AI Case Study

Kebotix aims to speed up materials discovery with machine learning

Kebotix leverages machine learning to discover new materials. It believes that these new compounds may have benefits such as, absorbing pollution, combating drug-resistant fungal infections, and serving as more efficient optoelectronic components. The system is fed 3-D models of molecules with known properties in order to be able to generate potential new materials.

Industry

Basic Materials

Chemicals

Project Overview

"A robot arm dips a pipette into a dish and transfers a tiny amount of bright liquid into one of many receptacles sitting in front of another machine. When all the samples are ready, the second machine tests their optical properties, and the results are fed to a computer that controls the arm. Software analyzes the results of these experiments, formulates a few hypotheses, and then starts the process over again. Humans are barely required.

The setup, developed by a startup called Kebotix, hints at how machine learning and robotic automation may be poised to revolutionize materials science in coming years. The company believes it may find new compounds that could, among other things, absorb pollution, combat drug-resistant fungal infections, and serve as more efficient optoelectronic components. The company’s software learns from 3-D models of molecules with known properties.

The goal is to use machine learning to generate candidate materials. “Discovery is too slow,” says Jill Becker, CEO of Kebotix. “You have an idea for a material, you try to make it, and you test it. Few ideas are tested, with even fewer results".

Kebotix uses several machine-learning methods to design novel chemical compounds. The company feeds molecular models of compounds with desirable properties into a type of neural network that learns a statistical representation of those properties. This algorithm can then come up with new examples that fit the same model.

Kebotix also uses another network to weed out designs that stray too far from the original and are therefore likely to be useless. Then the company’s robotic system tests the remaining chemical structures. The results of those experiments can be fed back into the machine-learning pipeline, helping it get closer to the desired chemical properties. The company dubs the overall system a “self-driving lab.”

Christoph Kreisbeck, the company’s chief product officer, says Kebotix will start out working with molecules for electronic applications and then try to tackle new polymers and alloys."

Reported Results

"The company believes it may find new compounds that could, among other things, absorb pollution, combat drug-resistant fungal infections, and serve as more efficient optoelectronic components."

Technology

"Kebotix uses several machine-learning methods to design novel chemical compounds. The company feeds molecular models of compounds with desirable properties into a type of neural network that learns a statistical representation of those properties. This algorithm can then come up with new examples that fit the same model.

Kebotix also uses another network to weed out designs that stray too far from the original and are therefore likely to be useless. Then the company’s robotic system tests the remaining chemical structures. The results of those experiments can be fed back into the machine-learning pipeline, helping it get closer to the desired chemical properties. The company dubs the overall system a “self-driving lab.”"

Function

Information Technology

Data Management

Background

"Software algorithms are already used to design chemical compounds and materials, but the process is slow and crude. Usually, a machine simply tests slight variations of a material, blindly searching for a viable new creation. Machine learning and robotics could make the process much faster and more effective. Kebotix is one of several startups working on this idea."

Benefits

Data

"3-D models of molecules with known properties"