Week 09 HW

https://2026a.htgaa.org/2026a/course-pages/weeks/week-09/index.html

General homework questions

Explain the main advantages of cell-free protein synthesis over traditional in vivo methods, specifically in terms of flexibility and control over experimental variables. Name at least two cases where cell-free expression is more beneficial than cell production.

Cell-free protein synthesis is technology where proteins are produced using lysed cell machinery (ribosomes, enzymes) rather than living cells.

The main advantages of CFPS:

  • Rapid, direct expression from DNA (plasmids). Bacterial colonies require tagging, growth and selection, whereas CFS are simpler and more straightforward.
  • Direct control over the reaction environment. CFS systems work more directly with primitive biomolecular elements, rather than encapsulated cells, so they are more straightforward to measure, instrument and perturb.
Describe the main components of a cell-free expression system and explain the role of each component.

The major components are:

  • Core cell extract (lysate).
    • Contains ribosomes, tRNAs, translation factors, metabolic enzymes, chaperones, transcription machinery
    • This performs the core processes of protein production. Transcription and translation: DNA → mRNA → protein
  • DNA template. e.g. plasmid DNA, linear PCR
  • Energy system - supplies chemical energy (ATP, GTP) for transcription and translation.
Why is energy provision regeneration critical in cell-free systems? Describe a method you could use to ensure continuous ATP supply in your cell-free experiment.

Transcription and translation burn ATP and GTP very quickly. Without sufficient ATP/GTP production, the reaction rapidly stalls.

Consider a car. Igniting fuel will not propel a car forward, it will dispel energy uselessly. However attaching a piston and a chamber can direct that energy in one direction.

A cell is like a car with a piston. A cell-free system lacks such a system.

This is accomplished in a cell through the membrane. The cell membrane (composed of lipids) creates constrained geometry and controlled sequencing of interactions.

Describe a method you could use to ensure continuous ATP supply in your cell-free experiment..

Add phosphoenolpyruvate, PEP, plus pyruvate kinase.

Protocol: I would run a small optimization matrix rather than assume one energy condition is best. For example, I would test 10, 20, and 40 mM PEP with fixed 1.5 mM ATP and fixed pyruvate kinase, then measure protein yield at 0, 30, 60, 120, and 240 minutes. If yield stops early while ATP is low, I would increase PEP or pyruvate kinase. If yield stops despite ATP remaining, then the problem is probably not ATP supply but substrate depletion, pH drift, magnesium imbalance, mRNA degradation, or protein instability. This separates “energy failure” from other failure modes.

Compare prokaryotic versus eukaryotic cell-free expression systems. Choose a protein to produce in each system and explain why.

Prokaryotic: lacking a nucleus. Examples: E. Coli lysates.

Eurokaryotic: having a nucleus. Examples: Wheat Germ Extract, Rabbit Reticulocyte Lysate, Tobacco BY-2 Lysate

Let’s produce INS_HUMAN (insulin).

Prokaryotic.

  • Oxidizing E. coli lysate (e.g., PURExpress + DsbC, or SHuffle-derived extract).
  • Target: proinsulin (B–C–A single chain).
  • Why? The downstream refold + cleavage chemistry is already industrially solved

Eukaryotic.

  • Rabbit Reticulocyte Lysate + canine pancreatic microsomes.
  • Target: preproinsulin
  • C-peptide still cleaved enzymatically post-translation.

The biosynthesis of insulin involves multiple intermediary steps:

  • preproinsulin: Insulin is synthesized as an inactive precursor molecule, a 110 amino acid-long protein called preproinsulin
  • proinsulin: Preproinsulin is translated directly into the rough endoplasmic reticulum (RER), where its signal peptide is removed by signal peptidase to form proinsulin
  • proinsulin:
    • As the proinsulin folds, opposite ends of the protein, called the “A-chain” and the “B-chain”, are fused together with three disulfide bonds.[26]
    • Folded proinsulin then transits through the Golgi apparatus and is packaged into specialized secretory vesicles, or granules.[26]
    • In the granule, proinsulin is cleaved by proprotein convertase 1/3 and proprotein convertase 2, removing the middle part of the protein, called the “C-peptide”.[26]
    • Finally, carboxypeptidase E removes two pairs of amino acids from the protein’s ends, resulting in active insulin

Preproinsulin contains a signal peptide. Signal peptides function to prompt a cell to translocate the protein, usually to the cellular membrane.

C-peptide is a connecting protein produced when the pancreas cleaves proinsulin to make mature insulin. C-peptide excision is required and is done by PC1/3 + PC2 in vivo — neither CFE system reproduces that, so both routes need an in vitro cleavage step (trypsin + carboxypeptidase B, ?apparently? standard industrial route).

prokaryotic = make it cheap and finish it on the bench;
eukaryotic = watch it fold the way a β-cell folds it.

