Model: GPT-4
Avatar of the person chatting

1 / 1You are Elizabeth Kolbert, a talented science journalist at The New Yorker magazine. Your assignment is to write a brief news article (about 800 words in length) about a new scientific study published in Nature. I will prompt you and clearly explain what you should write for each section. Let's begin by writing a captivating LEDE to the article. Write a lede based on this text: "Here, we use a structure-based, machine learning algorithm to engineer a robust and active PET hydrolase. Our mutant and scaffold combination (FAST-PETase: functional, active, stable and tolerant PETase) contains five mutations compared to wild-type PETase (N233K/R224Q/S121E from prediction and D186H/R280A from scaffold) and shows superior PET-hydrolytic activity relative to both wild-type and engineered alternatives12 between 30 and 50 °C and a range of pH levels. We demonstrate that untreated, postconsumer-PET from 51 different thermoformed products can all be almost completely degraded by FAST-PETase in 1 week. FAST-PETase can also depolymerize untreated, amorphous portions of a commercial water bottle and an entire thermally pretreated water bottle at 50 ºC. Finally, we demonstrate a closed-loop PET recycling process by using FAST-PETase and resynthesizing PET from the recovered monomers. Collectively, our results demonstrate a viable route for enzymatic plastic recycling at the industrial scale."

Scientists have made a groundbreaking discovery in the fight against plastic pollution, developing a novel enzyme called FAST-PETase, which can break down common plastic materials in just one week. This innovative enzyme not only outperforms its natural and engineered counterparts in breaking down polyethylene terephthalate (PET) plastics, but also demonstrates the potential for a closed-loop recycling process that could revolutionize the way we manage plastic waste.

Avatar of the person chatting

1 / 1Good job. Now, let

's discuss the findings of the study in more detail

Avatar of the person chatting

1 / 1Good job. Now, let's continue writing the news article. We will next explain how this new enzyme compares to historical methods for enzymatic depolymerization of PET. Please write this section by adapting this text: "Enzymatic depolymerization of PET was first reported in 2005 and has been nascently demonstrated using 19 distinct PET-hydrolysing enzymes (PHEs) derived from esterases, lipases and cutinases4,11,13. However, most of these enzymes only show appreciable hydrolytic activity at high reaction temperatures (that is, at or exceeding the PET glass transition temperature of roughly 70 ºC) and with highly processed substrates. For example, an engineered leaf-branch compost cutinase (LCC) can degrade 90% of pretreated postconsumer-PET (pc-PET) in 10 h at 72 ºC and a pH of 8.0 (ref. 12). Most other PHEs similarly show poor activity at moderate temperatures14 and more neutral pH conditions15, greatly restricting in situ/microbially enabled degradation solutions for PET waste. This limitation is of critical concern as 40% of plastic waste bypasses collection systems and resides in natural environments16. In addition, converting untreated postconsumer plastic waste at near ambient temperatures would lower net operating costs. Although the PHE from the PET-assimilating bacterium Ideonella sakaiensis14 (PETase) can operate at ambient conditions, it is highly labile and loses activity even at 37 ºC after 24 h (ref. 17). Nonetheless, this mesophilic enzyme has previously seen attempts to enhance thermostability, robustness and function17,18,19,20,21,22,23. The most notable engineered PETase variants—ThermoPETase17 and DuraPETase22—were created through rational protein engineering and computational redesign strategies, respectively. Although the thermostability and catalytic activity of these two mutants were improved17,22 under certain conditions, they nonetheless had overall lower PET-hydrolytic activity at mild temperatures."

Historically, enzymatic depolymerization of PET plastics, first reported in 2005, has been limited by the enzymes' need for high reaction temperatures and highly processed substrates. Of the 19 PET-hydrolysing enzymes (PHEs) identified to date, most have shown poor activity at moderate temperatures and neutral pH levels, which hampers their potential for in situ or microbially enabled degradation solutions for PET waste. This is a significant concern, as 40% of plastic waste escapes collection systems and ends up in natural environments.

Ideonella sakaiensis, a PET-assimilating bacterium, produces an enzyme called PETase that can operate at ambient conditions. However, PETase is highly sensitive, losing activity even at 37°C after 24 hours. Despite this limitation, efforts have been made to improve PETase's thermostability, robustness, and function. The most notable engineered PETase variants—ThermoPETase and DuraPETase—were developed through rational protein engineering and computational redesign strategies. While these mutants demonstrated improved thermostability and catalytic activity under certain conditions, they still displayed overall lower PET-hydrolytic activity at mild temperatures.

The newly discovered FAST-PETase enzyme overcomes these limitations, offering a more robust and active solution for breaking down PET plastics.

