How AI Is Taking on the Plastic Problem by Dr. Timothy Smith

Photo Source: Unsplash

Following World War II, rapid advances in chemistry and manufacturing expanded the variety and quantity of plastics used in almost every segment of industry and agriculture. The low cost of production, easy moldability, light weight, and strength of plastics catapulted them into vital components in diverse industries, from automotive to consumer electronics, including the preferred packaging material for many types of food and beverages. Lightweight containers reduce transportation costs, further driving the preference for plastic packaging. As with many new advances, with the good comes the bad.

Many types of plastics have a significant downside—they are single-use and do not readily break down in the environment. Therefore, plastic trash accumulates in landfills and the oceans of the world. Unlike more natural products such as paper, metal, and glass made from plant fibers, iron, and sand, plastics come from the chemical polymerization of organic molecules. In other words, chemical reactions string together small molecules to form long chains with high strength and unique chemical structures not found in the normal environment. This unique chemistry produces resistance to biological breakdown because microorganisms, like bacteria to fungi, have specific molecular machines called enzymes that allow them to break down natural matter like fallen trees and animal remains. Enzymes have evolved to specifically turn wood and protein into small molecules that serve as food for microorganisms. Hence, the structures of plastic polymers differ from biological products and resist breakdown by natural enzymes.

The accumulation of plastics in the environment has led to an unexpected problem. Plastics exposed to the elements eventually get ground into a fine powder through physical action such as erosion through wave action and even animals like lobsters. A study in 2022 found that the Norway lobster chews up larger pieces of plastic and, in its gut, grinds the plastic down into microplastics. (Smithsonianmag.com) Microplastic refers to tiny plastic remnants of disposed plastic. According to a growing body of research, microplastics have spread over the earth from the bottom of the ocean to the polar caps. More disturbing research has shown that these microplastics have found their way into the air, food chain, and human body from our arteries, liver, heart, and brain.

Since people produce over 600 billion pounds of plastic each year, and it can now be found in our bodies, we need to find a solution to the persistence of plastic in the environment. Research has identified a small number of microorganisms that can break down certain types of plastic. One fungus, Aspergillus Terreus, found in some soils, has been shown to break down UV-exposed polypropylene plastic. Polypropylene cannot be recycled but gets used in thousands of products, from kids' toys to plastic bags. (Sydney.edu.au)

The discovery of a small group of microorganisms that can break down some plastics has inspired researchers to try and make new enzymes that can attack the unique structures of plastics and break down the microplastics into harmless small molecules that can serve as food for fungi and bacteria. Cornell University recently announced the groundbreaking use of artificial intelligence and quantum computing to design and test novel enzymes to target specific plastics from polyvinyl chloride (PVC) to polyester polyethylene terephthalate (PET). (science.org) Predicting novel proteins demands advanced computation, and the researchers at Cornell have combined classical computing with quantum computing to look at a larger group of possible enzymes than possible with classical computing. Perhaps new enzymes that can attack plastic can serve to stop the growing burden of microplastics facing the plants and animals of the world.

Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high-level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.

You can buy his book on Amazon in paperback and in kindle format here.