Technology 3 min read

IBM Announces AI-Based Chemistry Lab to Develop new Materials

Carson Masterson /

Carson Masterson /

The process of devising new material has remained the same for thousands of years.

It involves combining several raw materials, usually through specific treatments, to induce chemical reactions. Indeed, it’s a trial-and-error method that’s not only tedious but also expensive.

According to IBM, it costs an average of $10 million and ten years to develop useful new material.

For example, researchers began working on Nylon as far back as 1927. But, it was first used in toothbrush in 1938. Similarly, the synthesis of vitamin B12 required 12 years and a workforce of over 100 people.

IBM hopes to cut the time and expense by automating a bulk of the process through artificial intelligence and cloud technology. With that in mind, the company has launched an AI-based chemistry lab.

In a blog post announcement, Distinguished RSM, Manager at IBM Research Europe, Teodoro Laino wrote:

“All it took was a combination of AI, cloud technology, and chemistry automation. This mixture led to the creation of RoboRXN: machine learning algorithms autonomously designing and executing the production of molecules in a laboratory remotely accessible with as little human intervention as possible.”

IBM described the groundbreaking work in the peer-reviewed journal, Nature Communications.

An AI-based Chemistry Lab for Efficient Raw Material Creation

Back in 2018, IBM launched RXN for Chemistry — a free cloud-based app that predicts the outcome of chemical reactions. While RoboRXN is an expansion of the app, it takes things a step further.

The new autonomous lab allows chemists to feed the system a molecule that they intend to create. In response, the AI provides a step-by-step guide of the process, including a list of ingredients to use.

Laino wrote:

“Imagine an AI model that can not only retrieve your favorite recipes upon request. It can also automatically draw from its embedded knowledge to deliver an optimal list of instructions to make that gourmet pizza that will surely impress your dinner guests.”

According to IBM, the new system will help chemists to synthesize materials in unprecedented ways.

For example, assume that scientists discover a plant that might slow the onset of Alzheimer’s disease. After close study, they were able to identify the active ingredient in the plant — a specific molecule.

The next step would involve trying to synthesize that molecule in the lab, which could take years.

RoboRxn simplifies the process significantly, said IBM. The chemist simply needs to submit the particulars of the molecule. After that, the system would generate explicit instructions on how to make it.

Like all new technologies, the system is not perfect.

For one, there’s no guarantee that the formula that RoboRxn generates would be cost-effective. Also, the system’s current configuration can only handle five synthetic steps.

Read More: IBM’s Supercomputer Identifies 77 Potential COVID-19 Treatments

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.

Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Least Recent least recent
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.