Welcome to Norachem

An entirely new paradigm in drug discovery

Norachem uses AI-based generative design to make novel drugs for specific diseases - from scratch.

Norachem blows the traditional drug discovery process out of the water.

Current computational approaches in drug discovery are suboptimal— resulting in a half-decade long numbers game that costs millions of dollars and is prone to error.

Norachem uses generative design to tailor molecules for specific diseases. Our algorithms can access a region of near-infinite chemical space while simultaneously optimizing for ease of synthesis, low toxicity, and high binding affinity— resulting in faster, less expensive, and superior drug molecules.

  • Faster Discovery

    Our generative design paradigm searches the chemical space more effectively and uncovers promising hits with lead-optimized features.

  • Lower Cost

    Our unique computational approach minimizes the need for synthesis and testing, thereby reducing the cost of drug discovery tremendously.

  • Better Drugs

    Our novel optimization techniques scan the chemical space more thoroughly than any competing approach, and produce better drug molecules.

Norachem's current focus is on creating better drugs for cancers, CNS diseases like Alzheimer's, and aging. But the potential of our technology isn’t limited to the pharmaceutical industry.

Our ultimate goal is for Norachem to be used to find better solutions wherever less toxic and more effective chemicals are needed.

Publications

03/30/2022

On the Question of Rediscovering Drug Molecules

In conversations with people outside Norachem, the most common enquiry is whether the platform can rediscover a known drug. An intriguing question — since it is often accompanied by the belief that by doing so, Norachem would provide renewed validation of its generative design paradigm. So, we decided to run simulations to prove Norachem’s capabilities in this regard…

09/02/2021

On the Shortcomings of Continuous Representations of Chemical Space

The paper (Gomez-Bombarelli et al., 2018), which introduces Chemical VAE and provides the exploratory technique for the GENTRL model described in (Zhavoronkov et al., 2019), makes a few stark claims in its introduction…

05/31/2021

Generative Design for De Novo Drugs

Recent years have seen a surge in the use of computational methods to design de novo drugs. In most instances, the computation has consisted entirely of using predictive modeling to screen a chemical library to identify potent compounds. This approach towards drug discovery has several shortcomings…