Evolutionary Multiobjective Optimization of Multiligand Metal Complexes in Diverse and Vast Chemical Spaces

Hannes Kneiding, Ainara Nova, David Balcells (2023)
Highlighted by Jan Jensen

Figure 5 from the paper. (c) 2023 the authors. Reproduced under the CC BY ND license

The authors show that an NBO analysis can be used to identify the charges (as well as their coordination mode) of individual ligands in TM-complexes. This is a key property needed to properly characterise the ligands and, thus, the complex as a whole. They have manually checked the approach for 500 compounds and finds that it gives reasonable results in 95% of the cases. That number drops to 92% if coordination mode is also considered. They provide these, and many other, properties of 30K ligands extracted from the CSD.

The NBO analysis is based on PBE/TZV//PBE/DZV calculations, which are a bit costly, but it will be interesting to see whether lower theories (e.g. DZV//xTB) give similar results.

Based on this knowledge the authors build a data set of 1.37B square-planar Pd compounds and compute their polarizability and HOMO-LUMO gap. They then search this space for molecules with both large polarizabilities and HOMO-LUMO gaps using a genetical algorithm that optimises the Pareto front, and show that optimum solutions can be found by considering only 1% if the entire space. The GA code is not available yet, but should be released soon.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Deep Learning Metal Complex Properties with Natural Quantum Graphs

Hannes Kneiding, Ruslan Lukin, David Balcells (2022)
Highlighted by Jan Jensen

Figure 2 from the paper (c) The authors. Reproduced under the CC-BY-NC-ND 4.0 license

While there's been a huge amount of ML work on organic molecules, there as been comparatively little on trantition metal complexes (TMCs). One of the reasons is that many of the cheminformatics tools we take for granted are harder to apply to TMCs due to their more complex bonding situations. This makes bond perception and computing node-features like formal atomic charges, and hence graph representations, quite tricky. Which, in turn, makes standard ML tools like binary finger prints or graph-convolution NNs tricky to apply to TMCs.

This paper suggest using data from DFT/NBO calculations to create so-called "quantum graphs", where the edges are determined using both bonding orbitals and bond-orders while node- and edge-features are derived from other NBO properties.

This representation is combined with two graph-NN methods (MPNN and MXMNet) and trained against DFT properties such as the HOMO-LUMO gap. The results are quite good and generally better than radius graph methods such as SchNet. However, one should keep in mind that both the descriptors and properties are computed with DFT.

Given that the computational cost of the descriptors is basically the same as the property of interest, this is a proof-of-concept paper that shows the utility of the general idea. However, it remains to be seen whether cheaper descriptors (e.g. based on semi-empirical calculations) result in similar performance. However, given the current sparcity of ML tools for TMCs this is a very welcome advance.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Polyoxometalates are cationic, not anionic

N.V. Izarova, N. Vankova, A. Banerjee, G.B. Jameson, T. Heine, F. Schinle, O. Hampe, U. Kortz, Angewandte Chemie International Edition 2010, 49, 7807-7811 (Paywall)
Contributed by Marcel Swart

Polyoxometalates are clusters of metals connected together through oxygens, and can be giant molecules such as {(Mo^VI)Mo^VI₅O₂₁}₁₂(Mo^V₂O₄)₃₀]^12- (also known as Mo₁₃₂) as shown by Bo and Miró in Dalton Transactions recently^[1]. These clusters bear a total anionic charge, for instance -12 in the aforementioned example. However, this is not the complete picture.

Ulrich Kortz (Univ. Bremen) visited Girona a couple of months ago and reported an interesting example of how theory can be useful. His group was working on a "A Noble-Metalate Bowl", and when trying to reproduce the ⁵¹V NMR spectrum computationally, it was impossible to get good agreement. By introducing Na/K cations they did get more and more reasonable results, and only obtained good agreement after having introduced 7 potassiums (or alternatively 6 potassiums and 1 sodium).

At first, the experimental people did not believe the calculations, because they had their mind set on the fact that polyoxometalates carry a large negative charge, and not a positive one. However, after doing electrospray mass spectrometry, indeed they observed mainly two peaks:

1) a singly charged molecular cation {K₇[Pd₇V₆O₂₄(OH)₂]}⁺ (with seven potassiums)
2) a singly charged molecular cation {Na₁K₆[Pd₇V₆O₂₄(OH)₂]}⁺ (with six potassiums)

Therefore, contrary to popular belief, polyoxometalates are cationic!

[1] C. Bo, P. Miró, Dalton Trans. 2012, 41, 9984-9988


This work is licensed under a Creative Commons Attribution 3.0 Unported License.