Our best method reaches a top-1 accuracy of 47% and 90% when top 5 space groups are selected. That's very good, given what we know about polymorphism and the tight energetic spacing of structures with different space groups from crystal structure prediction studies.
#compchemsky #machinelearning #ML

Hi. We do currently calculate (upper bounds for) energy barriers between structures. We do get some insight into transition pathways from the calculations, but are doing other work along those lines to get more info on pathways - more to come soon.

Congratulations Dr @jennieemartin.bsky.social on an excellent PhD.

Thanks for the comments!

corrected link to Jay's preprint: doi.org/10.26434/che...

and
Jay Johal is presenting poster 129: "Exploring organic chemical space using crystal structure prediction informed evolutionary design," work related to his recent Chemrxiv preprint: lnkd.in/egJe-NDM

4/4

2) Sophie Bennett, also on Monday, at 17.20 in soft matter and biomaterials, speaking on "Guiding the discovery of non-linear optical materials with crystal structure prediction"

3/4

1) Joe Glover 15.20 on Monday in the nano and porous materials session: "Crystal structure prediction of porous isoreticular non-metal organic frameworks"

2/4

Not the prettiest, but the taste turned out pretty good. Hot, but good.

Something like that... possibly. Needed to pick the red currant before the birds ate them, and had a bag full of frozen chillis from last year.
Improvising from there.

Predictive capabilities are assessed when fine-tuned for a range of properties: bulk modulus of small molecule crystal structures, charge carrier mobility in organic semiconductors, CH4 diffusivity & deliverable capacity in porous structures, and lattice energies for assessing polymorph stability.

The Molecular Crystal Representation from Transformers (MCRT) model is pre-trained on over 700,000 molecular crystal structures, ready for fine-tuning for property prediction.