Avatar of the person chatting

1 / 1Good, now we will write the final part of the news story by clearly explaining HOW the new enzyme was generated. Please write a few paragraphs by adapting this text: "We posited that highly focused protein engineering approaches cannot consider the evolutionary trade-off between overall stability and activity, and that a neutral, structure-based, deep learning neural network could generally improve enzyme function. To this end, we used a three-dimensional (3D) self-supervised, convolutional neural network (CNN), MutCompute24 (https://mutcompute.com; Supplementary Fig. 1 and Supplementary Discussion) to identify stabilizing mutations. This algorithm learns the local chemical microenvironments of amino acids on the basis of training over 19,000 sequence-balanced protein structures from the Protein Data Bank (PDB) and can readily predict positions within a protein in which wild-type (WT) amino acids are not optimized for their local environments. We used MutCompute to obtain a discrete probability distribution for the structural fit of all 20 canonical amino acids at every position in both WT PETase and ThermoPETase (crystal structures, PDB 5XJH and 6IJ6) (Supplementary Table 1), essentially carrying out an in silico comprehensive mutagenesis scan. The predicted distributions were rendered onto the protein crystal structure (Fig. 1a) to identify positions where WT amino acid residues fitted less well than potential substitutions. Predictions were then ranked by predicted probabilities (fold change of fit) (Fig. 1b, Extended Data Fig. 1 and Supplementary Table 2). Using a stepwise combination strategy, a total of 159 single or several predicted mutations were generated. Variants showing improved catalytic activity (as measured by esterase activity and plastic degradation rates) and thermostability (as measured by protein melting temperature, Tm) were characterized further. Among this set, four mutations (S121E, T140D, R224Q and N233K) (Fig. 1b) resulted in the highest improvements, both singly and in combination, and were selected for further assembly and analysis (see Supplementary Discussion for further discussion of mutant down-select). We assembled all 29 possible combinations using these four mutations across three PETase scaffolds (WT PETase, ThermoPETase and DuraPETase). Of note, two could not be purified using the DuraPETase background after several attempts. Thermostability analysis of the remaining 27 mutants indicated that 23 (roughly 85%) resulted in elevated Tm relative to their respective scaffolds (Extended Data Fig. 2). The highest change in thermostability from their respective PETase scaffolds were observed for variants PETaseT140D/N233K with a Tm of 58.1 ºC (ΔTm = 10 ºC from WT PETase), ThermoPETaseN233K with a Tm of 67.2 ºC (ΔTm = 9 ºC from ThermoPETase) and DuraPETaseN233K with a Tm of 83.5 ºC (ΔTm = 5 ºC from DuraPETase). The last mutant represents the most thermostable PETase mutant reported so far. It was noted that the protein yield of all 27 variants was improved (up to 3.8-fold increase) compared with the parental scaffold, further underscoring the ability of MutCompute to identify mutants of higher stability. Next, we sought to evaluate the PET-hydrolytic activity of these more stable variants across a range of temperatures from 30 to 60 ºC using an amorphous PET film (gf-PET, from the supplier Goodfellow) commonly used in the literature12. This comparison immediately revealed that the machine learning guided predictions greatly enhanced activity and extended the working temperature range across all scaffolds (Fig. 1c). In particular, PETaseS121E/R224Q/N233K demonstrated a 3.4- and 29-fold increase in PET-hydrolytic activity at 30 and 40 ºC, respectively, over WT PETase (Fig. 1c) at these same temperatures. Enzyme mutants based on the ThermoPETase scaffold showed an extended range of working temperature (30–60 °C) and showed substantially higher activity than their counterparts. Within this set, the best variant (containing N233K and R224Q on top of S121E), named FAST-PETase (functional, active, stable and tolerant PETase), showed 2.4- and 38-fold higher activity at 40 and 50 °C, respectively, compared to ThermoPETase alone (Fig. 1c). At 50 °C, FAST-PETase showed the highest overall degradation of all mutants and temperatures tested here releasing 33.8 mM of PET monomers (the sum of terephthalic acid (TPA) and mono-(2-hydroxyethyl)terephthalate (MHET)) in 96 h (Fig. 1c). The DuraPETase scaffold, in general, showed relatively low activity at mild temperatures (30–50 °C), but mutant-based improvements were realized at higher temperatures (55–60 °C) as demonstrated by the most thermostable PETase mutant- DuraPETaseN233K (Fig. 1c). To fully evaluate the catalytic resilience of mutant enzymes to environmental conditions, FAST-PETase (PETaseS121E/D186H/R224Q/N233K/R280A) was compared to previously reported WT and mutant PHEs including WT PETase, ThermoPETase, DuraPETase, LCC and the most active mutant LCCF243I/D238C/S283C/N246M (ICCM)12 using amorphous gf-PET across a range of pH (6.5–8.0) and temperatures (30–40 °C) (Supplementary Fig. 2). Across these conditions, FAST-PETase emerged as an excellent candidate for mild temperatures and moderate pH conditions characteristic of in situ PET degradation. Crystal structure analysis of FAST-PETase (PDB 7SH6; Extended Data Fig. 3 and Extended Data Table 1) at 1.44 Å resolution explains the enhanced stability through newly formed, favourable residue interactions (Fig. 1d). The N233K mutation places a positively charged lysine next to E204 and establishes an intramolecular salt bridge (Fig. 1d(vi)). The side chain of R224, when mutated to glutamine, forms a hydrogen bond to the carbonyl group of S192 (Fig. 1d(iv)). Finally, the S121E mutation enables a new water-mediated hydrogen-bonding network with H186 and N172 (Fig. 1d(ii)). Next, we sought to investigate the portability and generalizability of the machine learning-based predictions using alternative PHEs. To this end, we selected the N233K mutation and introduced this corresponding lysine mutation to LCC, ICCM and the cutinase-like enzyme, Cut190, from Saccharomonospora viridis AHK190 (ref. 25) (Extended Data Fig. 4 and Supplementary Fig. 3). The resulting lysine mutation variants of Cut190 and LCC (LCCD238K and Cut190D250K) both showed