Machine Learning-Based Enzyme Engineering of PETase for Improved Efficiency in Degrading Non-Biodegradable Plastic

Globally, nearly a million plastic bottles are produced every minute (1). These non-biodegradable plastic products are composed of Polyethylene terephthalate (PET). In 2016, researchers discovered PETase, an enzyme from the bacteria Ideonella sakaiensis which breaks down PET and nonbiodegradable plastic. However, PETase has low efficiency at high temperatures. In this project, we optimized the rate of PET degradation by PETase by designing new mutant enzymes which could break down PET much faster than PETase, which is currently the gold standard. We used machine learning (ML) guided directed evolution to modify the PETase enzyme to have a higher optimal temperature (Topt), which would allow the enzyme to degrade PET more efficiently. First, we trained three machine learning models to predict Topt with high performance, including Logistic Regression, Linear Regression and Random Forest. We then used Random Forest to perform ML-guided directed evolution. Our algorithm generated hundreds of mutants of PETase and screened them using Random Forest to select mutants with the highest Topt, and then used the top mutants as the enzyme being mutated. After 1000 iterations, we produced a new mutant of PETase with Topt of 71.38℃. We also produced a new mutant enzyme after 29 iterations with Topt of 61.3℃. To ensure these mutant enzymes would remain stable, we predicted their melting temperatures using an external predictor and found the 29-iteration mutant had improved thermostability over PETase. Our research is significant because using our approach and algorithm, scientists can optimize additional enzymes for improved efficiency.

Comparing Overhead versus Drip Irrigation for Production of Three Cultivars of Romaine Lettuce on Biodegradable Plastic Mulch

Growers seeking alternatives to traditional polyethylene plastic mulch may use biodegradable plastic mulches (BDMs). However, plasticulture systems typically also use plastic drip tape underneath the mulch, which must be removed from the field and disposed of at the end of the season, making tilling the BDM into the soil more difficult and expensive. A potential solution to this dilemma may be to use other irrigation methods, such as overhead sprinklers, that could be more easily removed from the field and reused from year to year. At Knoxville, TN, in 2019 and 2020, we grew three cultivars of romaine lettuce (Lactuca sativa) on BDM with two irrigation systems (overhead sprinklers above the mulch and drip irrigation tape under the mulch) to compare water use, disease, and yield in these two irrigation systems. Water use was higher in overhead vs. drip irrigation in both years; however, the difference in water use was much smaller in 2019 due to higher rainfall amounts during the time period the lettuce was growing in the field (March to May). Disease incidence and severity were very low both years for both irrigation systems. There were no differences in marketable yield (number of heads) between irrigation treatment in 2019. In 2020, marketable yield by number was greater in the drip vs. overhead irrigation treatment. Unmarketable yield in 2019 was due to heads that were too small; in 2020, unmarketability was predominantly due to tipburn in overhead irrigated ‘Jericho’. Overall, marketable lettuce yield did not differ between irrigation treatments in 2019 and was similar for ‘Parris Island Cos’ in 2020. Although quantitative weed counts were not made, observations of weed pressure between rows showed that weed pressure was higher in overhead irrigated compared with drip irrigated subplots. This highlights the need to have a between-row weed management program in place. The results of this study suggest that with attention to cultivar and weed management, overhead irrigation could be a viable alternative to drip irrigation for lettuce production on BDM, especially for early spring lettuce when rainfall is historically more plentiful.

Nitrogen fixing bacteria facilitate microbial biodegradation of a bio-based and biodegradable plastic in soils under ambient and future climatic conditions

We discovered a biological mechanism supporting microbial degradation of bio-based poly (butylene succinate-co-adipate) (PBSA) plastic in soils under ambient and future climates. Here, we show that nitrogen-fixing bacteria facilitate the...

The Succession of Bacterial Community Attached on Biodegradable Plastic Mulches During the Degradation in Soil

Despite the increasing application of biodegradable plastic mulches (BDMs) in agriculture, the colonization and succession of the attached microbial community on BDMs during their degradation processes remain poorly characterized. Here, we buried four types of commonly used BDMs, including pure polylactic acid (PLA), pure polybutylene adipate terephthalate (PBAT), and two mixtures of PLA and PBAT (85:15 and 15:85 w/w), and one classic polyethylene (PE) mulch in soil for 5 months. Both plastic components and incubation time significantly shaped the β-diversities of microbiota on the plastic mulches (p < 0.001). Meanwhile, the microbial compositions and community structures on BDMs were significantly different from PE mulch, and when excluding PE mulch, the microbiota varied more with time than by the composition of the four BDMs. The orders Burkholderiales and Pseudonocardiales were dominant on most BDMs across different time points. The genus Ramlibacter was revealed as a common biomarker for both PLA and PBAT by random-forest model, and all biomarkers for the BDMs belonged to the dominant order Burkholderiales. In addition, degradation-related and pathogen-related functional taxa were enriched in all mulches among all 40 functional groups, while surprisingly, potential pathogens were detected at higher levels on BDMs than PE. For community assembly on all mulches, the drift and dispersal processes played more important roles than selection, and in particular, the contribution of stochastic drift increased during the degradation process of BDMs while selection decreased, while the opposite trend was observed with PE mulch. Overall, our results demonstrated some degradation species and pathogens were specifically enriched on BDMs, though stochastic processes also had important impacts on the community assembly. It suggested that, similar to conventional plastic mulch, the increased usage of BDMs could lead to potential hazards to crops and human health.

Biodegradable plastic modification from durian seed starch and shrimp chitosan with the addition of plasticiziers glycerol and polyglycerol using microwaves

Plastic waste takes up to 450 years to decompose. These problems can be overcome by creating other alternatives, one of which is by using biodegradable plastic. Biodegradable plastics are plastics made from natural polymers that are easily degraded by microorganisms. This study aims to examine the effect of the amount of plasticizer on the length of the degradation process and the effect of using microwaves on the length of time for molding biodegradable plastic. This biodegradable plastic is made by combining durian seed starch, shrimp chitosan and plasticizers in the form of glycerol and polyglycerol with volume variations of 1 mL, 2 mL, 3 mL, 4 mL, and 5 mL. This polymerization was carried out using a microwave with a power of 100 watts for 60 minutes. The resulting biodegradable plastics were characterized using the FTIR test, the Mechanical Properties test, the Absorbency test, and the Biodegradation test to determine the quality of the biodegradable plastic. The results of this study indicate the greatest tensile strength value is 1.9768 MPa, the largest elongation value is 21.2772%, the smallest water absorption is 45.40% for 5 minutes, and the largest degraded mass is 0.908 grams for 7 days. Based on this research, it can be concluded that the use of polyglycerol can accelerate the plastic degradation process. In addition, the use of microwaves can speed up the molding time of biodegradable plastics.