ginaelnesr.bsky.social
stanford phd • nsf grfp fellow • deep learning for protein design • oly weightlifter 🏋🏽♀️• 🇪🇬
gelnesr.github.io
17 posts
1,122 followers
178 following
Prolific Poster
Conversation Starter
comment in response to
post
Upon further experimentation, this approach is mostly garbage for larger proteins
comment in response to
post
First off: a great primer and motivation for the workshop by @ginaelnesr.bsky.social !! Amazing to recognize all the researchers (both computational and even experimentalists) that have made the nobel-winning work of AF2 possible!
comment in response to
post
+1 here - as organizers, we also wished they were either nearby or separate days!! Luckily there is also a live stream online, so hopefully that helps mitigate it a bit
comment in response to
post
Stoked to see this out and to listen to the talk at @workshopmlsb.bsky.social this weekend!!
comment in response to
post
This is super exciting. I'm curious, what was the longest timescale used for any individual MD, and perhaps what does that data distribution of time scale vs. protein (frequency / size) look like?
comment in response to
post
This is sooooo cool!!!
comment in response to
post
I’d be sooo curious to see if they also have high melting temperatures 🤔
comment in response to
post
Also, the fact that mean pooling works so well (compared to other methods) indicates to me that we are definitely not getting the most out of these models (compared to what we know about how protein sequence relates to protein function/properties)
comment in response to
post
Wonderful animation. Just note that the typical (20 conformer) NMR "ensemble" deposited in the PDB does generally not reflect the dynamics of the molecule, but rather the uncertainty of the determined structure (with a few exceptions such as PDB ID 1XQQ)
comment in response to
post
Congrats!!! 🎉
comment in response to
post
No! This is a separate, peer-reviewed submission process. All MLSB submissions will be published on mlsb.io as in previous years.
comment in response to
post
And big-lab-group-think is a stifling influence. Last month I gave a talk at a local big pharma site and the director/host literally asked me “if [insert three big names of field] haven’t already thought of the idea you presented, how could it possibly be true/important?”
comment in response to
post
🙋🏽♀️🙋🏽♀️
comment in response to
post
Would love to be on it!