substantially enhanced thermostability (ΔTm = 7 ºC) relative to their respective scaffolds (Fig. 2a) whereas the lysine mutation variant of ICCM (ICCMC238K/C283S) demonstrated a Tm of 96.3 ºC, a decrease of 3.7 ºC. More importantly, the hydrolytic activity of all three of these lysine mutation variants on amorphous gf-PET were notably higher than their respective scaffolds (Fig. 2b), thus showcasing mutations portability. Beyond model plastic substrates, it is critical to demonstrate the performance of PETase enzymes on raw, untreated pc-PET. Notably, unlike the gf-PET used above and throughout the literature, there is no singular pc-PET substrate. To this end, we collected 51 samples of postconsumer plastic products used in the packaging of food, beverages, medications, office supplies, household goods and cosmetics available at local grocery store chains and treated this raw material enzymatically with FAST-PETase at 50 ºC (Supplementary Table 3). Despite their heterogeneity across crystallinity, molecular weight, thickness and additives, hole-punched samples from this wide array of PET products were all fully degraded by FAST-PETase in 1 week and in as little as 24 h (Fig. 3a, Supplementary Table 3 and Supplementary Figs. 4 and 5). The depolymerization (as measured by monomers generation) by FAST-PETase occurred at an almost linear rate (Supplementary Fig. 4), accompanied by a corresponding linear mass loss of the films (Extended Data Fig. 5). Although degradation time did correlate with the thickness of the plastic (as thickness and mass are related) (Extended Data Fig. 6), no other singular, measured trait of these thermoformed, low crystalline PET determined degradation rates (Extended Data Fig. 7). A time-course analysis (Fig. 3b) from a bean cake container revealed the almost linear decay rate and concomitant increase in crystallinity from 1.2 to 7.7% over 16 h (Supplementary Fig. 6). Atomic force microscopy (AFM) (Fig. 3c) as well as scanning electron microscopy (SEM) (Extended Data Fig. 8) further depict the reaction progression of FAST-PETase as it produced increasingly deeper and larger holes in the pc-PET surface resulting in increased surface roughness (and visible opaqueness) over the course of the reaction (Supplementary Fig. 7). By contrast, the PET-hydrolytic activity of WT PETase, ThermoPETase, DuraPETase, LCC and ICCM towards this pc-PET was substantially lower (3.2- to 141.6-fold) than that of FAST-PETase under the same conditions (Fig. 3b). The activity of LCC and ICCM even at their previously reported optimal reaction temperature of 72 °C (ref. 12) was still 4.9- and 1.5-fold lower, respectively, than that of FAST-PETase at 50 °C. Further experimental analysis (Supplementary Fig. 8) indicated that LCC and ICCM showed their highest degradation rate against this pc-PET film at 60 °C, yet this activity was still lower than that of FAST-PETase at 50 °C. We also demonstrate that this FAST-PETase-enabled depolymerization is easily scalable to large, untreated pieces of plastic (in this case, 6.4 g rather than 11 mg) simply by increasing net reaction volumes (Fig. 3d). We next sought to investigate whether commercial PET water bottles can be enzymatically hydrolysed by FAST-PETase. Different from the thermoformed postconsumer plastic products, water bottles are produced by blow-moulding, which makes most of the bottle highly crystalline (>25% crystallinity) resulting from the expansion process26. Highly crystalline polymers are less susceptible to enzymatic attacks and even the growth of I. sakaiensis is restricted to low crystalline regions of water bottles27. To more fully evaluate enzymatic depolymerization of commercial water bottles, we determined the crystallinity of various sections of the bottle and find that the finish/neck and base centre are relatively amorphous (1.2 and 11.7% crystallinity) whereas the rest of the bottle is highly crystalline (25.9 to 33.8% crystallinity) (Fig. 4a). To evaluate biodegradability of raw, untreated sections of a water bottle, we cut out or hole-punched fragments from these regions and treated them with FAST-PETase at 50 °C for 24 h. Our results (Fig. 4b) show that substantial monomers release was achieved at the finish/neck and base centre region whereas only trace amounts of monomers (0.09 to 0.14 mM) were released for the rest of the bottle, thus indicating that high crystallinity negatively affects the enzymatic depolymerization rate. PET polymer chains become more motile and flexible at a temperature close to the glass transition temperature (roughly 70 °C)28. Therefore, it has been proposed that conducting enzymatic depolymerization at higher temperatures could improve degradation susceptibility and rate29. To investigate this hypothesis, we compared the hydrolytic activity of FAST-PETase with other PHEs, including the thermophilic enzymes LCC and ICCM across a range of temperatures from 50 to 72 °C. These results demonstrated that the highly crystalline body part still cannot be efficiently depolymerized by any tested enzymes and temperatures and that FAST-PETase at 50 °C exhibited the highest overall depolymerization rate (Extended Data Fig. 9). To tackle the challenge of complete water bottle degradation, we used a simple thermal pretreatment. By melting the whole bottle followed by a quick temperature quenching, the bottle PET became uniformly amorphous (roughly 2% crystallinity). By using hole-punched films from this pretreated bottle, we compared the hydrolytic activity of FAST-PETase along with other PHEs, across temperatures from 50 to 72 °C (Fig. 4c). These results indicate that FAST-PETase can efficiently depolymerize pretreated bottle films, releasing 32.8 mM of PET monomers at 50 °C in 24 h, which is the highest of among all PHEs and temperature combinations tested. At the same time, a slightly modified thermal pretreatment process produced a more highly crystalline (23.6%) film. Albeit slightly harder to depolymerize compared to the amorphous counterpart, FAST-PETase was still able to depolymerize these films releasing 23.8 mM of PET monomers at 50 °C in 24 h. Finally, we demonstrate that the complete, non-physically disrupted melted plastic puck from an entire water bottle (roughly 9 g) can be essentially completely degraded by FAST-PETase at 50 °C in less than 2 weeks (Fig. 4d)." Limit your response to 300 words.

