Nav: Home

Scientists develop machine-learning method to predict the behavior of molecules

October 11, 2017

An international, interdisciplinary research team of scientists has come up with a machine-learning method that predicts molecular behavior, a breakthrough that can aid in the development of pharmaceuticals and the design of new molecules that can be used to enhance the performance of emerging battery technologies, solar cells, and digital displays.

The work appears in the journal Nature Communications.

"By identifying patterns in molecular behavior, the learning algorithm or 'machine' we created builds a knowledge base about atomic interactions within a molecule and then draws on that information to predict new phenomena," explains New York University's Mark Tuckerman, a professor of chemistry and mathematics and one of the paper's primary authors.

The paper's other primary authors were Klaus-Robert Müller of Berlin's Technische Universität (TUB) and the University of California Irvine's Kieron Burke.

The work combines innovations in machine learning with physics and chemistry. Data-driven approaches, particularly in the area of machine learning, allow everyday devices to learn automatically from limited sample data and, subsequently, to act on new input information. Such approaches have transformed how we carry out common tasks like online searching, text analysis, image recognition, and language translation.

In recent years, related development has occurred in the natural sciences, with efforts directed toward engineering, materials science, and molecular design. However, machine- learning approaches in these fields have generally not explored the creation of methodologies--tools that could advance science in ways that have already been achieved in banking and public safety.

The research team created a machine that can learn complex interatomic interactions, which are normally prescribed by complex quantum mechanical calculations, without having to perform such intricate calculations.

In constructing their machine, the researchers created a small sample set of the molecule they wished to study in order to train the algorithm and then used the machine to simulate complex chemical behavior within the molecule. As an illustrative example, they chose a chemical process that occurs within a simple molecule known as malonaldehyde. To weigh the viability of the tool, they examined how the machine predicted the chemical behavior and then compared their prediction with our current chemical understanding of the molecule. The results revealed how much the machine could learn from the limited training data it had been given.

"Now we have reached the ability to not only use AI to learn from data, but we can probe the AI model to further our scientific understanding and gain new insights," remarks Klaus-Robert Müller, professor for machine learning at Technical University of Berlin.

A video demonstrating, for the first time, a chemical process that was modelled by machine learning -- a proton transferring within the malonaldehyde molecule -- can be viewed here: http://bit.ly/2xaTuPn.
-end-
The paper's other authors also include Felix Brockherde, the lead author, who is a Ph.D. student in computer science and software engineering at the TUB, Leslie Vogt, a postdoctoral researcher in chemistry at NYU, and Li Li, a recent graduate from UC Irvine.

The study was supported, in part, by grants from the U.S. Army Research Office (W911NF-13-1-0387), the U.S. National Science Foundation (CHE 1464795), the Information & Communications Technology Promotion (IITP) of the Korean government (No. 2017-0-00451), and the Einstein Foundation.

DOI: 10.1038/s41467-017-00839-3

The impetus for the study came from a meeting between the authors at UCLA's Institute for Pure and Applied Mathematics in Los Angeles, CA.

New York University

Related Solar Cells Articles:

On the trail of organic solar cells' efficiency
Scientists at TU Dresden and Hasselt University in Belgium investigated the physical causes that limit the efficiency of novel solar cells based on organic molecular materials.
Exciting tweaks for organic solar cells
A molecular tweak has improved organic solar cell performance, bringing us closer to cheaper, efficient, and more easily manufactured photovoltaics.
For cheaper solar cells, thinner really is better
Researchers at MIT and at the National Renewable Energy Laboratory (NREL) have outlined a pathway to slashing costs further, this time by slimming down the silicon cells themselves.
Flexible thinking on silicon solar cells
Combining silicon with a highly elastic polymer backing produces solar cells that have record-breaking stretchability and high efficiency.
Perovskite solar cells get an upgrade
Rice University materials scientists find inorganic compounds quench defects in perovskite-based solar cells and expand their tolerance of light, humidity and heat.
Can solar technology kill cancer cells?
Michigan State University scientists have revealed a new way to detect and attack cancer cells using technology traditionally reserved for solar power.
Solar cells with new interfaces
Scientists from NUST MISIS (Russia) and University of Rome Tor Vergata found out that a microscopic quantity of two-dimensional titanium carbide called MXene significantly improves collection of electrical charges in a perovskite solar cell, increasing the final efficiency above 20%.
Welcome indoors, solar cells
Swedish and Chinese scientists have developed organic solar cells optimised to convert ambient indoor light to electricity.
Mapping the energetic landscape of solar cells
A new spectroscopic method now makes it possible to measure and visualize the energetic landscape inside solar cells based on organic materials.
Solar energy becomes biofuel without solar cells
Soon we will be able to replace fossil fuels with a carbon-neutral product created from solar energy, carbon dioxide and water.
More Solar Cells News and Solar Cells Current Events

Trending Science News

Current Coronavirus (COVID-19) News

Top Science Podcasts

We have hand picked the top science podcasts of 2020.
Now Playing: TED Radio Hour

Teaching For Better Humans 2.0
More than test scores or good grades–what do kids need for the future? This hour, TED speakers explore how to help children grow into better humans, both during and after this time of crisis. Guests include educators Richard Culatta and Liz Kleinrock, psychologist Thomas Curran, and writer Jacqueline Woodson.
Now Playing: Science for the People

#556 The Power of Friendship
It's 2020 and times are tough. Maybe some of us are learning about social distancing the hard way. Maybe we just are all a little anxious. No matter what, we could probably use a friend. But what is a friend, exactly? And why do we need them so much? This week host Bethany Brookshire speaks with Lydia Denworth, author of the new book "Friendship: The Evolution, Biology, and Extraordinary Power of Life's Fundamental Bond". This episode is hosted by Bethany Brookshire, science writer from Science News.
Now Playing: Radiolab

Dispatch 3: Shared Immunity
More than a million people have caught Covid-19, and tens of thousands have died. But thousands more have survived and recovered. A week or so ago (aka, what feels like ten years in corona time) producer Molly Webster learned that many of those survivors possess a kind of superpower: antibodies trained to fight the virus. Not only that, they might be able to pass this power on to the people who are sick with corona, and still in the fight. Today we have the story of an experimental treatment that's popping up all over the country: convalescent plasma transfusion, a century-old procedure that some say may become one of our best weapons against this devastating, new disease.   If you have recovered from Covid-19 and want to donate plasma, national and local donation registries are gearing up to collect blood.  To sign up with the American Red Cross, a national organization that works in local communities, head here.  To find out more about the The National COVID-19 Convalescent Plasma Project, which we spoke about in our episode, including information on clinical trials or plasma donation projects in your community, go here.  And if you are in the greater New York City area, and want to donate convalescent plasma, head over to the New York Blood Center to sign up. Or, register with specific NYC hospitals here.   If you are sick with Covid-19, and are interested in participating in a clinical trial, or are looking for a plasma donor match, check in with your local hospital, university, or blood center for more; you can also find more information on trials at The National COVID-19 Convalescent Plasma Project. And lastly, Tatiana Prowell's tweet that tipped us off is here. This episode was reported by Molly Webster and produced by Pat Walters. Special thanks to Drs. Evan Bloch and Tim Byun, as well as the Albert Einstein College of Medicine.  Support Radiolab today at Radiolab.org/donate.