Awards

1.1 Competition Deliverables

We confirm that we have or will fully complete the required deliverables.

Wiki:

We have made a wiki to introduce our idea, explain our project and make it accessible to a larger audience.

Presentation Video:

We produced a presentation video to give an explicit explanation of the purpose, principle, content and the significance of our project.

Judging Form:

We have filled in the judging form.

Judging Session:

We will attend the judging session in person with interesting videos, delicate brochure and special gifts. Look forward to the Grand Jamboree!

1.2 Project Attributions

We have filled in the Attributions section to give appreciation to every member, professor, team, organization and enterprise that supported and helped our project.

1.3 Project Description

In the Description section, we detailedly stated the background, current situation and problems, motivation, solution and importance of our project, allowing you to fully comprehend HEATMAP.

1.4 Contribution

We demonstrated every contribution to the iGEM community in the Contribution section.

In the Software & AI Contribution section, we developed the HEATMAP-AI model, which can accurately predict the optimal operating temperature of enzymes based on their sequences, thereby enhancing the understanding of enzyme operating conditions.

In the Model Contribution section, we built an etcGEM model of $Saccharopolysporaspinosa$ based on the HEATMAP-AI model, digitizing its metabolic network and providing data support for future scientific research on this species.

In the Data Contribution section, we compiled and organized enzyme sequence data along with their corresponding optimal temperature data from public databases and scientific literature, as well as the predicted optimal temperature data from the HEATMAP-AI model.

2.1 Engineering Success

Our engineering task is to construct both ecGEM and etcGEM models of $Saccharopolysporaspinosa$, following the Design → Build → Test → Learn engineering design cycle, which we showed detaily in the Engineering section.

In the construction of ecGEM model within the $Saccharopolysporaspinosa$, we began with the Learn phase to understand the principles of building an ecGEM using the GECKO framework. In the Design phase, we designed the corresponding adapters for $Saccharopolysporaspinosa$ to obtain relevant protein and enzyme function information and integrated it with the GEM model. During the Build phase, we obtained enzyme $k_{cat}$ values through fuzzy matching or DLKcat predictions. In the Test phase, we fine-tuned the ecGEM model and evaluated its ability to simulate the organism’s physiological states.

Building upon the ecGEM model of $Saccharopolysporaspinosa$, we entered a second DBTL cycle. In constructing the etcGEM model of $Saccharopolysporaspinosa$, we utilized the Learn phase to apply the deep learning model. In the Design phase, using Cobrapy in Python, we modified the key matrices of the ecGEM model by incorporating temperature data. In the Build phase, we filled the model with parameters such as $T_{opt}$, $T_m$, $k_{cat}$, $fN\left(T\right)$, and $k_{cat}\left(T\right)$, enabling the calculation of enzyme concentrations at any given temperature via specific functions. During the Test phase, we simulated the growth rate of $Saccharopolysporaspinosa$ at different temperatures.

By applying the DBTL cycle of synthetic biology to the overall metabolic network model of $Saccharopolysporaspinosa$, we successfully completed the digital modeling of its metabolic network.

2.2 Human Practice

You can read about the extensive human practice work we have done in the Integrated Human Practice section.

To begin with, we communicated with the United Union about the environmental problems worldwide. At the same time, we consulted with both internal and external professors about the topic and solution of our project, during which we received quite a few precious suggestions.

Meanwhile, we also went to different industries related to our project to do field research and understand the situation in practical production. In addition, we cooperated with over 15 iGEM teams to optimize our project. Both ways indeed get our team inspired, thus we continually improve our project and present the most perfect one.

3.1 Excellence in Synthetic Biology

Model:

In our project, we have successfully and innovatively constructed multiple models. It is worth mentioning that not only have we successfully constructed the models, but their performance is also exceptionally outstanding, which can provide assistance to future synthetic biology researchers, as you can see in the Model section.

