AI Predicts Organic Reactions | AIChE

AI Predicts Organic Reactions

November
2018

Imagine a way to uncover the unknown product of a set of reactants, any set of reactants, without fear of wasting resources or time, or producing a toxic byproduct. Researchers at IBM in Zurich have achieved just that with a new technology that implements artificial intelligence (AI) to predict the outcomes of complex organic chemistry reactions. IBM officially launched the system in August, and it is freely available online for students and researchers to use at the following link: www.research.ibm.com/ai4chemistry.

In 1969, chemists discovered that organic synthesis could be performed by machines, which were able to rationalize immense sets of reactants and reactions. The race to produce target molecules using datasets has been barreling ahead since then.

Previous efforts in the past 50 years have been brilliant but tedious — both time- and labor-intensive. The IBM researchers have developed an AI-based technique that recognizes reactants and predicts products within seconds.

The technology behind the new system is based on neural machine translation, which is commonly used by companies like Google to automatically convert webpages written in one language, such as Spanish, into another language, such as English.

This notion is what inspired IBM researchers to treat organic chemistry like a language of its own, where each chemical structure corresponds to a...

Would you like to access the complete CEP News Update?

No problem. You just have to complete the following steps.

You have completed 0 of 2 steps.

  1. Log in

    You must be logged in to view this content. Log in now.

  2. AIChE Membership

    You must be an AIChE member to view this article. Join now.

Copyright Permissions 

Would you like to reuse content from CEP Magazine? It’s easy to request permission to reuse content. Simply click here to connect instantly to licensing services, where you can choose from a list of options regarding how you would like to reuse the desired content and complete the transaction.