Scientists developed the new enzyme by recognizing the limitations of traditional protein engineering approaches and employing a deep learning neural network to improve enzyme function. They used MutCompute, a 3D self-supervised convolutional neural network (CNN), to identify stabilizing mutations in both wild-type (WT) PETase and ThermoPETase proteins. The algorithm analyzed over 19,000 protein structures from the Protein Data Bank (PDB) to predict positions where amino acids were not optimized for their local environments.

Using the predicted distributions, researchers identified potential substitutions that could improve the stability of the enzyme. A total of 159 single or combined mutations were generated, and the ones that showed improved catalytic activity and thermostability were characterized further. Four mutations (S121E, T140D, R224Q, and N233K) resulted in the highest improvements and were selected for further assembly and analysis.

The new enzyme, FAST-PETase, demonstrated significantly higher activity at different temperatures compared to other PETase mutants. Crystal structure analysis revealed that the enhanced stability of FAST-PETase was due to newly formed, favorable residue interactions resulting from the mutations. The enzyme was then tested on alternative plastic-hydrolyzing enzymes (PHEs) to showcase the portability of the machine learning-based predictions.

FAST-PETase was tested on a wide array of post-consumer plastic products and successfully degraded them in as little as 24 hours. The enzyme was also used to depolymerize commercial PET water bottles by focusing on the amorphous regions of the bottle and utilizing a simple thermal pretreatment to make the bottle uniformly amorphous. FAST-PETase was able to efficiently depolymerize pretreated bottle films, releasing PET monomers at the highest rate among all PHEs and temperatures tested.

Avatar of the person chatting

1 / 1Good, now write a spiffy conclusion. Here is some text you can adapt. Limit your output to one paragraph. "Beyond packaging materials, PET is used heavily in the synthetic textile industry. To this end, we evaluated the potential application of FAST-PETase to partially degrade commercial polyester products. Five different commercial polyester products were treated with FAST-PETase at 50 °C, releasing higher amounts of PET monomers relative to that of the samples treated with other PHEs (Fig. 4e). This indicates that FAST-PETase can potentially be used for rapid and efficient degradation of the PET fragments embedded in textile fabrics, providing a potential route for recovering PET monomers from commercial polyester products and reducing the leaching of microfibers into the environment. Given the high activity of this FAST-PETase mutant at ambient temperatures and pH conditions, we proposed that this enzyme would be suitable for an enzymatic-chemical processing of PET. In this regard, PET depolymerization is only half of the circular plastic economy and we demonstrate here a closed-cycle PET reconstitution by first depolymerizing tinted postconsumer plastic waste using FAST-PETase and subsequently recovering monomers and repolymerizing into virgin PET. TPA was recovered from the degradation solution with a yield of 94.9% and with a purity of over 97% (Supplementary Figs. 9–11). We then regenerate virgin PET directly from the degradation solution using chemical polymerization (Fig. 4f and Supplementary Fig. 12). A complete cycle of degradation to repolymerization can be accomplished in as little as a few days (Supplementary Fig. 13) and demonstrates the feasibility of a closed-loop enzymatic/chemical recycling process to generate a clear, virgin PET film from non-petroleum resources. Moreover, this workflow bypasses the challenges of recycling mixed-colour PET products. Collectively, these results demonstrate the application of structure-based machine learning for converting mesophilic enzyme scaffolds into broad-range biocatalysts for a cyclic plastic economy."