1. HEATMAP-AI:
Aiming to predict the optimal temperature of enzymes with input data of sequences, we have successfully built HEATMAP-AI, which is based on Hyena-DNA frame. In the test part, we utilized the cross-validation method. The R of both are up to 0.95 and R2 are up to 0.89, which makes it the most precise model in predicting optimal temperature. Meanwhile, the result also proves it has excellent robustness, which indicates that our model has very strong universality. Visit AI section to get more model information of HEATMAP-AI.

2. HEATMAP-ecGEM:
As for $Saccharopolysporaspinosa$, there was no avaible GEM model before HEATMAP, let alone ecGEM model. In our project, we have successfully built and tested ecGEM for $Saccharopolysporaspinosa$.Visit Model section to get more model information of HEATMAP-ecGEM.

3. HEATMAP-etcGEM:
As the improved model of ecGEM, etcGEM is able to take the influence of temperature in to consideration. Previously, it is not put into use widely since it’s difficult to collect the thermodynamic data of all enzymes in an organism. However, with our high accuracy model HEATMAP-AI, etcGEM can easily be built based on a standard ecGEM model. We successfully tested the method in the ecGEM of $Actinoplanessp.SE50/110.$ Visit Model section to get more model information of HEATMAP-etcGEM.

3.2 Specialization

Integrated Human Practice:

In the section of Integrated Human Practice, our tremendous work is all presented.

In the communication with the United Union, we understood there are still some serious environmental problems exist worldwide.

In order to learn about the practical situation of spinosad, we get in touch with the producing industry and learn from them, through which we are inspired that the improvement of purity and unit yield of spinosad is a key solution to the high cost of producing spinosad from $Saccharopolysporaspinosa$.

At the same time, we consulted with professors, enterprises in different fields for advice and read documents to look for available solutions. Through a long term of research, consultation, and communication, we finally concluded our work: By collecting and analyzing the relevant data of $Saccharopolysporaspinosa$, we will develop a deep learning model to predict the optimal temperature of each enzyme in the process of spinosad synthesis, and compared it with the actual industrial fermentation temperature to find the enzyme with a large difference between the optimal temperature and the actual temperature. It is the fact that the activity of these enzymes is not fully realized during industrial fermentation that results in a decrease in yield. In order to simplify optimization, we added enzyme and temperature constraints to the existing GEM model and constructed the etcGEM model to identify the key enzymes that were both limited by temperature and affected by yield by analyzing the rate-limiting enzymes in the metabolic pathway. For these key enzymes, we will combine the prediction results of the deep learning model to propose an optimization strategy and conduct directed evolution experiments to make the optimal temperature closer to the actual fermentation temperature, so as to improve their catalytic efficiency.

Meanwhile, we consulted with experts about some ethical qustions to consummate our project. We also cooperated with over 15 iGEM teams to optimize our work. In the process of continuously optimize the project, we finally presented the perfect work: HEATMAP.

Education:

We have done comprehensive work in our Education section to popularize and broaden people's cognition about synthetic biology. We systematically classified our education work into 6 parts by age groups, respectively children, teenagers, peers, adults and the public.

For young children, we drew a picture book to simply imply knowledge of synthetic biology.

As for teenagers, we owned a stall on our school day and attracted more than 10000 people to look into synthetic biology with tamp books, keychains, memory cards, and various cartoon characters designed by our group to promote the work in a clear and engaging way. Meanwhile, we also hosted a visit for students from Shixi Middle School. Besides, in June, team members went back to their hometown to be a volunteer in student enrollment, introducing the major of biology to freshmen.

With peers, we made brochures and had friendly exchanges with iGEM teams from across the country at CCiC, and made both online and ofline meeting with iGEM teams at home and abroad.

As for the public, we actively set up our own WeChat public account, where we regularly publish articles on topics like actinomycetes and Streptomyces. In addition, we made 2 promotion videos to introduce synthetic biology.

Apart from the works mentioned above, since the beginning of our project, we have been searching for collaborations for realization of HEATMAP. By now, we are funded by 8 organizations and enterprises, and reached over 10 collaborations.