Low-Hanging Fruit in Automating Biology • Hacker News Board

Re: Low-Hanging Fruit in Automating Biology

#11

Post by foolinaround » Tue, Jun 15, 2021, 12:38 PM UTC

i have been wondering why blood tests have to be so expensive? See [1]

Once the human person has interacted in drawing the blood, then a few drops might be needed to do some additional tests, like check for adequate Vitamin D, etc that the doctor did not prescribe, but is still useful to know, and can be an upsell, there should be just a marginal cost to automated machines/processes doing that test.

A further improvisation is to be able to track a person's details like past history, current complaints, and make a recommendation to add a few additional tests for a few dollars each?

[1] https://www.letsgetchecked.com/us/en/home-micronutrient-test

Re: Low-Hanging Fruit in Automating Biology

#12

Post by agumonkey » Tue, Jun 15, 2021, 1:17 PM UTC

frisco wrote: post #8

udp wrote: post #7

Earlier quoted context omitted.

It would be more helpful to point out some specific examples of what has already been tried and what went wrong than just saying “don’t go there”

Sure, that’s fair. An API driven vivarium as a service with instrumented cages was tried to tens of $M by Vium. That didn’t take off, though there are lots of vendors of sophisticated cage instrumentation now, including based on computer vision. DeepLabCut is amazing and open source. In terms of general progress in experimental tools, there has been tons. The modern super resolution confocals; affordable femtosecond…

Incredible amount of stuff I never hear about, is there a journal or conference to track to follow advances in this field ?

Re: Low-Hanging Fruit in Automating Biology

#13

Post by gkk » Tue, Jun 15, 2021, 1:20 PM UTC

frisco wrote: post #8

udp wrote: post #7

Earlier quoted context omitted.

It would be more helpful to point out some specific examples of what has already been tried and what went wrong than just saying “don’t go there”

Sure, that’s fair. An API driven vivarium as a service with instrumented cages was tried to tens of $M by Vium. That didn’t take off, though there are lots of vendors of sophisticated cage instrumentation now, including based on computer vision. DeepLabCut is amazing and open source. In terms of general progress in experimental tools, there has been tons. The modern super resolution confocals; affordable femtosecond…

As someone with software background and interested in bio, it's a real pleasure to see a commentary from an experienced practitioner.

While we're discussing venues of progress, it's clear that software (and deep learning advances specifically) is poised to have a large impact on how bio research is conducted, and what categories of questions we'll be able to answer. The current consensus on how you leverage software in practice is to put both bio and software teams under one roof (Insitro and Recursion are canonical examples). I wonder if you think software-only company makes sense in this space? The analogy I like to use: people used to roll out their own accounting software within large enterprises until spreadsheets came along. Is there room for an equivalent in some segment of bio?

Re: Low-Hanging Fruit in Automating Biology

#14

Post by dnautics » Tue, Jun 15, 2021, 1:31 PM UTC

Gatsky wrote: post #9

frisco wrote: post #6

As someone who used to think a lot of the stuff in here, and definitely no longer does, I can say that this is not someone who is a practitioner. Adam, if you’re reading this, I would definitely encourage you to take a step back and go deep on how you might prove that the problems are where you think they are. The stuff you’re describing has all been done many times at this point and just either hasn’t turned out to…

Yeah, only someone with the most cursory undersanding of experimental life science could write something like this.

as someone who has worked in biology and "building fault tolerant systems" (erlang), I think this might be a real problem (I don't know if it is; the last lab stuff I did was just before automation), but it's simultaneously obvious that the writer has no clue about how to correctly merge the two concepts.