Sign in

Liwei Chang

@liweichang.bsky.social
59 followers 155 following 10 posts

Interested in molecules, small and large.

PostsRepliesMedia
Liwei Chang @liweichang.bsky.social · 09/01/2026
That’s an easy one to reach agreement on;) If I can add more, they also trained on distributions simulated at melting temperatures but try to predict room temperature conformations.
010
Liwei Chang @liweichang.bsky.social · 08/01/2026
Alanine dipeptide should be updated to fast folding proteins at this point in time.
010
Liwei Chang @liweichang.bsky.social · 14/12/2025
Sharing here as well — consider adding this to your or your fav llm’s reading list if you want a dive into 1) protein folding, 2) limitation of AlphaFold and what it learned. You could be one step closer to solve the protein folding problem. www.nature.com/articles/s41...
nature.com
Rapid estimation of protein folding pathways from sequence alone using AlphaFold2 - Nature Communications
Researchers find that AlphaFold2, despite imperfections, reveals folding intermediates and pathways, showing it has learned key folding principles.
021
Liwei Chang @liweichang.bsky.social · 04/10/2025
also faster to hit cluster center of bowls with extended similarity..
110
Liwei Chang @liweichang.bsky.social · 01/10/2025
was standing on the other side of fig. 1:)
010
Liwei Chang @liweichang.bsky.social · 01/08/2025
Similarly in predicted folding pathways, the C-termini hairpin of protein G doesn’t change structurally, but the confidence scores vary when surroundings fold closer to native.
100
Liwei Chang @liweichang.bsky.social · 01/08/2025
I think big part of what AF learned is mimicking the distance distribution of arbitrary pairwise residues/tokens in input from PDB. It changes with environment, adding more sequences affects structure predictions, and scores, which correlate well with the variance in predicted distograms.
110
Liwei Chang @liweichang.bsky.social · 01/08/2025
It was a surprise to see AF2 can predict folding pathways, but the scores keep increasing from unfolded to folded, unlike (real!) free energy map.
100
Liwei Chang @liweichang.bsky.social · 01/08/2025
That would be great! But I haven’t found strong evidence for that.. At least the confidence score doesn’t look like a good estimation for free energy from this work. www.biorxiv.org/content/10.1...
biorxiv.org
100
Liwei Chang @liweichang.bsky.social · 19/07/2025
How does ramen assemble in warming soup — the ultimate scientific challenge 🍜 - Entropy-driven noodle arrangement - Hydration kinetics - Diffusion and buoyancy activated topping sorting …
040
Reposted by Liwei Chang
Kresten Lindorff-Larsen @lindorfflarsen.bsky.social · 05/07/2025
An Evaluation of Biomolecular Energetics Learned by AlphaFold by Lyu, Herschlag et al doi.org/10.1101/2025... Interesting comparison of AF2/3 structures with the PDB (AF2 appears better) Reminder: The PDB itself is probably biased relative to solution conformational ensembles and energetics
0365
Reposted by Liwei Chang
Adrian Roitberg @adrianroitberg.bsky.social · 03/01/2025
Ever wanted to predict protein NMR chemical shifts accurately and very very fast ? Great new paper from MIkailya Darrows @mdarrows.bsky.social. chemrxiv.org/engage/chemr... Comments are welcome !
chemrxiv.org
LEGOLAS: a Machine Learning method for rapid and accurate predictions of protein NMR chemical shifts.
This work introduces LEGOLAS, a fully open source TorchANI-based neural network model designed to predict NMR chemical shifts for protein backbone atoms. LEGOLAS has been designed to be fast, and with...
23211
Reposted by Liwei Chang
Rommie Amaro @rommieamaro.bsky.social · 09/12/2024
For those following the @prof-ajay-jain.bsky.social /Cleaves/ @wpwalters.bsky.social preprint re: DiffDock @gcorso.bsky.social I have read some of the back-&-forth between the author groups As a practitioner in the field for > 20 yrs (academic side), here is my take: 🧵
24417
Reposted by Liwei Chang
Frank Noe @franknoe.bsky.social · 06/12/2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
21441147