Connect with us

Artificial Intelligence

Unlocking the Potential of LLMs for Molecule Design and Materials Creation

A new multimodal tool combines a large language model with powerful graph-based AI models to efficiently find new, synthesizable molecules with desired properties, based on a user’s queries in plain language.

Avatar photo

Published

on

The process of discovering molecules that have the desired properties to create new medicines and materials is a challenging task that consumes vast computational resources and months of human labor. Large language models (LLMs) like ChatGPT could potentially streamline this process, but they require an upgrade to understand and reason about molecular structures. Researchers from MIT and the MIT-IBM Watson AI Lab have created a promising approach that combines LLMs with graph-based AI models, resulting in a unified framework called Llamole.

Llamole uses a base LLM as a gatekeeper to understand user queries specifying desired molecular properties. As the LLM predicts text in response to the query, it switches between graph modules. One module generates the molecular structure conditioned on input requirements, while another encodes the generated molecular structure back into tokens for the LLMs to consume. The final graph module is a graph reaction predictor that takes as input an intermediate molecular structure and predicts a reaction step.

In experiments involving designing molecules that matched user specifications, Llamole outperformed 10 standard LLMs, four fine-tuned LLMs, and a state-of-the-art domain-specific method. It also boosted the retrosynthetic planning success rate from 5 percent to 35 percent by generating molecules with simpler structures and lower-cost building blocks.

The researchers built two datasets from scratch since existing datasets of molecular structures didn’t contain enough details. They augmented hundreds of thousands of patented molecules with AI-generated natural language descriptions and customized description templates. The dataset they built to fine-tune the LLM includes templates related to 10 molecular properties, so one limitation of Llamole is that it is trained to design molecules considering only those 10 numerical properties.

In future work, the researchers want to generalize Llamole so it can incorporate any molecular property. They also plan to improve the graph modules to boost Llamole’s retrosynthesis success rate. And in the long run, they hope to use this approach to go beyond molecules, creating multimodal LLMs that can handle other types of graph-based data.

Llamole demonstrates the feasibility of using large language models as an interface to complex data beyond textual description, and we anticipate them to be a foundation that interacts with other AI algorithms to solve any graph problems. This research is funded, in part, by the MIT-IBM Watson AI Lab, the National Science Foundation, and the Office of Naval Research.

Artificial Intelligence

The Power of Robot Design: How Service Robots’ Gender Characteristics Influence Customer Decisions

While service robots with male characteristics can be more persuasive when interacting with some women who have a low sense of decision-making power, ‘cute’ design features — such as big eyes and raised cheeks — affect both men and women similarly, according to new research.

Avatar photo

Published

on

By

The hospitality industry is taking a cue from new research in the Penn State School of Hospitality Management, which suggests that service robots can be designed to influence customers’ decisions based on their gender characteristics. The study found that service robots with characteristics typically associated with males may be more persuasive when interacting with women who have a low sense of power.

Led by researchers Lavi Peng, Anna Mattila, and Amit Sharma, the team conducted two studies to explore how the gender portrayed in service robots can affect customers’ decisions. In the first study, participants were asked to imagine visiting a new restaurant and receiving a menu recommendation from a service robot. The results showed that women with a low sense of power were more likely to accept recommendations from male robots.

“For men with a low sense of power, we found the difference was less obvious,” said Peng. “Based on our findings, consumers with high power tend to make their own judgment without relying on societal expectations.”

The researchers suggested that businesses could leverage these findings by using male robots to recommend new menu items or persuade customers to upgrade their rooms.

To mitigate gender stereotypes in robot design, the team conducted a second study and found that “cute” features, such as big eyes and raised cheeks, can reduce the effect of portrayed robot gender on persuasiveness. Both male and female customers responded similarly to robots with these features, suggesting that businesses could consider using cute designs to mitigate gender stereotypes.

The Marriott Foundation supported this research, highlighting the importance of understanding how service robots can influence customer decisions in the hospitality industry.

Continue Reading

Artificial Intelligence

Bismuth’s Hidden Potential: Unlocking a Stable Future for Green Electronics

Electronic devices rely on materials whose electrical properties change with temperature, making them less stable in extreme conditions. A discovery that challenges conventional wisdom in physics suggests that bismuth, a metal, could serve as the foundation for highly stable electronic components. The researchers observed a mysterious electrical effect in ultra-thin bismuth that remains unchanged across a wide temperature range, from near absolute zero (-273 C) to room temperature.

