LA-Proteina
Posted4 months agoActive4 months ago
github.comResearchstory
calmmixed
Debate
60/100
Protein DesignBiotechnologySynthetic Biology
Key topics
Protein Design
Biotechnology
Synthetic Biology
La-Proteina is an open-source protein design tool released by NVIDIA, sparking discussion on its potential applications and risks, including its impact on the biosphere and immune systems.
Snapshot generated from the HN discussion
Discussion Activity
Moderate engagementFirst comment
3d
Peak period
6
84-96h
Avg / period
3
Comment distribution12 data points
Loading chart...
Based on 12 loaded comments
Key moments
- 01Story posted
Sep 11, 2025 at 9:43 AM EDT
4 months ago
Step 01 - 02First comment
Sep 14, 2025 at 8:29 PM EDT
3d after posting
Step 02 - 03Peak activity
6 comments in 84-96h
Hottest window of the conversation
Step 03 - 04Latest activity
Sep 17, 2025 at 12:18 AM EDT
4 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
ID: 45211580Type: storyLast synced: 11/20/2025, 4:56:36 PM
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
But how concerned should we be with novel proteins being pumped into the biosphere? What does each new design do to our immune systems and ecosystems? How robust are these systems to, in effect, any protein that can be printed, and any substance that they can catalyze?
I am skeptical that a regulatory regime could reliably predict the consequences of releasing novel proteins via simulations or small scale experiments.
“Printing proteins” is a routine procedure since the late 70s and it included novel proteins or variations of existing proteins since the early days of recombinant synthesis. Insulin and growth hormones were some of the first practical applications.
Modern techniques mess with the print system of some cells to generate huge variability for specialized experiments. These proteins themselves are largely harmless or only viable in controlled conditions.
The type of research you can be a bit worried about is the one that involves designing entirely new contageous and airborne-transmissible viruses or perhaps other designer pathogens. If you only ever built a super hazardous protein, you would still need to find a virus to deliver it somewhere practical (or inject it, like insulin, if it works outside of cells) and then it falls to a different type of problem anyways. Viruses often only need to multiply to cause harm, so the dangerous parts of them are their injection, attachment, replication, or immune evation pieces and there is enough examples of these known from the study of existing viruses, so you dont really have much need of this type of computational tool.
So making any arbitrary protein literally go viral is a solved problem? Yes, I can see how that adds spice to a tool that supercharges the exploration of protein-space.
It may surprize people who dont work in these areas, but finding ways to kill humans by injecting something in them is completely trivial. The hard part is finding something that does not kill them and has a therapeutic effect.
No virus is necessary for prions to spread, and they are nearly impossible to destroy. And merely ingesting the right ones is sufficient.
Someone could (if they discovered one) construct a nasty prion directly eh? And we’d probably be pretty fucked.
So far though, we only know of a handful of actual working prions, so maybe there isn’t other others?
Agreed
> Someone could (if they discovered one) construct a nasty prion directly eh? And we’d probably be pretty fucked.
It would be easy to construct a potent prion-like sequence that works in isolation (in vitro) with such a tool, but not clear what the rationale would be even if one has nefarious purposes. We know of enough of them (eg pick Creutzfeldt–Jakob disease for human hosts; if you have a hydrogen bomb, the variations on the engineering could be intersting but most likely not needed.) I dont think we would be fucked if someone constructed new prion-like sequences with this method, though we might be at risk if someone makes genuine efforts to find ways to deliver the existing (or new ones) to humans at scale. The main risk factors in prions diseases involve exposure and host compatibility. You need enough time and thus enough of a starting dose for harm to happen. You need to enter the host and go to the right place, say nervous system, without being chopped up along the way by random proteases and without self aggregating in the wrong place and becoming useless. There may be other computational tools that in combination would help realise more potent/nasty/risky designs, but it is probably much easier to use human cell lines and benchwork (design a funky evolution experiment) to fish out nasty sequences that actually work in human cells.
Overall in biology and chemistry killing is easy, therapy is hard. Prions are somewhat interesting from a biology or engineering perspective, but they dont have the huge added risks of rapid exponential growth and easy transmission to hosts that many viruses have. They seem more like a curiosity and primitive danger form, and not a huge public health risk factor. Maybe there even exist some semi benign (even useful?) forms related to prions that we dont study much yet and they may end up influencing things like our understanding of aging or immune responses.
Prions relate to nucleation and first order phase transitions, so they have some technical appeal to people with past background in physics or chemistry, including myself, but they are not making it in my top 20 threats for humanity, not even if there were concerted efforts by rogue actors to create new nasty ones.