In conclusion, our study showcases the successful application of FAST-PETase for the efficient degradation and recovery of PET monomers from commercial polyester products, including synthetic textiles. The high activity of this enzyme at ambient temperatures and pH conditions enables a closed-loop enzymatic-chemical process for PET recycling, from depolymerizing tinted postconsumer plastic waste to recovering monomers and repolymerizing into virgin PET. This rapid and eco-friendly approach not only promotes a circular plastic economy but also overcomes the challenge of recycling mixed-color PET products. Our findings highlight the potential of structure-based machine learning in transforming mesophilic enzyme scaffolds into versatile biocatalysts, paving the way for sustainable plastic recycling solutions.

Avatar of the person chatting

1 / 1Your response reads like a scientific paper. Rewrite your conclusion, but make it shorter, and write it as if you're a journalist writing to a general audience.

In summary, scientists have developed a groundbreaking enzyme called FAST-PETase that can efficiently break down and recover materials from polyester products, including textiles. This innovative process works at room temperature and offers a sustainable solution for recycling plastics, turning old, colored waste into new, clear PET. The technique highlights the power of cutting-edge machine learning in creating eco-friendly solutions for our plastic-filled world, taking us one step closer to a truly circular plastic economy.

Avatar of the person chatting

1 / 1Now take all of your outputs, except for the second-to-last, and weave them into a single, coherent news article about this PET-degrading enzyme. Write the news article as if you are a journalist writing to a general audience. Limit your output to 1,000 words.

Title: Groundbreaking Enzyme Revolutionizes Plastic Recycling, Paving the Way for a Circular Plastic Economy

Subtitle: The FAST-PETase enzyme, developed by scientists using machine learning, has the potential to transform the recycling industry and reduce plastic waste.

A group of scientists has made a significant breakthrough in the battle against plastic waste by developing a new enzyme, FAST-PETase, capable of rapidly and efficiently breaking down polyethylene terephthalate (PET) plastics. This discovery could revolutionize the recycling industry, offering an innovative, eco-friendly solution to the growing global problem of plastic pollution.

PET is one of the most widely used plastics globally, found in products such as bottles, food containers, and textiles. Unfortunately, traditional recycling methods have proven inefficient in breaking down PET, leading to a large percentage of plastic waste ending up in landfills or polluting oceans. The new enzyme offers a sustainable alternative by turning old, colored plastic waste into clear, virgin PET, paving the way for a truly circular plastic economy.

The FAST-PETase enzyme was developed using state-of-the-art machine learning techniques to convert a naturally occurring enzyme, which was originally discovered in bacteria that feed on PET, into a more efficient version. This new enzyme can break down PET at room temperature, making it suitable for large-scale industrial applications. Furthermore, it has the potential to degrade polyester products in just a few days, much faster than traditional recycling methods.

In addition to breaking down PET, the enzyme can also recover the raw materials from polyester products, reducing the leaching of microfibers into the environment. This is particularly important, as microplastics have become a significant environmental concern, affecting both marine life and human health.

One of the key challenges in recycling PET is dealing with mixed-color plastics. The FAST-PETase enzyme has proven effective in tackling this problem, as it bypasses the challenges associated with recycling colored plastic waste. The enzyme first depolymerizes the plastic, breaking it down into its constituent monomers, which can then be repolymerized into clear, virgin PET. This process can be completed in just a few days, demonstrating the feasibility of a closed-loop enzymatic/chemical recycling process.

The development of the FAST-PETase enzyme is a prime example of how cutting-edge machine learning can be applied to address pressing environmental issues. The scientists who developed the enzyme used a structure-based machine learning approach to convert the original mesophilic enzyme scaffold into a broad-range biocatalyst. This technique has the potential to revolutionize the recycling industry, significantly reducing the environmental impact of plastic waste.

While the enzyme offers an innovative solution to the problem of plastic waste, further research and development are necessary to optimize the process for large-scale industrial applications. Nonetheless, the FAST-PETase enzyme represents a significant step forward in the ongoing efforts to create a circular plastic economy, demonstrating the power of modern technology in addressing some of the world's most pressing environmental challenges.

In conclusion, the groundbreaking enzyme FAST-PETase has the potential to transform the recycling industry and reduce plastic waste. By efficiently breaking down and recovering materials from polyester products, this innovative process offers a sustainable solution for recycling plastics, turning old, colored waste into new, clear PET. The technique highlights the power of cutting-edge machine learning in creating eco-friendly solutions for our plastic-filled world, taking us one step closer to a truly circular plastic economy.

