Week 1 HW: Principles and Practices + Pre-Lecture 2 Questions

1. First, describe a biological engineering application or tool you want to develop and why. This could be inspired by an idea for your HTGAA class project and/or something for which you are already doing in your research, or something you are just curious about.

Answer: I am curious how native tissue in the body regulate oxidation, since the lipids within native tissue tend to be much less oxidized than that of foods. So I want to harness the mechanism that the body uses to eliminate reactive oxagen species (ROS) and develop bio-antioxidants. The reason behind developing this tool is to unlock a more robust method of flavor preservation using metabolic pathways found in nature rather than relying on chemicals/ingredients for the mechanism of action. This solution could also be more compatible with our bodies, and, designing microbe based food technology to have specific functions within both food systems and in our bodies, it could be a step towards direclty engineering our gut microbiom as we would want (grander goal).

2. Next, describe one or more governance/policy goals related to ensuring that this application or tool contributes to an “ethical” future, like ensuring non-malfeasance (preventing harm). Break big goals down into two or more specific sub-goals. Below is one example framework (developed in the context of synthetic genomics) you can choose to use or adapt, or you can develop your own. The example was developed to consider policy goals of ensuring safety and security, alongside other goals, like promoting constructive uses, but you could propose other goals for example, those relating to equity or autonomy.

Answer: The governance with longterm consumptions of engineered technologies, especially those that directly interact within our bodies, is critical towards an “ethical” future. Some aspects that this goal should be able to achieve is that the consumer understands the risks they are taking by consuming such technologies. Although this may limit adoption by larger companies, small companies may take on the challenge to educate the consumer and persuade them to try such technologies; regardless, the technology’s risks should be clearly labeled. The risks with chronically consuming microbes may be that it could more significantly change our gut microbiome in ways we have yet to understand versus any other stand alone chemical/ingredient, and, thereby, more significantly impact how our body operates. Once we figure out how we can engineer microbes to control how our body reacts to it, another governance needs to be that the consumer understands and consents to having that technology interacts with their body, and that they don’t intentially put the consumer in harms way.

3. Next, describe at least three different potential governance “actions” by considering the four aspects below (Purpose, Design, Assumptions, Risks of Failure & “Success”). Try to outline a mix of actions (e.g. a new requirement/rule, incentive, or technical strategy) pursued by different “actors” (e.g. academic researchers, companies, federal regulators, law enforcement, etc). Draw upon your existing knowledge and a little additional digging, and feel free to use analogies to other domains (e.g. 3D printing, drones, financial systems, etc.).

–

1. Purpose: What is done now and what changes are you proposing?
2. Design: What is needed to make it “work”? (including the actor(s) involved - who must opt-in, fund, approve, or implement, etc)
3. Assumptions: What could you have wrong (incorrect assumptions, uncertainties)?
4. Risks of Failure & “Success”: How might this fail, including any unintended consequences of the “success” of your proposed actions?

Answer:

FDA: regulatory already has ingredients labeled as Generally Recognized as Safe (GRAS), but, now as engineered microbes with human oversight arises, a new regulatory label should be mandated as Generally Recognized as Good (GRAG) to act on top of GRAS. Although this is still very general, GRAG status would require detailed guidelines behind the targeted mechanism being functional and does not harm the consumer, and careful observations of the off-target affects be documented. If any off-target affects begin to harm the consumer, GRAS status would be lost. This is to limit the risk of failure & “success” by limiting unintended consequences and filter out intentional consequences.

Technology in product use: the company that decides to use this needs to be careful of how the microbe can foster and evolve a microbe community in their product. The product still needs to be safe to eat, so harmful to humans bacteria can not grow inside the product. Yet, this technology would need to survive in the product in order to be functional is what is assumed. Having companies continue doing rigorious log reduction challenges with pathogens while developing products that are able to selectively host the engineered microbes is an important step in food manufacturing that needs to continue to happen. It should also be noted about the dangers of developing microbes that resistant to the mechanisms that would otherwise kill harmful bacteria, where, through homologous gene transfer, the harmful bacteria may also become resistant to those mechanisms. For this case, microbes can not be genetically encoded to resist these mechanisms. Some solutions to this could be to physically entrap the microbes in a microenvironment, dissolved in a different phase, etc. If this limits innovation by being too difficult to solve, then preservatives should be removed and a realistic shelf life and refrigeration guidelines for the product be established.

