As someone with a math degree (and a chemistry degree) - there is something similar between chemical intuition and mathematical intuition. Whereby with mathematical intuition I don't mean "gleaning estimates of calculation", but rather, "being able to easily find tractable solutions to proofs".
I think the similarity lies in that both are "black box" processes, where you have to "dictionary knowledge" of existing facts, but not in the "lookup" sense, but in the "spin creative analogies". Then what remains is to formalize the imagined analogy and check to see if the result is confirmed by reality. In the case of proofs, it's writing it down and checking the logic of each step and making sure the axioms lead to the conclusion. In the case of (synthetic) chemistry, it's doing the labor of the reaction and seeing if you get the desired product.
In my case, I looked at the structure of an enzyme and guessed that it was functioning as a PNP transistor, and for my purposes alleviating the high-energy region in the center was probably a good idea - turning it into (effectively) a direct conductor instead of a 'semiconductor'. Making that alteration (justified by the literature) resulted in a 4x improvement in enzyme yield. I don't know for sure if the analogy is exactly correct (didn't have the tools to suss that out), but that's what intuitively "inspired" the strategy that I pursued.
As an alternative perspective: I worked in a lab that was relying heavily on intuition and heuristics for exploratory synthesis. By digitizing all of the lab's data and doing some straightforward machine learning, we were able to sufficiently improve the efficiency of the lab, compared to using intuition, and help the chemists develop a deeper understanding of the system they were studying:
from original article: "One of the most striking features of chemistry as a science is that very palpable properties like color, smell, taste and elemental state are directly connected to molecular structure."
If the lab notebook doesn't contain that information, no amount of machine learning will find it. There's also intuition in subtle things that don't necessarily make it into the lab notebook (did I shake the extractor vigorously or just a little bit?). Or when running on autopilot, maybe you didn't do something that you wrote down you did - that makes a difference.
If you could automate lab note taking, that would be excellent.
Moreover, this 'principles based search' in the subthread article is about crystallization, which is notorious for being a tractable solution based on high-throughput methodologies (and thus has massive parallelization as a worked out strategy). Synthesis, by contrast, is a low-n experience. When machine learning techniques get good at classification by solving MNIST by looking at 3-5 samples of each letter, then maybe I'll be more optimistic.
>> One of the most striking features of chemistry as a science is that very palpable properties like color, smell, taste and elemental state are directly connected to molecular structure.
That doesn't sound so striking. Smell and taste are both direct physical assessments of molecular structure. There's no model where they could fail to be related to molecular structure.
In other words, having that good intuition heuristic matters less when you can brute-search a wider range of options. Of course, no one likes being told that idiotically testing many many options is better than "intelligence". I suspect we programmers are going to be OK with this idea, until we're replaced too. :-)
There will still be cases where this isn't possible. In the chemistry case, let's say you look at the structure of your starting material and your product and notice that it has a functional group that your catalyst can be tethered to with a particular reach length and chirality to reach the reaction site... Unless the computer "understands" these concepts building on some other set of principles, it won't be able to creatively generate solutions to those sorts of problems. In some cases, the "n" of directly analogous situations may be in the low single digits or even zero.
Brute-search is not idiotic testing. It is many times much faster to automate the search and then to move on to the next level/parameter (where you may get to start exploring again).
Brute-force search is idiotic testing, almost by definition. The smart approach is sparse matrices, optimized either by staring at mountains of data (possible computer-assisted), or by gut feeling. Oftentimes the search space is so large (protein crystallization involves at least buffer, precipitant, pH, concentration) that you need to look at promising spots in the search space.
it might not be that easy. What happens when each iteration takes 30 minutes of setup, 4 hours -> overnight reaction time, 20 minutes of concentration, and a 30 minute silica gel column?
you know you have chemical intuition when you glance at a couple molecular structures and immediately know what the diels alder reaction product will look like.
This article gave me awful flashbacks to organic chemistry exams. I got just as far as I could on memorization and math, but as soon as the questions started just being gigantic molecules and "so if we hit this with an acid, what would the leaving group be?" I checked out.
I think the similarity lies in that both are "black box" processes, where you have to "dictionary knowledge" of existing facts, but not in the "lookup" sense, but in the "spin creative analogies". Then what remains is to formalize the imagined analogy and check to see if the result is confirmed by reality. In the case of proofs, it's writing it down and checking the logic of each step and making sure the axioms lead to the conclusion. In the case of (synthetic) chemistry, it's doing the labor of the reaction and seeing if you get the desired product.
In my case, I looked at the structure of an enzyme and guessed that it was functioning as a PNP transistor, and for my purposes alleviating the high-energy region in the center was probably a good idea - turning it into (effectively) a direct conductor instead of a 'semiconductor'. Making that alteration (justified by the literature) resulted in a 4x improvement in enzyme yield. I don't know for sure if the analogy is exactly correct (didn't have the tools to suss that out), but that's what intuitively "inspired" the strategy that I pursued.