Jo Grundy
@drjojo.bsky.social
Senior Teaching Fellow at Southampton, between computer science and chemistry.
Teaching Cheminformatics to computer scientists. Working for the PSDI.
Also a Mum, I sing Alto and Tenor, and like to run.
Teaching Cheminformatics to computer scientists. Working for the PSDI.
Also a Mum, I sing Alto and Tenor, and like to run.
Fell over and broke my fall with the back of my head while ice skating. Was trying to keep youngest child upright, he’d have been fine with a little tumble. Ended up on a trolley in AnE for about 4 hours before being sent home and told not to work, watch TV or play computer games. What do I do now?
December 15, 2024 at 2:25 PM
Fell over and broke my fall with the back of my head while ice skating. Was trying to keep youngest child upright, he’d have been fine with a little tumble. Ended up on a trolley in AnE for about 4 hours before being sent home and told not to work, watch TV or play computer games. What do I do now?
Reposted by Jo Grundy
The next installment in the history of #MerckChemistry #CompChemSky is the amazing work done by Kate Holloway on collaborative design of the HIV drug Crixivan. Not only did she use molecular modeling to contribute to the patent but she was then featured as a clue w/ Chen Zhao on Jeopardy!! #ChemSky
November 21, 2024 at 2:10 PM
The next installment in the history of #MerckChemistry #CompChemSky is the amazing work done by Kate Holloway on collaborative design of the HIV drug Crixivan. Not only did she use molecular modeling to contribute to the patent but she was then featured as a clue w/ Chen Zhao on Jeopardy!! #ChemSky
Now this is mad..
Fresh off the presses:
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
In "Learning on compressed molecular representations" Jan Weinreich and I looked into whether GZIP performed better than Neural Networks in chemical machine learning tasks. Yes, you've read that right.
TL;DR: Yes, GZIP can perform better than baseline GNNs and MLPs. It can ..
Learning on compressed molecular representations
Last year, a preprint gained notoriety, proposing that a k-nearest neighbour classifier is able to outperform large-language models using compressed text as input and normalised compression distance (...
pubs.rsc.org
November 22, 2024 at 8:27 AM
Now this is mad..