Consumer: if an ingredient/chemical exists that is GRAS and more functional then the engineered microbe, then careful consideration should be given when choosing to include that microbe rather than the functional ingredient/chemical. Is the microbe going to be a healthier alternative for the consumer, if not, then the ingredient/chemical should be used. Even if the microbe is more functional, it needs to be healthier than the current alternative.

4. Next, score (from 1-3 with, 1 as the best, or n/a) each of your governance actions against your rubric of policy goals. The following is one framework but feel free to make your own:

5. Last, drawing upon this scoring, describe which governance option, or combination of options, you would prioritize, and why. Outline any trade-offs you considered as well as assumptions and uncertainties. For this, you can choose one or more relevant audiences for your recommendation, which could range from the very local (e.g. to MIT leadership or Cambridge Mayoral Office) to the national (e.g. to President Biden or the head of a Federal Agency) to the international (e.g. to the United Nations Office of the Secretary-General, or the leadership of a multinational firm or industry consortia). These could also be one of the “actor” groups in your matrix.

Answer: I would prioritize enforcing that the product passes the micro challenge of pathogens. Cosnumers need to trust the product, if within expiration date, won’t make them sick, even if microbes are living in the product. If preservatives are left out of the product as the most straight-forward implementation of the technology with the guidelines, then the microbe environment in the product needs to be carefully controlled and understood between manufacturing to consumption. New tests need to be developed to understand the evolution of such environments so that probabilities of harmful communities arising be reported, and this critical to safety attribute be tested for throughout processing and manufacturing. This is adding expenses, but the tradeoff would be a healthier alternative for the consumer and a more functional alternative for the company. The assumption is that there is a market for this, and that companies are willing to invest in such testing for the technologies, and that researchers at other companies and labs are incentivized to make such technologies because they can assume that the companies would want to buy such technologies. This would be a national FDA level audience that would need to enforce this governance, and it should be addressed before there is a significant demand for such technologies in the market.

Reflecting on what you learned and did in class this week, outline any ethical concerns that arose, especially any that were new to you. Then propose any governance actions you think might be appropriate to address those issues. This should be included on your class page for this week.

Reflection: Trust that humanity will generally use technologies for good is an idea I have considered in the past, but, with the context of the world today, it has made me reflect on it differently. At the beginning, it seems like visionaries and optimistist want to tackle innovating with these double-edge sword technologies. For instance, with the internet, it started off with a seemingly free for all, and then people kind of caught on to the consequences of chronic use of internet and social media, but became dependent on it regardless. Now that it is such a fundamental fabric of society, AI and powerful players can leverage the data tracking from the internet for however they wish, and its hard to tell if it is for good or bad. Still, it would have been hard to have anticipated this, but it became so obvious once the rosy glasses dissapeared to some, while other fall even deeper into its consequences that are intentionally put into the world. Regardless, I still do believe we will end up using the internet for good once we overcome the consequences we are living through currently and put stricter governance in the future. Learning from this, I think it is important to provide strict governance throughout development so that we don’t get a boom of invention and then not be able to track how it is used. Indeed, for something as slow as engineering biology, this may not seem attractive, but, for the future of humanity, it is likely to be worthwhile. Especially since it is much more detrimental when a lack of internal bioligical defenses from bioterriosism exists rather than a lack of physical and virtual defenses from their respective defenses, since its not an attack that we can relatively quickly act on at this point.

Pre-Lecture Week 2 HW:

Homework Questions from Professor Jacobson:

1. Nature’s machinery for copying DNA is called polymerase. What is the error rate of polymerase? How does this compare to the length of the human genome. How does biology deal with that discrepancy?

Answer: 1:10⁶, the human genome is orders of magnitude larger, and biology deals with this with the MutS Repair System.

2. How many different ways are there to code (DNA nucleotide code) for an average human protein? In practice what are some of the reasons that all of these different codes don’t work to code for the protein of interest?

Answer:

Using ChatGPT (prompt was question), 500 for average amino acids length, 20 amino acids, and 61 sensing codons, the genetic code’s average degeneracy d̄ = 61/20 ≈ 3.05, the number of distinct DNA sequences that can encode an average human protein is:

Ways ≈ (61/20)⁵⁰⁰ ≈ 1.4 × 10²⁴²

Homework Questions from Dr. LeProust:

1. What’s the most commonly used method for oligo synthesis currently?

Answer: Electrochemical-based microarray by CombiMatrix

2. Why is it difficult to make oligos longer than 200nt via direct synthesis?

Answer: Mutation error rate

3. Why can’t you make a 2000bp gene via direct oligo synthesis?

Answer: Error rate

Homework Question from George Church:

1. (Using Google & Prof. Church’s slide #4) What are the 10 essential amino acids in all animals and how does this affect your view of the “Lysine Contingency”?