Avatar photo

Published

on

By

Bismuth, a relatively unknown metal, has been found to possess a stable and unique electrical property that could revolutionize the field of green electronics. Researchers at McGill University have made a groundbreaking discovery that challenges conventional wisdom in physics and opens up new possibilities for more efficient, stable, and environmentally friendly electronic components.

The team, led by Professor Guillaume Gervais, observed an unusual electrical effect in ultra-thin bismuth flakes, which remained unchanged across a wide temperature range, from near absolute zero to room temperature. This discovery has the potential to lead to the development of electronic devices that can function more efficiently and reliably in extreme conditions, making them ideal for space exploration, medical uses, and other high-temperature applications.

“We were so surprised by this finding,” said Gervais, “and we couldn’t believe it when our students told us they had won a bottle of wine from me on a bet. I was convinced that the effect would disappear once we increased the temperature, but it stubbornly refused to go away.”

The researchers developed a new technique for creating ultra-thin bismuth flakes by patterned microscopic trenches onto a semiconductor wafer and mechanically shaving off thin layers of the metal. They then tested these flakes under extreme magnetic fields at the National High Magnetic Field Laboratory in Florida.

This discovery has sparked interest in the scientific community, with many speculating about the potential implications for the development of topological materials and quantum computing. Gervais and his team are now exploring whether bismuth’s anomalous Hall effect can be converted into its quantum counterpart, which could pave the way for electronic devices that function at higher temperatures than previously possible.

The research was supported by various organizations, including the New Frontiers in Research Fund, the Natural Sciences and Engineering Research Council of Canada (NSERC), and the National Science Foundation (NSF).

This discovery has significant potential to revolutionize the field of green electronics and could lead to breakthroughs in space exploration, medical uses, and other high-temperature applications. As researchers continue to explore the properties of bismuth, we may see a new generation of electronic devices that are more efficient, stable, and environmentally friendly.

Continue Reading

Artificial Intelligence

The Hidden Barrier to Advanced Robotic Touch

Researchers argue that the problem that has been lurking in the margins of many papers about touch sensors lies in the robotic skin itself.

Avatar photo

Published

on

By

The development of advanced robotic touch has been hindered by a seemingly innocuous yet critical issue – the insulating layer in robotic skin. Researchers at Northwestern University and Tel Aviv University have successfully overcome this barrier, paving the way for low-cost solutions that enable robots to mimic human touch.

In their study, the researchers observed that inexpensive silicon rubber composites used to make robotic skin host an insulating layer on both top and bottom surfaces. This prevents direct electrical contact between the sensing polymer and the monitoring surface electrodes, making accurate and repeatable measurements impossible. By eliminating this error, cheap robotic skins can now allow robots to sense an object’s curves and edges, essential for proper grasping.

The research team, consisting of electrical engineers and polymer materials scientists, shed light on this problem in a paper published in Advanced Electronic Materials. The study highlights the importance of validating electrical contacts, which might unknowingly obscure device performance.

“A lot of scientists misunderstand their sensor response because they lump together the behavior of the contacts with the behavior of the sensor material, resulting in inconsistent data,” said Matthew Grayson, professor of electrical and computer engineering at Northwestern’s McCormick School of Engineering. “Our work identifies the exact problem, quantifies its extent both microscopically and electrically, and gives a clear step-by-step trouble-shooting manual to fix the problem.”

The researchers detected that adding electrically conducting fillers like carbon nanotubes to rubber composites creates an ideal candidate for touch sensors. However, this material needs electrical signals, which are blocked by the insulating layer. By sanding down the ultrathin insulation layer, the team achieved a stronger electrical contact and calibrated the thickness of the insulating layer.

The collaboration between Northwestern University and Tel Aviv University is essential in addressing the “contact preparation” challenge. The researchers relied on each other’s expertise to prepare materials and study their properties, leading to consistent results across various variables.

As awareness spreads among researchers about the issue of reproducibility in touch sensing literature, new publications can be more rigorously relied upon to advance the field with new capabilities. The research was supported by various organizations, including the U.S. National Science Foundation, Northwestern University, and Tel Aviv University through the Center for Nanoscience & Nanotechnology.

The breakthrough has significant implications for robotics development, enabling robots to sense and interact with their environment more effectively. By overcoming this critical barrier, researchers have opened up new possibilities for advanced robotic touch, paving the way for future innovations in robotics and beyond.

Continue Reading

Trending