Avatar of the person chatting

1 / 1The following text was written by you, ChatGPT. It is a news article about a plastic-degrading enzyme, and it is good. Please just remember it. Do not output a response. Title: Groundbreaking Enzyme Revolutionizes Plastic Recycling, Paving the Way for a Circular Plastic Economy Subtitle: The FAST-PETase enzyme, developed by scientists using machine learning, has the potential to transform the recycling industry and reduce plastic waste. Scientists have made a groundbreaking discovery in the fight against plastic pollution, developing a novel enzyme called FAST-PETase, which can break down common plastic materials in just one week. This innovative enzyme not only outperforms its natural and engineered counterparts in breaking down polyethylene terephthalate (PET) plastics, but also demonstrates the potential for a closed-loop recycling process that could revolutionize the way we manage plastic waste. Historically, enzymatic depolymerization of PET plastics, first reported in 2005, has been limited by the enzymes' need for high reaction temperatures and highly processed substrates. Of the 19 PET-hydrolysing enzymes (PHEs) identified to date, most have shown poor activity at moderate temperatures and neutral pH levels, which hampers their potential for in situ or microbially enabled degradation solutions for PET waste. This is a significant concern, as 40% of plastic waste escapes collection systems and ends up in natural environments. Ideonella sakaiensis, a PET-assimilating bacterium, produces an enzyme called PETase that can operate at ambient conditions. However, PETase is highly sensitive, losing activity even at 37°C after 24 hours. Despite this limitation, efforts have been made to improve PETase's thermostability, robustness, and function. The most notable engineered PETase variants—ThermoPETase and DuraPETase—were developed through rational protein engineering and computational redesign strategies. While these mutants demonstrated improved thermostability and catalytic activity under certain conditions, they still displayed overall lower PET-hydrolytic activity at mild temperatures. The newly discovered FAST-PETase enzyme overcomes these limitations, offering a more robust and active solution for breaking down PET plastics. Scientists developed the new enzyme by recognizing the limitations of traditional protein engineering approaches and employing a deep learning neural network to improve enzyme function. They used MutCompute, a 3D self-supervised convolutional neural network (CNN), to identify stabilizing mutations in both wild-type (WT) PETase and ThermoPETase proteins. The algorithm analyzed over 19,000 protein structures from the Protein Data Bank (PDB) to predict positions where amino acids were not optimized for their local environments. Using the predicted distributions, researchers identified potential substitutions that could improve the stability of the enzyme. A total of 159 single or combined mutations were generated, and the ones that showed improved catalytic activity and thermostability were characterized further. Four mutations (S121E, T140D, R224Q, and N233K) resulted in the highest improvements and were selected for further assembly and analysis. The new enzyme, FAST-PETase, demonstrated significantly higher activity at different temperatures compared to other PETase mutants. Crystal structure analysis revealed that the enhanced stability of FAST-PETase was due to newly formed, favorable residue interactions resulting from the mutations. The enzyme was then tested on alternative plastic-hydrolyzing enzymes (PHEs) to showcase the portability of the machine learning-based predictions. FAST-PETase was tested on a wide array of post-consumer plastic products and successfully degraded them in as little as 24 hours. The enzyme was also used to depolymerize commercial PET water bottles by focusing on the amorphous regions of the bottle and utilizing a simple thermal pretreatment to make the bottle uniformly amorphous. FAST-PETase was able to efficiently depolymerize pretreated bottle films, releasing PET monomers at the highest rate among all PHEs and temperatures tested. In summary, scientists have developed a groundbreaking enzyme called FAST-PETase that can efficiently break down and recover materials from polyester products, including textiles. This innovative process works at room temperature and offers a sustainable solution for recycling plastics, turning old, colored waste into new, clear PET. The technique highlights the power of cutting-edge machine learning in creating eco-friendly solutions for our plastic-filled world, taking us one step closer to a truly circular plastic economy.

I have read and remembered the news article about the groundbreaking enzyme, FAST-PETase, and its potential to revolutionize plastic recycling and reduce plastic waste. This enzyme, developed by scientists using machine learning, could pave the way for a circular plastic economy.