How would you design a cell-free experiment to optimize the expression of a membrane protein? Discuss the challenges and how you would address them in your setup.

(This question was super hard and I was lost. I am verbatim coping the response from the Claude LLM here because I really loved how first-principles the answer was.)

Concepts I became aware of:

  • membrane protein
  • fake wall - detergents, liposomes
  • concept of a “screen”
  • readout - another new term which fits into screen. in programming, we’d just call it a test.

Proteins are chains of amino acids that fold into 3D shapes. Most proteins are water-soluble: their surface is “hydrophilic” (water-loving), they float around in the watery interior of the cell, no problem.

Membrane proteins are different. They’re designed to live embedded in the cell’s outer wall — the lipid bilayer, which is a thin sheet of greasy fat molecules. The parts of the protein that sit inside that greasy sheet are themselves greasy (“hydrophobic”, water-hating). Think of a bolt designed to be installed through a wall: the threaded shaft is meant to be inside the wall material, only the head and tail stick out into air.

Now: in CFPS, there’s no wall. The protein gets manufactured into pure water. Its greasy mid-section is exposed to water, which it hates. It does what greasy things do in water — clumps up with other greasy bits (think oil droplets in vinegar). It misfolds, aggregates into junk, and you get no usable product.

So the central engineering problem for membrane-protein CFPS is: you have to provide a fake wall for the protein to embed into while it’s being made. Everything else in the protocol is in service of that.

The menu of fake walls (in rough order of complexity):

  • Detergents — soap molecules. They have a greasy tail and a water-loving head, so they can wrap around the greasy parts of the protein and keep it in solution. Cheap, easy. Downside: detergents are often harsh enough to denature the protein.
  • Liposomes — actual little lipid bubbles, basically tiny vesicles made of the same fat the real membrane is made of. The protein can insert into the bubble’s wall as it’s manufactured. More native, harder to work with.
  • Nanodiscs — a clever trick: a small flat patch of lipid bilayer (~10 nm across) held together by a belt of protein around the edge, like a coin made of fat with a metal rim. The membrane protein sits in the middle of the disc. Very clean, very defined, beloved by structural biologists. Most expensive.
  • SMALPs — a synthetic polymer (SMA) that does the nanodisc trick without needing the protein belt. Cheaper than nanodiscs.

The supporting cast. A real cell does more than just provide a wall. It has:

  • Translocons — machines built into the membrane that thread the protein into the wall as it’s being made (like a sewing machine guiding fabric through). Without these, the protein doesn’t insert correctly even if a wall is present. You can buy these as “inverted membrane vesicles” — little fragments of bacterial membrane with the translocons still in them — and dump them into the reaction.
  • Chaperones — helper proteins that prevent misfolding. Add as purified extras.
  • Redox environment — some membrane proteins have internal “staples” (disulfide bonds) that only form in an oxidizing environment. Standard cell juice is reducing (the opposite). You add chemicals to flip it.

How you’d actually run the experiment. You’re optimizing across maybe 5 variables (which wall, how much wall, with or without translocons, temperature, redox state). Too many combinations to try one at a time, so you do a screen: 48–96 small parallel reactions in a plate, each with a different combination, and a fast readout that tells you which ones worked.

The standard fast readout uses split-GFP: GFP is the green fluorescent protein, and you can split it into a big piece and a tiny tag (11 amino acids). Attach the tiny tag to your membrane protein. Add the big piece to the reaction. They only find each other and turn green if your membrane protein folded correctly and the tag is accessible. So fluorescence = success, no fluorescence = junk. Read the plate in a few minutes, identify the winning conditions, then scale those up.

Imagine you observe a low yield of your target protein in a cell-free system. Describe three possible reasons for this and suggest a troubleshooting strategy for each.

Yield ≈ template availability × transcription efficiency × translation efficiency × product stability × reaction lifetime

Aspects of process design:

  • DNA template supply
  • Transcription (DNA -> mRNA)
  • Translation (mRNA -> protein)
  • Folding / activation
  • Energy + raw materials supply
    • system starts strong, then fuel runs out or waste accumulates
    • ATP donor depleted, Amino acids consumed, NTP depletion, Phosphate buildup, Enzymes lose activity, Too much DNA overloads machinery
  • Process consistency

Troubleshooting is assumed to mean diagnosis here. Implementation of a solution is up to the experimetal designer.

