunology targets.
- The platform is used to generate best-in-class pan-mutant PIK3CA inhibitors for oncology.