Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Wet-lab innovations will lead the AI revolution in biology

substack.com

Post reply on HN
Print view View original

21–27 of 27 posts

Re: Wet-lab innovations will lead the AI revolution in biology

#21

Post by koeng »

Clonal DNA synthesis has increased in price over the past 6 years (even when accounting for inflation). On that metric, we’re actually regressing in our ability to modify the natural world. It’s even worse than stagnation.

Or even look at lab robotics - in 2015, you were able to buy a new opentrons for $2500. Now it’s about $10,000 - the only way to rival the old pricing is to scrounge around used sales.

Enzyme prices haven’t dropped in basically forever. Addgene increased plasmid prices a little bit ago.

I feel like computer hackers can’t even imagine how bad it is over here

Re: Wet-lab innovations will lead the AI revolution in biology

#22

Post by abhishaike »

koeng wrote: post #21

Clonal DNA synthesis has increased in price over the past 6 years (even when accounting for inflation). On that metric, we’re actually regressing in our ability to modify the natural world. It’s even worse than stagnation. Or even look at lab robotics - in 2015, you were able to buy a new opentrons for $2500. Now it’s about $10,000 - the only way to rival the old pricing is to scrounge around used sales. Enzyme price…

this is super interesting, had no idea this was happening! i assumed things were tending towards cheaper given sequencing prices were dropping, why are things rising elsewhere?

Re: Wet-lab innovations will lead the AI revolution in biology

#23

Post by throwawaymaths »

staunton wrote: post #16
throwawaymaths wrote: post #14

Earlier quoted context omitted.

How exactly would ML speed it up something that takes 3 grad students full time? Listen. A lot of this shit gets discovered for crazy reasons. For two years these two postdocs were throwing away one fraction of their size exclusion chromatography step. I got into a really heated six hour argument where i insisted that the postdocs did not understand that size exclusion chromatography, big shit comes out first (they t…

A hypothetical good AI would have reviewed the experimental design and pointed out the misconception

How would the AI know to look there? Trash on ends "void volumes" of chromatography is common.

Anyways what is your training set? Probably upwards of 50% of papers are trash. Will the AI have the intuition to know which ones are good? Does the AI listen at the water cooler to grad students griping about Corey yield?

(It's not on the internet. It's the general sentiment that yields reported by the E.J. Corey lab are inflated).

Re: Wet-lab innovations will lead the AI revolution in biology

#24

Post by koeng »

abhishaike wrote: post #22
koeng wrote: post #21

Clonal DNA synthesis has increased in price over the past 6 years (even when accounting for inflation). On that metric, we’re actually regressing in our ability to modify the natural world. It’s even worse than stagnation. Or even look at lab robotics - in 2015, you were able to buy a new opentrons for $2500. Now it’s about $10,000 - the only way to rival the old pricing is to scrounge around used sales. Enzyme price…

this is super interesting, had no idea this was happening! i assumed things were tending towards cheaper given sequencing prices were dropping, why are things rising elsewhere?

For synthesis, it’s mainly because there is a monopoly and the challenge (DNA assembly) is super boring in comparison to sexy things like DNA synthesis.

For robotics, it’s because Opentrons started scaling and needed to make more $$$ rather than staying small (fair to them, SoftBank dollars are attractive)

Generally speaking, biology is hard and uncertain, so the market isn’t as competitive as you’d imagine. Synthesis prices stagnated a little bit for a while in comparison to where they could be because Illumina didn’t have competition

Re: Wet-lab innovations will lead the AI revolution in biology

#25

Post by theGnuMe »

jdeaton wrote: post #2

> people unacquainted with biology have a false perception of how low-throughput biology experimentation is. In many ways, it can be. But the underlying physics of microbiology lends itself very well to experiments that could allow one to collect tens-of-thousands, if not millions, of measurements in a singular experiment. It just needs to be cleverly set up. I think this passage gets to the fundamental rift of disag…

NGS is the counter example here. We will also have single cell proteomics in the near future. Robots can do lots of things like vary the initial conditions across a spectrum of variables... something no grad student would want to do.

Re: Wet-lab innovations will lead the AI revolution in biology

#26

Post by esel2k »

dexwiz wrote: post #15
bartread wrote: post #3

Earlier quoted context omitted.

You have just very eloquently expressed why I left a career in biochemistry behind after undergrad. Realistically I had no business doing that degree in the first place: I simply don't have the patience for the lab work grind.

Same reason I left Chemistry. Gotta grind for 80 hours a week for a decade for a chance at a good position. And hope you don’t get stuck under a PI that steals all the credit.

Seems like I am not alone - I still tried for 4 years to make it work in pharma but realised that spending 3 days to grow primary cells to just get irreproducible results was not going go be satisfying.

Re: Wet-lab innovations will lead the AI revolution in biology

#27

Post by esel2k »

The lab is not incredibly low throughput but also most of the experiments look at a single modality. Take a cell viability or FACS assay - while some additional measurements could be taken or analysed - most of the time the scientist will look at a single parameter. In a separate assay the cell (other passage/day) will be undertaken another assay resulting in nearly incomparable data.

The solution: Multimodal data and getting more info on experiments setup (often a bit of voodoo and not written down properly).

Post reply on HN