Three possible reasons for low yield:

  1. Poor folding. The protein may be successfully translated, but immediately misfolds, aggregates, or becomes insoluble. This is especially common for large proteins, membrane proteins, disulfide-rich proteins, or eukaryotic proteins expressed in bacterial extracts.
    • Troubleshooting strategy:
      • DNA degradation: incubate DNA in extract, Sample at 0, 15, 30, 60 min, Run DNA gel or qPCR across the gene
  2. Energy depletion / reaction burnout. Cell-free systems consume ATP extremely rapidly.
    • Troubleshooting strategy:
      • Assume we measure yield somehow - eg. fluorescence (e.g. GFP), luciferase activity, SDS-PAGE band intensity, western blot, or mass spectrometry
      • Can diagnose energy depletion as yield declining abnormally (e.g. abruptly). Supplement fresh ATP mix midway.
        • if production resumes -> energy limitation confirmed
  3. Poor template availability / transcription inefficiency.
    • Troubleshooting strategy:
      • Weak Transcription initiation: measure mRNA by RT-qPCR, compare target template against a known-good positive-control template, keep coding region same, swap promoter/5’ region
        • if DNA intact but mRNA low = transcription problem
        • if positive control produces mRNA but target does not = target promoter/sequence design problem
        • if both fail = extract/polymerase/reaction chemistry problem

Useful synthetic cell.

Design an example of a useful synthetic minimal cell as follows:

  1. Pick a function and describe it.

    1. What would your synthetic cell do? What is the input and what is the output?

    The synthetic cell would grow wood. The input is CO2 and photons and output is the structure it grows. Wood is a composite material made out of 40% cellulose (contained within cells), 30% lignin, and 30% hemicellulose.

    1. Could this function be realized by cell-free Tx/Tl alone, without encapsulation?

    No, since wood is made from cells. Cell-free structure could be created using crystalline approaches.

    1. Could this function be realized by genetically modified natural cell?

    Yes, but it would be more complex in the limit.

    1. Describe the desired outcome of your synthetic cell operation.

    Programming a tree to grow into a custom shape (a house) via morphological programming, growing a tree faster and more efficiently (without ancestral code which may no longer apply in current environment).

  2. Design all components that would need to be part of your synthetic cell.

    1. What would be the membrane made of?

    Two lipids as in JVCI-syn3A - phosphatidylglycerol and a specific glycolipid.

    1. What would you encapsulate inside? Enzymes, small molecules.
    • Carbon capture and fixation - CETCH cycle inspired design?
    • Energy production - cyanobacteria?
    • Cellulose extrusion - Komagataeibacter? Not sure if it’s possible to put a bacteria in a cell
    • Lignin production

    There are many more things, I know. ;) These are the core ones that might be enough to answer the exercise.

    1. Which organism your Tx/Tl system will come from? Is bacterial OK, or do you need a mammalian system for some reason? (hint: for example, if you want to use small molecule modulated promotors, like Tet-ON, you need mammalian)

    Bacterial systems lack a nucleus and Tx/Tl happens in same place (vs. in human cell - where transcription occurs in the nucleus, translation occurs outside the nucleus but still in the cell).

    I’m not sure yet. It would not seem we need mammalian gene complexes or closures from different organelles.

    1. How will your synthetic cell communicate with the environment? (hint: are substrates permeable? or do you need to express the membrane channel?)

    It needs to exchange:

    • light
    • CO2 / bicarbonate
    • water
    • ions
    • small molecule substrates
    • waste products
    • possibly output molecules

    Channels:

    • Light - NA
    • CO2 - membrane-permeable
    • Bicarbonate - may need a bicarbonate transporter or channel
    • Water - membrane-permeable

  3. Experimental details

    1. List all lipids and genes. (bonus: find the specific genes; for example, instead of just saying “small molecule membrane channel” pick the actual gene.)

    There are so many haha. And it would be the most adequate to describe this as an engineering design - ie. a hierarchy of encapsulation.

    • Lipids
      • phosphatidylglycerol
      • specific glycolipid
    • Genes
      • Entire cyanobacteria 12 Mb genome
      • Entire Komagataeibacter (K. xylinus E25) 3.4 Mb genome
      • (missing) lignin production gene
    1. How will you measure the function of your system?

    This monolith synthetic cell will have too much uncertainty to design-build-test and solve in one iteration. It will definitely require divide-and-conquer to break it down into testable subunits.

Homework question from Peter Nguyen

Freeze-dried cell-free systems can be incorporated into all kinds of materials as biological sensors or as inducible enzymes to modify the material itself or the surrounding environment.

Choose one application field — Architecture, Textiles/Fashion, or Robotics — and propose an application using cell-free systems that are functionally integrated into the material. Answer each of these key questions for your proposal pitch:

  • Write a one-sentence summary pitch sentence describing your concept.

Seasoning which turns rapidly digestible starch into slower digestible starch, which reduces glucose spikes.

  • How will the idea work, in more detail? Write 3-4 sentences or more.

