I don't know if I have missed the big thing here (was supposed to do exactly the same flowery thing described there for crystals around 2019-2020), but the graphic with the Autoencoder is roughly what people did in 2018 (Gomez-Bombarelli,
https://pubs.acs.org/doi/10.1021/acscentsci.7b00572), I think the review cited reproduced this. Also notice: it has the MLP in the middle, the performance of which was/is not really helping either - especially if your model should actually produce novel stuff, e.g. extrapolate.
Finally: every kid can draw up novel structures. Then: how do you actually fabricate these (in the case of real novel chemistry and not some building-block stuff). Noone has a clue!
I for myself have decided that for now (with the data at hand and non-Alphafold-budgets) the 2 keys areas, where you can actually help computational chemistry are:
- creating really robust and generally applicable ML-MD-potentials, potentially using graphs https://arxiv.org/abs/2106.08903 (or a traditional approach: https://www.nature.com/articles/s41467-020-20427-2). Facebook is also working in this area: https://pubs.acs.org/doi/10.1021/acscatal.0c04525
- and approximating exchange correlation functionals (... Google and some guys at Oxford, which got stomped over by the deepmind-PR machine https://arxiv.org/pdf/2102.04229.pdf): https://www.science.org/doi/10.1126/science.abj6511
If anyone can tell me how those generative models spit out graphs which look like reality (actually this is imho part of AlphaFold), wake me up.
Finally: every kid can draw up novel structures. Then: how do you actually fabricate these (in the case of real novel chemistry and not some building-block stuff). Noone has a clue!
I for myself have decided that for now (with the data at hand and non-Alphafold-budgets) the 2 keys areas, where you can actually help computational chemistry are:
- creating really robust and generally applicable ML-MD-potentials, potentially using graphs https://arxiv.org/abs/2106.08903 (or a traditional approach: https://www.nature.com/articles/s41467-020-20427-2). Facebook is also working in this area: https://pubs.acs.org/doi/10.1021/acscatal.0c04525
- and approximating exchange correlation functionals (... Google and some guys at Oxford, which got stomped over by the deepmind-PR machine https://arxiv.org/pdf/2102.04229.pdf): https://www.science.org/doi/10.1126/science.abj6511
If anyone can tell me how those generative models spit out graphs which look like reality (actually this is imho part of AlphaFold), wake me up.