Accelerating life sciences research

So the same concept of an LLM training and inferring tokenized language, it’s doing tokenized aminos. Instead of artificial intelligence/language it’s doing artificial evolution/life I guess?

Re: Accelerating life sciences research

#5

Post by mrbungie » Sat, Aug 30, 2025, 5:36 AM UTC

dingnuts wrote: post #3

[flagged]

You are probably going to be downvoted this, and with some justification even (i.e. implying something about visitors).

Anyways, this is old and the original post didn't get much attention anyways: https://news.ycombinator.com/item?id=44985844

Re: Accelerating life sciences research

#6

Post by dang » Sat, Aug 30, 2025, 5:40 AM UTC

outside1234 wrote: post #2

[flagged]

Please don't do this here.

Edit: we asked you to stop posting unsubstantive comments quite recently (https://news.ycombinator.com/item?id=44832751) and have done so many times before (https://news.ycombinator.com/item?id=33700337).

If you continue doing this, we'll end up banning you. I don't want to ban you, so if you'd please review https://news.ycombinator.com/newsguidelines.html and fix this, that would be good.

Re: Accelerating life sciences research

#7

Post by Legend2440 » Sat, Aug 30, 2025, 5:41 AM UTC

If I’m understanding this right:

1. They have a protein model similar to AlphaFold

2. A biotech startup used this model to engineer a protein that converts adult cells into stem cells, at a higher efficiency than existing techniques. (But still only a tiny fraction of cells convert)

Application to life extension seems speculative.

Re: Accelerating life sciences research

#8

Post by pu_pe » Sat, Aug 30, 2025, 5:52 AM UTC

Legend2440 wrote: post #7

If I’m understanding this right: 1. They have a protein model similar to AlphaFold 2. A biotech startup used this model to engineer a protein that converts adult cells into stem cells, at a higher efficiency than existing techniques. (But still only a tiny fraction of cells convert) Application to life extension seems speculative.

Yes, that's how I read it too.

Seems odd that OpenAI would want to get involved in this space, feels like Deepmind has a huge headstart already.

Re: Accelerating life sciences research

#9

Post by biophysboy » Sat, Aug 30, 2025, 6:12 AM UTC

> We initialized it from a scaled-down version of GPT‑4o to take advantage of GPT models’ existing knowledge, then further trained it on a dataset composed mostly of protein sequences, along with biological text and tokenized 3D structure data, elements most protein language models omit.

> A large portion of the data was enriched to contain additional contextual information about the proteins in the form of textual descriptions, co-evolutionary homologous sequences, and groups of proteins that are known to interact.

These bits made me wonder what would have happened if they had only used the supplementary biological data with an untrained LLM model.