A long-held goal by chemists across many industries, including energy, pharmaceuticals, energetics, food additives and organic semiconductors, is to imagine the chemical structure of a new molecule and be able to predict how it will function for a desired application. In practice, this vision is difficult, often requiring extensive laboratory work to synthesize, isolate, purify and characterize newly designed molecules to obtain the desired information.

Recently, a team of Lawrence Livermore National Laboratory (LLNL) materials and computer scientists have brought this vision to fruition for energetic molecules by creating machine learning (ML) models that can predict molecules’ crystalline properties from their chemical structures alone, such as molecular density. Predicting crystal structure descriptors (rather than the entire crystal structure) offers an efficient method to infer a material’s properties, thus expediting materials design and discovery. The research appears in the Journal of Chemical Information and Modeling.

“One of the team’s most prominent ML models is capable of predicting the crystalline density of energetic and energetic-like molecules with a high degree of accuracy compared to previous ML-based methods,” said Phan Nguyen, LLNL applied mathematician and co-first author of the paper.

“Even when compared to density-functional theory (DFT), a computationally expensive and physics-informed method for crystal structure and crystalline property prediction, the ML model boasts competitive accuracy while requiring a fraction of the computation time,” said Donald Loveland, LLNL computer scientist and co-first author.

Members of LLNL’s High Explosive Application Facility (HEAF) already have begun taking advantage of the model’s web interface, with a goal to discover new insensitive energetic materials. By simply inputting molecules’ 2D chemical structure, HEAF chemists have been able to quickly determine the predicted crystalline density of those molecules, which is closely correlated with potential energetics’ performance metrics.

“We are excited to see the results of our work be applied to important missions of the Lab. This work will certainly aid in accelerating discovery and optimization of new materials moving forward,” said Yong Han, LLNL materials scientist and principal investigator of the project.

Follow-up efforts within the Materials Science Division have used the ML model in conjunction with a generative model to search large chemical spaces quickly and efficiently for high density candidates.

“Both efforts push the boundaries of materials discovery and are facilitated through the new paradigm of merging materials science and machine learning,” said Anna Hiszpanski, LLNL material scientist and co-corresponding author of the paper.

The team continues to search for new properties of interest to the Lab with the vision of providing a suite of predictive models for materials scientists to use in their research.

The post Machine learning aids in materials design appeared first on Artificial Intelligence.

UNIVERSITY PARK, Pa. — In smart cities of the future, sensors distributed throughout buildings and bridges could monitor infrastructure health. Cloud-based computing could decrease traffic with real-time analysis available to commuters. Windows could tint themselves darker on sunny days or lighten to brighten a room on cloudy ones. 

None of these innovations, however, can materialize without managing the enormous amounts of data generated by robust sensing networks, according to an interdisciplinary team of Penn State researchers. They published a perspective article on March 19 in Science, highlighting smart materials that can sense environmental changes and respond accordingly — without externally transferring data — as one avenue to avoid this data overload.

Science also released a podcast featuring the work on March 18, outlining the benefits of implementing smart materials in tomorrow’s cities, ranging from self-healing concrete structures to building materials that can solve complex equations. 

“Since this problem sits at the intersection of materials science, structural health monitoring and computation, collaboration was important from the get-go,” said Rebecca Napolitano, assistant professor of architectural engineering, who co-wrote the article. 

Napolitano collaborated with Wesley Reinhart, assistant professor of materials science and engineering in the College of Earth and Mineral Sciences, and Juan Pablo Gevaudan, affiliate professor of architectural engineering and Marie Sklodowska-Curie Research Fellow at the University of Leeds. 

Napolitano’s interest in smart cities began during her graduate studies, when she wondered how historic buildings would be accommodated in cities of the future. Her current research, focused on supporting merging infrastructures via computational methods, led her to collaborate with Gevaudan. He investigates how modern concrete materials degrade to better engineer their response and ability to adapt to certain conditions in new and existing buildings. The two researchers lead the adaptive architecture research area in the Convergence Center for Living Multifunctional Material Systems at Penn State.

Reinhart and Napolitano previously collaborated to investigate building damage at the micro- and macroscales through computation. Reinhart works on metamaterials, which are materials engineered to gain unique properties from their structure, and their potential applications in infrastructure. For example, such a metamaterial could sense the path of the sun and perform a calculation to adjust a solar panel accordingly and optimize the energy stored. 

The researchers plan to continue exploring avenues for developing these materials and robust computational methods to optimize them. With further research, according to the researchers, the implementation of smart materials could increase the lifetime of buildings and civil structures, reduce energy consumption and reduce waste from production and use of electronic sensors — all on a citywide scale.

The post Smart materials could pose solution for big-data bottleneck in future cities appeared first on Artificial Intelligence.

Scientists and engineers are on a quest to develop electronic devices that are compatible with our bodies: think of materials that can help wire neurons back together after brain injuries, or diagnostic tools that can easily be absorbed within the body.

