[HN Gopher] Digitizing Smell: Using Molecular Maps to Understand...
___________________________________________________________________
Digitizing Smell: Using Molecular Maps to Understand Odor
Author : taubek
Score : 114 points
Date : 2022-09-07 07:23 UTC (1 days ago)
(HTM) web link (ai.googleblog.com)
(TXT) w3m dump (ai.googleblog.com)
| isoprophlex wrote:
| Some fluff in this PR piece, but I love the message that
| molecular chemistry can now also benefit from deep learning
| advances, thanks to graph neural networks. Because molecules are
| by their nature graphs of atoms, it makes sense to learn a latent
| representation of a molecular entity with a GNN, and use that for
| various classification or prediction tasks.
|
| Makes me wonder if the computationally expensive geometry
| optimization calculations using DFT etc. can be partially done by
| a GNN. So, pre-optimize a structure with a computationally
| cheaper GNN to speed up convergence.
| cing wrote:
| This has been a previous area of research for Google
| (https://ai.googleblog.com/2017/04/predicting-properties-
| of-m...). It remains routine to benchmark GNNs and other
| molecular machine learning models on predicting quantum
| mechanical properties including energies (which speed up
| geometry optimization)
| 6stringmerc wrote:
| I've been wondering for years if it might be possible to use a
| UAV with a pretty hefty sniffer to check out some areas and
| detect cannabis pollen. Then it would maneuver toward the origin
| based on wind data and if it hits it would photo and log GPS and
| auto fly to base ASAP. Then Subcontract to some hardcore
| criminals to go rip it off and flip it. Totally risk free money!
| pstuart wrote:
| Cannabis is typically grown with all males removed prior to
| pollination (aka sinsemilla), so this scenario isn't likely to
| exist.
|
| This must be tongue in cheek, as even if there are grows with
| that scenario, that it being a "business idea" is questionable
| from the start.
| 1024core wrote:
| Pollen is big enough that you could detect it directly.
| LegitShady wrote:
| seems like a risk to life (stealing drugs, hiring criminals,
| etc) when you could just move somewhere where its legal and
| start a legal business. And all for a fairly low value crop
| compared to hard drugs.
|
| I mean it doesn't sound impossible it just sounds like it isn't
| worth it even if you could do it.
| pontifier wrote:
| Thinking about smell a few years ago I realized that individual
| differences in odor perception might be due to missing smell
| receptors.
|
| In color vision we have only three different kinds of cones.
| Color blindness due to a missing type of cone is present in a
| substantial portion of the population.
|
| I believe one of my children is colorblind, and it took a long
| time to figure that out. With a missing smell receptor it would
| be even more difficult to detect the differences between people.
| CoastalCoder wrote:
| I'm curious how much Google's model would be improved by _not_
| aggregating the individual humans together, instead treating
| their identities as a part of the dataset.
| durpkingOP wrote:
| Does this mean we will finally get Smell-o-Vision?
| ChrisMarshallNY wrote:
| Is that like Feel-O-Rama?
|
| https://www.youtube.com/watch?v=-79Mb_uE9Fk
| ggambetta wrote:
| I think it's more like the Smell-O-Scope
| (https://futurama.fandom.com/wiki/Smell-O-Scope).
| olwmc wrote:
| Obligatory: https://archive.google.com/nose/
| adomasm3 wrote:
| exciting direction in this largely unexplored area. Empirically
| we have done a bunch of work with correlating mixtures of
| molecules to human perception at Volatile AI
| (https://volatile.ai) and the degrees of variation in mixtures
| are really wild - a tiny amount of something in a mixture can
| change the smell perception of the whole mixture. So getting
| decent results will be so much harder when looking beyond single
| molecules
| AlbertCory wrote:
| > recently made discoverable by Google Books, which we
| subsequently made machine-readable
|
| You might say "WTF? Google Books already made it machine-
| readable. "
|
| The problem, as you'll discover here;
|
| https://www.theatlantic.com/technology/archive/2017/04/the-t...
|
| is legal and political. Google has it in digital form, but they
| can't give it to you, sell it to you, show it to you, or do
| anything else with it. So the researchers had to re-digitize it.
| Or maybe ("The Google Books team brought the USDA dataset
| online.") the researchers had some special help from Google.
| brilee wrote:
| https://www.google.com/books/edition/Chemicals_Evaluated_as_...
|
| Here's your data.
|
| The "machine digitization" is referring to OCR of the PDFs and
| subsequent translation of archaic chemical names into SMILES
| strings.
|
| disclaimer: I work on this team.
| AlbertCory wrote:
| Thanks. I was in Google Patent Litigation, and there was a
| book I wanted to see. I didn't _know_ it was valuable; if it
| was, there 'd be no problem buying it, but most of the time,
| these things were false positives.
|
| Someone in Books offered to let me come over and see it on
| HIS screen, because he couldn't give me the link even as a
| Google employee.
|
| But I guess Sciences (or GAS, or whatever it's called), got
| y'all to help. Good for them (and you).
| csdvrx wrote:
| > Here's your data.
|
| No. It's the source.
|
| > disclaimer: I work on this team.
|
| Good then: is your research reproducible? As in, do you have
| some code and data somewhere that can be used to verify your
| results?
|
| By that, I mean to run it on the input dataset to create
| something that gives results similar to you GNN results for
| whatever testset you used (in your example, predicting the
| mosquito repellency of a set of molecules)
| nico wrote:
| This is very cool.
|
| It would be great if they could also create an olfactory-nerves-
| electrical-activity to odor map.
|
| Then maybe with that, a device could be built that you could put
| in your nose and feel different smells. Kind of like a VR headset
| but for your nose.
| skbly7 wrote:
| In case someone is interested about this domain. There was an
| interesting challenge around it on AIcrowd last year.
|
| It was called 'Learning to Smell' and hosted by popular swiss
| fragrance and flavour business Firmenich. It contains publicly
| available dataset, baselines, winner codebases, etc., to play
| around with.
|
| [1] https://www.aicrowd.com/challenges/learning-to-smell
|
| [2] https://discourse.aicrowd.com/c/learning-to-smell/357
|
| [3] https://www.aicrowd.com/challenges/learning-to-
| smell/noteboo...
|
| Disclaimer: I have been affiliated with AIcrowd.
| flobosg wrote:
| If you want to have an idea of the molecular mechanisms involved,
| last year the structures of an insect odorant receptor in complex
| with two different odorants was published:
| https://www.nature.com/articles/s41586-021-03794-8
___________________________________________________________________
(page generated 2022-09-08 23:01 UTC)