Answer: histidine, cysteine, methionine, asparagine, lysine, arginine, tyrosine, threonine, serine, aspartate go through PTMs, although google says these are the 10 essential amino acids histidine, isoleucine, leucine, lysine, methionine, phenylalanine, threonine, tryptophan, valine, arginine. Lysine seems like it is definitely an essential amino acid that must come from our diet, so were animals ever able to make lysine in their bodies? Was there a gene to even knock out in jurassic park? I think there wasn’t is my conclusion.

Week 2 HW: DNA Read Write and Edit

Question 1

Question 3 I chose fruit fly because of their ommitidia. 3.4) I would first amplify with PCR, and then purify with gel extraction. Make sure I have a sizeable concentration of DNA, and then I would try to use a cell free system to produce my protein. I would need to choose the right buffer that has the RNAases and ribosomes/tRNAs I need for transcription and translation, respectively.

Question 4

Question 5 Read I) I want to read the gene related to oxidation reactions in human cells so that I can build effective antioxidant therapies. This could be applied from preserving the taste in foods to fighting ROS deregulation. Ii) 1. My method is third generation, as I would likely need to sequence many long mammalian DNA in parallel. 2. I would obtain mammalian cells, extract DNA, cut around the supposed regions of interest that control oxidation reactions in cells with restriction enzymes. Order primers and amplify these regions of interest with PCR. And then ligated to a plasmid so that it can be transformed with competent cells and transfected into bacterial vectors. 3. The sequencing technology works by anchoring the DNA fragments down, and then fluorescenting matching the bases while the camera captures the light that emitted. Piecing together the fragments with overlaps allows decoding of the entire sequences of interest. 4. The output will be bacteria that are able to reduce the amount of oxidative species in its environment.

Write I) I would like to write a novel antibody sequence that is able to detect receptors that show up on cells that become cancerous and circumvent the normal cell cycle. Ii) 1. I would need to write my sequence of interest using existing antibody research and my best hypothesized sequences that might work, and then order the sequences through twist, and integrate them into cancerous mammalian cells to see if the cells lose their cancerous character. 2. There is no known cure to all cancers at the moment, the ability to come up with accurate sequences is a major rate limiting step. Amplifying and transecting into mammalian cells is likely a major time and scalability limiting step.

Edit I) I would like to edit genes that allow some organisms to see infrared light to see if other wavelengths of light can be sensed by those organisms. Ii) 1. I would use CRISPR for the specificity and accuracy and ease of editing. I would need the respective guide RNAs for the genes, and the cas9-CRISPR system to edit the DNA. 2. I would need to prepare the CRISPR system to work in vivo with the organism of interest, I would deliver the editing system with virial vectors, with the respective guides. 3. Major limitations would be the delivery and measuring the output, and I would combat this by optimizing the cycle through trial and error, and have adaptive behavior testing based on stimulus from the wavelength of light of interest. I could also use this test to try to evolve their DNA as needed.

Week 3 HW: Lab Automation

Question 1

Inspiration: I am reading project hail mary with my friends as a weekly book club before the movie is released in late March. A character in the book is Rocky, and that is who is represented in the bio-art.

Code: https://colab.research.google.com/drive/1RF8Lu9l6_CmfEs6N-k-AFWMyPn6nrlXo#scrollTo=pczDLwsq64mk&line=1&uniqifier=1

AI Assistance: Google Gemini 2.5 Flash built into Google Collab

Prompts:

I want to make a design that resembles a rock with six legs like a spider, this is the starter code you have to build this image, the starter code is in the “your code” up to the ### YOUR CODE HERE to create your design line

————————————————————————— NameError Traceback (most recent call last) /tmp/ipython-input-2180272395.py in <cell line: 0>() 1 # Execute Simulation / Visualization – don’t change this code block —-> 2 protocol = OpentronsMock(well_colors) 3 run(protocol) 4 protocol.visualize() NameError: name ‘OpentronsMock’ is not defined I get this error when I try to visualize the code output with this code# Execute Simulation / Visualization – don’t change this code block protocol = OpentronsMock(well_colors) run(protocol) protocol.visualize() You’re encountering a NameError because the OpentronsMock class, which is used for simulating the Opentrons protocol and visualizing the results, hasn’t been defined in your current execution environment. While the example visualization works, its definition seems to be missing from the parts of the notebook you’re currently running.

sorry the code to make the rock with six legs is good, but I want the rock to have more curvature and the legs to have more volume

I mean curvature meaning that its more like fractial shape then a perfect circle Ah, I understand! You’d like the rock to have a more organic, less perfectly circular shape, resembling a fractal. I can achieve this by adding a small, random variation to the radius as each point of the rock is drawn. This will give it a rougher, more natural edge.