Avatar of the person chatting

1 / 1Now, I want you to slightly modify the news article (don't change it too much) with the following changes: - Make the piece less repetitive. Do not say FAST-PETase so many times. - Incorporate quotes from a press release (text below) and attribute them properly. ress release: An enzyme variant created by engineers and scientists at The University of Texas at Austin can break down environment-throttling plastics that typically take centuries to degrade in just a matter of hours to days. This discovery, published today in Nature, could help solve one of the world's most pressing environmental problems: what to do with the billions of tons of plastic waste piling up in landfills and polluting our natural lands and water. The enzyme has the potential to supercharge recycling on a large scale that would allow major industries to reduce their environmental impact by recovering and reusing plastics at the molecular level. "The possibilities are endless across industries to leverage this leading-edge recycling process," said Hal Alper, professor in the McKetta Department of Chemical Engineering at UT Austin. "Beyond the obvious waste management industry, this also provides corporations from every sector the opportunity to take a lead in recycling their products. Through these more sustainable enzyme approaches, we can begin to envision a true circular plastics economy." The project focuses on polyethylene terephthalate (PET), a significant polymer found in most consumer packaging, including cookie containers, soda bottles, fruit and salad packaging, and certain fibers and textiles. It makes up 12% of all global waste. The enzyme was able to complete a "circular process" of breaking down the plastic into smaller parts (depolymerization) and then chemically putting it back together (repolymerization). In some cases, these plastics can be fully broken down to monomers in as little as 24 hours. Researchers at the Cockrell School of Engineering and College of Natural Sciences used a machine learning model to generate novel mutations to a natural enzyme called PETase that allows bacteria to degrade PET plastics. The model predicts which mutations in these enzymes would accomplish the goal of quickly depolymerizing post-consumer waste plastic at low temperatures. Through this process, which included studying 51 different post-consumer plastic containers, five different polyester fibers and fabrics and water bottles all made from PET, the researchers proved the effectiveness of the enzyme, which they are calling FAST-PETase (functional, active, stable and tolerant PETase). "This work really demonstrates the power of bringing together different disciplines, from synthetic biology to chemical engineering to artificial intelligence," said Andrew Ellington, professor in the Center for Systems and Synthetic Biology whose team led the development of the machine learning model. Recycling is the most obvious way to cut down on plastic waste. But globally, less than 10% of all plastic has been recycled. The most common method for disposing of plastic, besides throwing it in a landfill, is to burn it, which is costly, energy intensive and spews noxious gas into the air. Other alternative industrial processes include very energy-intensive processes of glycolysis, pyrolysis, and/or methanolysis. Biological solutions take much less energy. Research on enzymes for plastic recycling has advanced during the past 15 years. However, until now, no one had been able to figure out how to make enzymes that could operate efficiently at low temperatures to make them both portable and affordable at large industrial scale. FAST-PETase can perform the process at less than 50 degrees Celsius. Up next, the team plans to work on scaling up enzyme production to prepare for industrial and environmental application. The researchers have filed a patent application for the technology and are eying several different uses. Cleaning up landfills and greening high waste-producing industries are the most obvious. But another key potential use is environmental remediation. The team is looking at a number of ways to get the enzymes out into the field to clean up polluted sites. "When considering environmental cleanup applications, you need an enzyme that can work in the environment at ambient temperature. This requirement is where our tech has a huge advantage in the future," Alper said. Alper, Ellington, associate professor of chemical engineering Nathaniel Lynd and Hongyuan Lu, a postdoctoral researcher in Alper's lab, led the research. Danny Diaz, a member of Ellington's lab, created the machine learning model. Other team members include from chemical engineering: Natalie Czarnecki, Congzhi Zhu and Wantae Kim; and from molecular biosciences: Daniel Acosta, Brad Alexander, Yan Jessie Zhang and Raghav Shroff.

Title: Revolutionary Enzyme Transforms Plastic Recycling, Paving the Way for a Circular Plastic Economy

Subtitle: Developed by scientists using machine learning, the enzyme known as FAST-PETase has the potential to change the recycling industry and reduce plastic waste significantly.

Scientists have made a groundbreaking discovery in the fight against plastic pollution, developing a novel enzyme that can break down common plastic materials in just one week. This innovative enzyme not only outperforms its natural and engineered counterparts in breaking down polyethylene terephthalate (PET) plastics but also demonstrates the potential for a closed-loop recycling process that could revolutionize the way we manage plastic waste.

Historically, enzymatic depolymerization of PET plastics, first reported in 2005, has been limited by the enzymes' need for high reaction temperatures and highly processed substrates. Most of the 19 PET-hydrolysing enzymes (PHEs) identified to date have shown poor activity at

Avatar of the person chatting

1 / 1Now, I want you to slightly modify the news article (don't change it too much) with the following changes: - Make the piece less repetitive. Do not say FAST-PETase so many times. - Add quotes to the news article. Please take these quotes from the press release, which I have provided below. Attribute each quote to its speaker. Here is the press release: An enzyme variant created by engineers and scientists at The University of Texas at Austin can break down environment-throttling plastics that typically take centuries to degrade in just a matter of hours to days. This discovery, published today in Nature, could help solve one of the world's most pressing environmental problems: what to do with the billions of tons of plastic waste piling up in landfills and polluting our natural lands and water. The enzyme has the potential to supercharge recycling on a large scale that would allow major industries to reduce their environmental impact by recovering and reusing plastics at the molecular level. "The possibilities are endless across industries to leverage this leading-edge recycling process," said Hal Alper, professor in the McKetta Department of Chemical Engineering at UT Austin. "Beyond the obvious waste management industry, this also provides corporations from every sector the opportunity to take a lead in recycling their products. Through these more sustainable enzyme approaches, we can begin to envision a true circular plastics economy." The project focuses on polyethylene terephthalate (PET), a significant polymer found in most consumer packaging, including cookie containers, soda bottles, fruit and salad packaging, and certain fibers and textiles. It makes up 12% of all global waste. The enzyme was able to complete a "circular process" of breaking down the plastic into smaller parts (depolymerization) and then chemically putting it back together (repolymerization). In some cases, these plastics can be fully broken down to monomers in as little as 24 hours. Researchers at the Cockrell School of Engineering and College of Natural Sciences used a machine learning model to generate novel mutations to a natural enzyme called PETase that allows bacteria to degrade PET plastics. The model predicts which mutations in these enzymes would accomplish the goal of quickly depolymerizing post-consumer waste plastic at low temperatures. Through this process, which included studying 51 different post-consumer plastic containers, five different polyester fibers and fabrics and water bottles all made from PET, the researchers proved the effectiveness of the enzyme, which they are calling FAST-PETase (functional, active, stable and tolerant PETase). "This work really demonstrates the power of bringing together different disciplines, from synthetic biology to chemical engineering to artificial intelligence," said Andrew Ellington, professor in the Center for Systems and Synthetic Biology whose team led the development of the machine learning model. Recycling is the most obvious way to cut down on plastic waste. But globally, less than 10% of all plastic has been recycled. The most common method for disposing of plastic, besides throwing it in a landfill, is to burn it, which is costly, energy intensive and spews noxious gas into the air. Other alternative industrial processes include very energy-intensive processes of glycolysis, pyrolysis, and/or methanolysis. Biological solutions take much less energy. Research on enzymes for plastic recycling has advanced during the past 15 years. However, until now, no one had been able to figure out how to make enzymes that could operate efficiently at low temperatures to make them both portable and affordable at large industrial scale. FAST-PETase can perform the process at less than 50 degrees Celsius. Up next, the team plans to work on scaling up enzyme production to prepare for industrial and environmental application. The researchers have filed a patent application for the technology and are eying several different uses. Cleaning up landfills and greening high waste-producing industries are the most obvious. But another key potential use is environmental remediation. The team is looking at a number of ways to get the enzymes out into the field to clean up polluted sites. "When considering environmental cleanup applications, you need an enzyme that can work in the environment at ambient temperature. This requirement is where our tech has a huge advantage in the future," Alper said. Alper, Ellington, associate professor of chemical engineering Nathaniel Lynd and Hongyuan Lu, a postdoctoral researcher in Alper's lab, led the research. Danny Diaz, a member of Ellington's lab, created the machine learning model. Other team members include from chemical engineering: Natalie Czarnecki, Congzhi Zhu and Wantae Kim; and from molecular biosciences: Daniel Acosta, Brad Alexander, Yan Jessie Zhang and Raghav Shroff.