A family of self-assembling peptides, called π-conjugated oligopeptides, has shown promise for becoming the basis of the next-generation of these electronic, biocompatible materials. But identifying the right molecular sequences to create the optimal self-assembled nanostructures would require testing thousands of possibilities that each take approximately one month to test in the lab.

Assoc. Prof. Andrew Ferguson and his collaborators have sped up that process by developing machine learning tools that can screen for the best candidates. By screening 8,000 candidates of self-assembled peptides, the team was able to rank each design. That paves the way for experimentalists to test the most promising candidates.

The results were published in The Journal of Physical Chemistry B. The paper was also selected as the ACS Editors’ Choice, which offers free public access to new research of importance to the global scientific community, and to be featured on the journal cover.

“By understanding data science, materials science, and molecular science, we were able to find an innovative way to screen for new possible candidates,” Ferguson said. “The fact that this paper was chosen as an ACS Editors’ Choice shows that there is a lot of interest in coupling artificial intelligence to domain science. It’s an important problem that is of broad interest to the physical chemistry community.”

Ranking peptides for experimentalists

To help find the best candidates, Ferguson and graduate student Kirill Shmilovich screened a family of π-conjugated oligopeptides using machine learning and molecular simulation. The set included 8,000 potential peptides, if researchers kept the same core and just changed the three amino acids on each side of the molecule. (The amino acids on the sides are symmetrical—if you change one on one side, it changes on the other side, as well.)

Using a form of machine learning known as active learning or Bayesian optimization to guide molecular simulations, they were able to construct reliable data-driven models of how the sequence of the peptide influenced its properties after considering only 186 peptides.

The model predictions could then be reliably extrapolated to predict the properties of the rest of the peptide family. The process also removed human bias from the equation, letting artificial intelligence find features of peptide designs that researchers hadn’t considered before that actually made them better candidates.

They then ranked each peptide and handed off their results to their experimental collaborators, who will then test the top candidates in the lab. Next, they hope to expand their system to include trying out different π-conjugated cores, while feeding new experimental data back into the loop to further strengthen their models.

They also hope to use this machine learning system for designing proteins, optimizing self-assembling colloids to make atomic crystals, and even to one day incorporate these tools into a self-driving laboratory, where artificial intelligence would take data, create predictions, run experiments, then feed that data back to the model—all without human intervention.

“This is a method that could be useful in many different domains,” Ferguson said.

The post Machine learning reveals new candidate materials for biocompatible electronics appeared first on Artificial Intelligence.

Machine learning’s ability to perform intellectually demanding tasks across various fields, materials science included, has caused it to receive considerable attention. Many believe that it could be used to unlock major time and cost savings in the development of new materials.

The growing demand for the use of machine learning to derive fast-to-evaluate surrogate models of material properties has prompted scientists at the National Institute for Materials Science in Tsukuba, Japan, to demonstrate that it could be the key driver of the “next frontier” of materials science in recently published research.  

Insufficient Materials Data

To learn, machines rely on processing data using both supervised and unsupervised learning. 

With no data, however, there is nothing to learn from. 

Unfortunately, potential technological advances in machine learning and its potential applications in materials science are not being fully exploited due to a considerable lack of volume and diversity of materials data. This, the Japanese researchers believe, is greatly stifling progress.

However, a machine learning framework known as “transfer learning” is said to have great potential in being able to overcome the problem of a relatively small data supply. This framework relies on the concept that various property types – for example, physical, electrical, chemical, and mechanical – are physically interrelated. 

To successfully predict a target property from a limited supply of training data, the researchers used models of related proxy properties that have been pretrained using sufficient data. These models are then able to capture common features that are relevant to the target task.

This repurposing of machine-acquired features on the target task has demonstrated high prediction performance even when the data sets are very small

Facilitating the Widespread Use of Transfer Learning

To facilitate the widespread use and boost the power of transfer learning, the Japanese researchers created their own pre-trained model library, XenonPy.MDL. 

In its first release, the library is comprised of more than 140,000 pre-trained models for various properties of small molecules, polymers, and inorganic crystalline materials. Along with these models, the researchers provide literature that describes some of their most outstanding successes of applying transfer learning in varying scenarios. Examples such as being able to build models using the framework in conjunction with only dozens of pieces of materials data nicely hammer home the effectiveness of the transfer learning framework.

The researchers also highlight how they discovered that transfer learning transcends across different disciplines of materials science, such as underlying bridges between organic and inorganic chemistry. 

Indispensable to Machine Learning-Centric Workflows

Although transfer learning is being used often across various fields of machine learning, its use in materials science is still lacking. 

Furthermore, the limited availability of openly accessible big data will likely continue in the near future, the researchers say, due to a distinct lack of incentives for data sharing, a problem partly caused by the conflicting goals of stakeholders across academia, industry, and public and government organizations. This means that the relevance of transfer learning will only grow and contribute further to the success of machine learning-centric workflows in materials science.

The post Using Transfer Learning to Overcome the Barriers Facing Machine Learning in Materials Science appeared first on Artificial Intelligence.