Nanoparticles are tiny particles, made up of just a few hundred atoms, that help create the world’s newest “smart” surfaces and systems. Nanoparticles play a key role in the development of advanced consumer products such as transparent sunscreens and stain resistant fabrics. They are also designed for biomedical applications such as the delivery of drugs inside the body.
Sounds like a miracle substance, right? The obstacle is that identifying one in the lab is akin to finding a needle in a haystack. Out of a potential pool of hundreds of thousands of nanoparticles, only a few can actually be viable, meaning that they are the right size and will function in a specific temperature range (eg, body temperature). So how can researchers facilitate the process? Machine learning.
Davoud Mozhdehi, Assistant Professor of Chemistry at the College of Arts and Sciences (A&S), and Shikha Nangia, Associate Professor of Biomedical and Chemical Engineering at the College of Engineering and Computer Science (ECS), received a National Science Foundation grant $ 575,000 develop a machine learning approach to aid in the discovery and design of new intelligent nano-biomaterials.
This project stems from the team’s recent efforts to design models for a nanoparticle to deliver therapeutic drugs to the brain. When the group used their theories to make a prediction about the size and stability of particles to operate at certain temperatures, they found their model to be wrong. Unwavering, this setback motivated them to deepen the search for a new way to propose predictive rules to guide the design of nanoparticles.
Thanks to a CUSE grant, Mozhdehi and Nangia collected preliminary data that contributed to a key element of their new proposal, which established the feasibility of using computers to predict the functional properties of nanoparticles. Their current project combines data from simulations and experiments, and uses machine learning to sort vast amounts of data to better predict the properties of a nanoparticle to respond to specific temperatures.
Their collaborative project will integrate experiments from Mozhdehi’s lab that explore physical properties such as size and shape, and computer simulations from Nangia’s lab.
By incorporating machine learning, Nangia and her students will design algorithms to simulate millions of variations of nanoparticles, based on data from previous experiments and simulations, to accelerate the design of temperature-sensitive nanoparticles. This integrated approach can reduce design time by 100 to 1000 times. That is, work that previously took a year can now be done in one to four days with their new approach.
The team’s method will seek to identify patterns in the data to determine which nanoparticles are stable at specific temperatures. Researchers compare their process to Google and Facebook algorithms that comb through millions of user data points to group individuals based on the links they select and the items they purchase online. Their algorithms will group together particles that look different but behave in the same way, like different individuals who click on the same link. Their goal is to extract attributes and assess what makes certain particles similar and what makes them dissimilar in order to develop theories to help model stable nanoparticles.
Once they know more about the functional temperatures, Mozhdehi’s lab will then conduct experiments to determine physical characteristics such as the possible size and shape of the nanoparticles. Their results can then be applied to the machine learning branch of the project to better calibrate these results.
Mozhdehi and Nangia, both members of the BioInspiré Institute, hope this project will establish a cost-effective method of enforcing rules that will one day lead to the development of stable nanoparticles over a wide range of temperatures. The researchers say this basic research could lead to the development of future nano-biomaterials capable of delivering therapeutic drugs directly to cancerous tumors and damaged organs.