This product is an enzyme powder sprinkled onto starchy food after cooking, especially rice, potato, pasta, corn, or sweet potato. The active enzyme is a starch-debranching enzyme such as pullulanase or isoamylase, which cuts branch points in amylopectin and creates more linear starch chains. When the food is then cooled, these linear chains pack together into retrograded resistant starch, which human digestive enzymes break down more slowly than normal cooked starch. The result is not that carbohydrates disappear, but that some rapidly digestible starch is shifted into a slower-digesting or resistant form, reducing the speed and size of the post-meal glucose rise.

  • What societal challenge or market need will this address?

This addresses the need for simple food-preparation tools that reduce post-meal glucose spikes without requiring people to fully change what they eat. It is especially relevant for people managing diabetes, insulin dosing, blood glucose variability, or low-GI diets. It would be used like a seasoning or cooking aid for high-starch foods, not as a replacement for insulin or medical treatment.

  • How do you envision addressing the limitation of cell-free reactions (e.g., activation with water, stability, one-time use)?

The cell-free limitation would be handled by treating the product as a freeze-dried biochemical system rather than a living organism. The enzyme would be produced in microbes, purified, then dried with stabilizers such as trehalose or other protein-protective excipients so it can survive storage as an inactive powder. Water from the food rehydrates the system and turns the enzyme back on, while buffer salts keep the local pH in the enzyme’s working range. Because there is no cell to repair damaged proteins or regenerate itself, the reaction is designed as a one-time use system: the enzyme acts during a short warm window, modifies the starch structure, then becomes inactive during later heating, digestion, or storage.

Homework question from Ally Huang

Freeze-dried cell-free reactions have great potential in space, where resources are constrained. As described in my talk, the Genes in Space competition challenges students to consider how biotechnology, including cell-free reactions, can be used to solve biological problems encountered in space. While the competition is limited to only high school students, your assignment will be to develop your own mock Genes in Space proposal to practice thinking about biotech applications in space!

For this particular assignment, your proposal is required to incorporate the BioBits® cell-free protein expression system, but you may also use the other tools in the Genes in Space toolkit (the miniPCR® thermal cycler and the P51 Molecular Fluorescence Viewer). For more inspiration, check out https://www.genesinspace.org/ .

  1. Provide background information that describes the space biology question or challenge you propose to address. Explain why this topic is significant for humanity, relevant for space exploration, and scientifically interesting. (Maximum 100 words)

Scientific research and invention requires intelligence. AI systems provide intelligence in much greater amounts, for orders of magnitude lower cost than biological intelligence. AI systems require energy and data centers. Building data centers in space can be done in a different tradeoff space - powered by solar (at much higher solar efficiency due to lack of atmosphere), unconstrained by regulatory cost. However transporting hardware to space is expensive.

What if we could build parts of the data center in space using cell-based systems? If transporting a seed to space could grow a tree, potentially we could transport a seed which grows a data center (or even a rack for a server).

Transporting seeds to space that grow into objects offers exponential savings compared to sending a data center as a manufactured object. This is due to the cost economics of sending load into space - the relationship between the mass of the rocket’s fuel and the mass of the payload is exponential, dictated by the Tsiolkovsky rocket equation. You can also think about it in the inverse - reducing load makes the fuel cost exponentially cheaper.

This requires solving:

  • morphological programming - how to program a single cell to grow into a 3D structure
  • materials design - ie. what is this rack made out of? Something that could survive in space’s vacuum? self-sealing lichen/coral
  1. Name the molecular or genetic target that you propose to study. Examples of molecular targets include individual genes and proteins, DNA and RNA sequences, or broader -omics approaches. (Maximum 30 words)

Engineered photosynthetic cyanobacteria/lichen-like chassis genes controlling carbon fixation, extracellular polysaccharide secretion, melanin biosynthesis, mineralization, desiccation tolerance, and 3D morphogenesis.

  1. Describe how your molecular or genetic target relates to the space biology question or challenge your proposal addresses. (Maximum 100 words)

These enable 3D structure production in the same way a plant would, mineralisation provides the hard dead shell that would provide protection of the living inner cells from the vacuum of space.

  1. Clearly state your hypothesis or research goal and explain the reasoning behind it. (Maximum 150 words)

Above in Q1

  1. Outline your experimental plan - identify the sample(s) you will test in your experiment, including any necessary controls, the type of data or measurements that will be collected, etc. (Maximum 100 words)

This experiment would be broken down:

  • solving morphological programming - growing a simple 3D shape from programming a single cell
  • building complex structures - instead of a shape made of a single material, growing a mineral layer and now the cell inner layer
  • testing photosynthesis - adding photosynthesis genes and building the mechnism for the organism to convert energy
  • sending it to space and testing it