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.
A new learning algorithm is illustrated on a molecule known as malonaldehyde that undergoes an internal chemical reaction. The distribution of red points corresponds molecular configurations used to train the algorithm. The blue points represent configurations generated independently by the learning algorithm. The turquoise points confirm the predictions in an independent numerical experiment.
Image courtesy of Leslie Vogt
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.
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.
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.
James Devitt | EurekAlert!
Epilepsy: Seizures not forecastable as expected
25.09.2019 | Rheinische Friedrich-Wilhelms-Universität Bonn
Dresden creates ground-breaking interface between technology and medicine
05.09.2019 | Technische Universität Dresden
A new research project at the TH Mittelhessen focusses on the development of a novel light weight design concept for leisure boats and yachts. Professor Stephan Marzi from the THM Institute of Mechanics and Materials collaborates with Krake Catamarane, which is a shipyard located in Apolda, Thuringia.
The project is set up in an international cooperation with Professor Anders Biel from Karlstad University in Sweden and the Swedish company Lamera from...
Superconductivity has fascinated scientists for many years since it offers the potential to revolutionize current technologies. Materials only become superconductors - meaning that electrons can travel in them with no resistance - at very low temperatures. These days, this unique zero resistance superconductivity is commonly found in a number of technologies, such as magnetic resonance imaging (MRI).
Future technologies, however, will harness the total synchrony of electronic behavior in superconductors - a property called the phase. There is currently a...
How do some neutron stars become the strongest magnets in the Universe? A German-British team of astrophysicists has found a possible answer to the question of how these so-called magnetars form. Researchers from Heidelberg, Garching, and Oxford used large computer simulations to demonstrate how the merger of two stars creates strong magnetic fields. If such stars explode in supernovae, magnetars could result.
How Do the Strongest Magnets in the Universe Form?
A hot, molten Earth would be around 5% larger than its solid counterpart. This is the result of a study led by researchers at the University of Bern. The difference between molten and solid rocky planets is important for the search of Earth-like worlds beyond our Solar System and the understanding of Earth itself.
Rocky exoplanets that are around Earth-size are comparatively small, which makes them incredibly difficult to detect and characterise using telescopes. What...
Scientists at the Max Planck Institute for Chemical Physics of Solids in Dresden, Princeton University, the University of Illinois at Urbana-Champaign, and the University of the Chinese Academy of Sciences have spotted a famously elusive particle: The axion – first predicted 42 years ago as an elementary particle in extensions of the standard model of particle physics.
The team found signatures of axion particles composed of Weyl-type electrons (Weyl fermions) in the correlated Weyl semimetal (TaSe₄)₂I. At room temperature,...
02.10.2019 | Event News
02.10.2019 | Event News
19.09.2019 | Event News
14.10.2019 | Physics and Astronomy
14.10.2019 | Earth Sciences
14.10.2019 | Health and Medicine