Graeme Day
@graemeday.bsky.social
790 followers 220 following 65 posts
Professor, Head of Digital and Data-Driven Chemistry, School of Chemistry and Chemical Engineering at @unisouthampton.bsky.social Associate Editor at Chemical Science (@roysocchem.bsky.social) structure prediction, materials discovery
Posts Media Videos Starter Packs
graemeday.bsky.social
Just about ready for our first workshop on mol-cspy: our source software for crystal structure prediction
gitlab.com/mol-cspy/mol...
A massive thank you to the research team in getting material together for this.
#compchemsky #chemsky
graemeday.bsky.social
If you're attending the Materials and Molecular Modelling Hub #MMMHub conference this week, go listen to Jordan Dorrell: "Sensible Asymmetric Units for Crystal Exploration". These are new methods in crystal structure prediction aimed at better efficiency for complex structures. #compchemSky #ChemSky
stochasticchemist.bsky.social
A dreary Tuesday morning in Southampton but excited for the #MMMHub conference this afternoon! If you want to hear what I've been up to with @graemeday.bsky.social , I have a talk today at 15:40 and I'm poster number 7!
#compchem
graemeday.bsky.social
Thank you to the organisers of the "from molecules to materials" meeting in Bologna for inviting me to give a keynote talk.
Among other things, I spoke about @aichemyhub.bsky.social-funded large-scale crystal structure prediction and transferable ML potentials: doi.org/10.1039/D4FD...
#compchemsky
Image of speaker at conference in front of projected slide showing computer simulation results on molecular crystals.
graemeday.bsky.social
Congratulations @jennieemartin.bsky.social on this work.

The study adapts the SOAP (smooth overlap of atomic positions) kernel to molecular crystals and evaluates the resulting kernel for applications to crystal structure prediction landscapes.
doi.org/10.26434/che...

#CompChemSky #ChemSky
graemeday.bsky.social
Congratulations @aicooper.bsky.social on the award of the @royalsociety.org Davy Medal "for creating innovative digital approaches to chemistry that combine first-principles computational chemistry, autonomous robots and artificial intelligence." #RSMedals
A very well deserved award!
royalsociety.org
We are happy to announce the winners of the Royal Society's medals and awards for 2025. “[They] have all made outstanding contributions to science and its applications for the benefit of humanity." said Sir Adrian Smith PRS. Meet the winners: #RSMedals royalsociety.org/news/2025/08...
Invisibility cloak pioneer Sir John Pendry awarded Royal Society’s top prize | Royal Society
The Royal Society announces the medals and awards recipients 2025
royalsociety.org
graemeday.bsky.social
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.
graemeday.bsky.social
If you're at the 25th European crystallographic meeting in Poznan, I'll recommend MS43 – "Simulating and predicting structure" at 14:00 on Wed.

Pedro Juan Royo from our group will be presenting on our methods for mapping the interconnectivity of predicted crystal structures.
#CompChemSky #ChemSky
Graph showing the connections between crystal structures as a function of increasing energy. Each connection is represented as a node connecting lines from initial starting structures.
graemeday.bsky.social
Congratulations Dr @jennieemartin.bsky.social on an excellent PhD.
Phd candidate stood smiling with two examiners.
graemeday.bsky.social
Thanks for the comments!
graemeday.bsky.social
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
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
graemeday.bsky.social
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
graemeday.bsky.social
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
graemeday.bsky.social
Attending the @rsc.org International conference on materials chemistry #MC17, like organic materials and structure prediction? Then check these out from our team: #Chemsky #CompChemsky

1/4
graemeday.bsky.social
Not the prettiest, but the taste turned out pretty good. Hot, but good.
Two jam jars full of red currant jam.
graemeday.bsky.social
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.
graemeday.bsky.social
Did #chemistswhocook make its way to bluesky from that other place? #chemsky
A bowl of red currant next to a chopping a board with a knife and lots of chili peppers.
graemeday.bsky.social
On my way home after a day visiting the Warwick Centre for Predictive Modelling. Thanks for the invitation to speak and for the many interesting meetings.
#compchemsky
View from a train window looking out onto fields.
graemeday.bsky.social
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.
Figure showing correlation plots of MCRT predictions vs actual values for a range of properties: lattice energies, methane capacity, methane diffusivity, charge mobility and bulk modulus. The correlation is good in all cases. Errors and correlation coefficients are shown in the figure.
graemeday.bsky.social
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.
Figure showing the tasks involved in pre-training of the MCRT foundation model: masked atom prediction, atom pair classification, crystal density prediction and symmetry element prediction.
graemeday.bsky.social
Now published in @chemicalscience.rsc.org and highlighted as a #ChemSciPicks. Great work by @ffmmgg.bsky.social. Collab with @aicooper.bsky.social

A Universal Foundation Model for Transfer Learning in Molecular Crystals

#compchemsky #chemsky
@unisouthampton.bsky.social @liverpooluni.bsky.social
chemicalscience.rsc.org
This week's #ChemSciPicks comes from @graemeday.bsky.social (University of Southampton), @ffmmgg.bsky.social‬, Chengxi Zhao‬, Xenphon Evangelopoulos, and @aicooper.bsky.social‬ (University of Liverpool).

Read the full paper here: doi.org/10.1039/D5SC...

#ChemSky
graemeday.bsky.social
Have a look through our most popular 2024 papers in Chemical Science in Physical, Computational & Theoretical Chem. #chemsky #compchemsky

and it's all Open Access.
chemicalscience.rsc.org
Our #ChemSciMostPopular collection for work in Physical, Computational & Theoretical Chemistry is now available online!

The collection, like all papers published in the journal, is entirely free to read:
pubs.rsc.org/en/jour...

Check out some of these 🔥HOT🔥 articles:
A promotional slide for the Chemical Science themed collection on most popular work in the area of physical, theoretical and computational chemistry from 2024
Reposted by Graeme Day
aicooper.bsky.social
Alchemy Frontier Fund 2025 now open (aichemy.ac.uk/aichemy-fron...). Apply for 2-year projects of up to £1.25m to advance the frontiers of AI for chemistry. Deadline = Sept 12th 2025. Webinar to launch the fund on June 18th. For information, email: [email protected] @ukri.org #EPSRC #AI
graemeday.bsky.social
Congratulations Josh Dickman for passing his PhD today and thank you to @marwinsegler.bsky.social for examining the thesis. #compchemsky
@unisouthampton.bsky.social
Photo of PhD student and examiner, standing in front of a whiteboard.