Display screens made from organic light-emitting diodes (OLEDs) are becoming ever more popular and are beginning to replace liquid crystal display (LCD) technology. They work using organic LEDs that emit light when an electric current is applied. Since they do not require a backlight, they can be made as thin and flexible as a sheet of plastic and individual pixels can be switched on and off, which improves the screen’s colour contrast and the amount of energy that it consumes.

However, there is one problem: OLEDs require green, red and blue sub-pixels to reproduce all the colours on a screen, but it is difficult to find stable and efficient blue LEDs based on purely organic molecules. This makes OLEDs less competitive in terms of price for larger displays, such as those in televisions.

Quickly identifying new candidate OLED molecules

The new Molecular Space Shuttle screening process developed by a team of researchers led by Alan Aspuru-Guzik makes use of theoretical and experimental chemistry, machine leaning and cheminformatics to quickly identify new candidate OLED molecules that perform as well or even better than the best industry standards.

The researchers began by building a library of more than 1.6 million molecules and then developed machine-learning algorithms (based on neural networks) to predict which ones were likely to have good blue light-emitting characteristics.

"Molecules are like athletes"

"We were able to predict the colour and brightness of the molecules from a simple quantum chemical calculation using about 12 hours of computing time per molecule," explains team member Rafael Gomez-Bombarelli.

"Molecules are like athletes," adds Aspuru-Guzik. "It’s easy to find a runner, a swimmer and a cyclist, but difficult to find all three. Our molecules have to be triathletes – they have to be blue, stable and bright."

The team, reporting its work in Nature Materials doi:10.1038/nmat4717, went one step further with its aptly named “molecular Tinder” application, which identified 2500 molecules worth exploring further. Each month, the researchers "voted" for the most "attractive" ones and then pooled their results.

Screening technique might be extended to other molecules

The new approach drastically reduces the need for synthesising, experimentally characterising and optimising real-world molecules in the lab and might allow OLED technology to advance faster and more efficiently, say the researchers. And the icing on the cake: the screening technique might also be extended to molecules other than those used to make OLEDs.

"More challenges lie ahead," says Aspuru-Guzik. "We are currently working on exploring aspects of molecular stability for a variety of applications. How resistant to degradation can an organic molecule be for a particular application? That is an open question that we are now focusing on," he tells nanotechweb.org.