IBM today announced the launch of the Molecule Generation Experience (MolGX), a cloud-based, AI-driven molecular design platform that automatically invents new molecular structures. MolGX, a part of IBM’s overarching strategy that aims to accelerate the discovery of new materials by 10 to 100 times, uncovers materials from the property targets of a given product.

The chemical sciences have made strides in the discovery of novel and useful materials over the past decades. For example, in the area of polymers, the recent development of thermoplastics has had an influence on applications ranging from new paints to clothing fibers. But while the discovery of new materials is the driving force in the expansion and improvement of industrial products, the vastness of chemical space likely exceeds the ability of human experts to explore even a fraction of it.

By observing and selecting a dataset, MolGX leverages generative models to produce molecules from chemical properties like “solubility in water” and “heatability.” The platform trains an AI model to predict chemical characteristics within given parameters and synthesizes molecular structures based on the model built.

“The development of new materials follows a number of different pathways, depending on both the nature of the problem being pursued and the means of investigation. Breakthroughs in the discovery of new materials span from pure chance, to trial-and-error approaches, to design by analogy to existing systems,” Seiji Takeda, technical lead of material discovery at IBM, wrote in a blog post. “While these methodologies have taken us far, the challenges and requirements for new materials are more complex — so too are the demands and issues for which new materials are needed. As we face global problems such as pandemics and climate change, the necessity and urgency to design and develop new medicines and materials at a faster pace and on a molecular scale through to the macroscopic level of a final product is becoming increasingly important.”

IBM has released a free trial version of MolGX trained using a built-in dataset, which the company applied internally to the development of a new photoacid generator — a key material in electronics manufacturing. A professional version of MoIGX with additional functionality including data upload, results exportation, customized modeling, and more is available with a license. According to IBM, this paid release carried out the inverse design of sugar and dye molecules over 10 times faster than human chemists at Nagase & Co Ltd, a chemical manufacturing company.

Beyond IBM, startups like Kebotix are developing AI tools that automate lab experiments to uncover materials faster than with manual techniques. Meanwhile, Facebook and Carnegie Mellon have partnered on a project to discover better ways to store renewable energy, in part by tapping AI to accelerate the search for electrocatalysts, or catalysts that participate in electrochemical reactions.