I also want one of the legs to be waving hi, and add some musical notes in a speech bubble somewhere, scale the image as necessary so that allt he compoents can be shown

————————————————————————— ValueError Traceback (most recent call last) /tmp/ipython-input-2180272395.py in <cell line: 0>() 1 # Execute Simulation / Visualization – don’t change this code block 2 protocol = OpentronsMock(well_colors) —-> 3 run(protocol) 4 protocol.visualize() 3 frames/tmp/ipython-input-2092617955.py in run(protocol) 140 leg_points.append(center_location.move(types.Point(x=x, y=y))) 141 –> 142 draw_shape(pipette_20ul, ‘Green’, leg_points, volume_per_point=leg_volume_per_point) 143 144 # Speech Bubble (Orange) /tmp/ipython-input-2092617955.py in draw_shape(pipette, color_string, points_list, volume_per_point) 93 current_aspirated_volume += aspirate_chunk_size 94 —> 95 dispense_and_detach(pipette, volume_per_point, point_location) 96 current_aspirated_volume -= volume_per_point 97 pipette.drop_tip() /tmp/ipython-input-2092617955.py in dispense_and_detach(pipette, volume, location) 79 above_location = location.move(types.Point(z=location.point.z + 5)) # 5mm above 80 pipette.move_to(above_location) # Go to 5mm above the dispensing location —> 81 pipette.dispense(volume, location) # Go straight downwards and dispense 82 pipette.move_to(above_location) # Go straight up to detach drop and stay high 83 /tmp/ipython-input-917671935.py in dispense(self, volume, location) 106 assert(isinstance(volume, (int, float))) 107 if (location.point.x2 + location.point.y2 > MAX_DRAW_RADIUS**2): –> 108 raise ValueError(f’Dispensing outside “safe” area: Point ({location.point.x}, {location.point.y}) is more than’ + 109 f" {MAX_DRAW_RADIUS}mm away from the petri dish’s center.") 110 if not self.has_tip: ValueError: Dispensing outside “safe” area: Point

make the speech bubble bigger, and make sure that the music note is fully in the speech bubble You got it! I’ll make the speech bubble larger by increasing its radii and adjust its position slightly to ensure all the musical notes are comfortably inside.

don’t double dip into the same locations, and no speech bubble, but just add a musical note in space somewhere

fill in the fractial shape, and make the musical note bigger Okay, I’ll make those adjustments! I will fill in the fractal rock shape by drawing multiple concentric outlines, and I’ll make the musical note noticeably bigger. This should give your design a more complete and emphasized look.

make the musical note look like a beam note

make the note smaller, and add a quaver next to it

make sure that with orange, I am aspirating the saem amoutn that I am dispensing

Question 2

Paper title: Automated Discovery of Multicellular Behavior for Optimized Plant Growth and Climate Resilience

Paper citation: Mark A. DeAngelis, Philip R. LeDuc, Warren C. Ruder. Adv. Intell. Syst.. 2025; 000, e202500624. https://doi.org/10.1002/aisy.202500624

Paper Description: The paper walked through how it used a robot from opentrons to study how different culture conditions impacted duckweed growth, and how this system can be applied towards other multi-cellular organisms to similarly study varying climate and environmental impacts on their growth. The novalty in this paper involved developing an automated method to prepare, maintain, and characterize triplicates of different test conditions at the same time using an Opentrons OT-2 robot, a custom camera module, and Cellpose deep learning algorithm to analyze the images.

For plasmid construction and characterization, I wouold store all my materials in the 4 C TundraStore until I am ready to use my plasmid backbone and genes of interest. Between each step that requires plate sealed, I would use the PlateLoc, and when I need to analyze underneath the seal or apply a protocal that needs access to the contents, I would use the XPeel Plate Peeler. When the protocals call for centrifuge, I would use the HiG3, and when I need to incubate or shake my reagants I would use the Inheco. When I would want to amplify my components, I would use the ATC. When I am ready to combine reagants, I would use the Echo525 Liquid Transfer. Finally, when I am ready to read my plasmid designs, I would use the Spark Plate Reader.

Question 3

Ideas were thought of by myself, but the experiemntal details and automation integration was polished with ChatGPT 5.2 model.

Week 1 Lab: Pipetting

Individual Final Project

Group Final Project