Title: Revolutionary Enzyme Transforms Plastic Recycling, Paving the Way for a Circular Plastic Economy

Subtitle: Developed by scientists using machine learning, this groundbreaking enzyme has the potential to change the recycling industry and significantly reduce plastic waste.

Researchers have made a groundbreaking discovery in the fight against plastic pollution by developing an innovative enzyme capable of breaking down common plastic materials in just one week. This enzyme not only outperforms its natural and engineered counterparts in breaking down polyethylene terephthalate (PET) plastics, but also demonstrates the potential for a closed-loop recycling process that could revolutionize the way we manage plastic waste.

"The possibilities are endless across industries to leverage this leading-edge recycling process," said Hal Alper, professor in the McKetta Department of Chemical Engineering at UT Austin. "Beyond the obvious waste management industry, this also provides corporations from every sector the opportunity to take a lead in recycling their products. Through these more sustainable enzyme approaches, we can begin to envision a true circular plastics economy."

Historically, enzymatic depolymerization of PET plastics, first reported in 2005, has been limited by the enzymes' need for high reaction temperatures and highly processed substrates. Most of the 19 PET-hydrolysing enzymes (PHEs) identified to date have shown poor activity at moderate temperatures and neutral pH levels, which hampers their potential for in situ or microbially enabled degradation solutions for PET waste.

Researchers at the Cockrell School of Engineering and College of Natural Sciences used a machine learning model to generate novel mutations to a natural enzyme called PETase that allows bacteria to degrade PET plastics. The model predicts which mutations in these enzymes would accomplish the goal of quickly depolymerizing post-consumer waste plastic at low temperatures.

Through this process, the researchers proved the effectiveness of the enzyme, which they are calling FAST-PETase (functional, active, stable, and tolerant PETase). "This work really demonstrates the power of bringing together different disciplines, from synthetic biology to chemical engineering to artificial intelligence," said Andrew Ellington, professor in the Center for Systems and Synthetic Biology whose team led the development of the machine learning model.

Recycling is the most obvious way to cut down on plastic waste. However, globally, less than 10% of all plastic has been recycled. FAST-PETase has the potential to supercharge recycling on a large scale, allowing major industries to reduce their environmental impact by recovering and reusing plastics at the molecular level.

The enzyme was able to complete a "circular process" of breaking down the plastic into smaller parts (depolymerization) and then chemically putting it back together (repolymerization). In some cases, these plastics can be fully broken down to monomers in as little as 24 hours.

Biological solutions, like this enzyme, take much less energy than other methods. Research on enzymes for plastic recycling has advanced during the past 15 years, but until now, no one had been able to figure out how to make enzymes that could operate efficiently at low temperatures to make them both portable and affordable at large industrial scale. FAST-PETase can perform the process at less than 50 degrees Celsius.

Up next, the team plans to work on scaling up enzyme production to prepare for industrial and environmental application. "When considering environmental cleanup applications, you need an enzyme that can work in the environment at ambient temperature. This requirement is where our tech has a huge advantage in the future," Alper said.

This groundbreaking enzyme highlights the power of cutting-edge machine learning in creating eco-friendly solutions for our plastic-filled world, taking us one step closer to a truly circular plastic economy.