Ivy Zhang
LightNews LightNews
ivyzhang.bsky.social
Ivy Zhang
@ivyzhang.bsky.social
100 followers 92 following 0 posts
Computational chemist l PhD from John Chodera's group @ MSKCC
Posts Replies Media Videos
Reposted by Ivy Zhang
jchodera.bsky.social
Everything is chaos, but I wanted to share some awesome recent science from the lab that hints at where the future of biomolecular simulation is headed:

Foundation simulation models that can be fine-tuned to experimental free energy data to produce systematically more accurate predictions.
Figure 1 from arXiv preprint https://doi.org/10.1101/2025.01.06.631610 Fig. 1 Espaloma is an end-to-end differentiable molecular mechanics parameter assignment scheme for arbitrary organic molecules. Espaloma (extensible surrogate potential optimized by message-passing) is a modular approach for directly computing molecular mechanics force field parameters FFF from a chemical graph G such as a small molecule or biopolymer via a process that is fully differentiable in the model parameters FNN. In Stage 1, a graph neural network is used to generate continuous latent atom embeddings describing local chemical environments from the chemical graph. In Stage 2, these atom embeddings are transformed into feature vectors that preserve appropriate symmetries for atom, bond, angle, and proper/improper torsion inference via Janossy pooling.54 In Stage 3, molecular mechanics parameters are directly predicted from these feature vectors using feed-forward neural networks. This parameter assignment process is performed once per molecular species, allowing the potential energy to be rapidly computed using standard molecular mechanics or molecular dynamics frameworks thereafter. The collection of parameters FNN describing the espaloma model can be considered as the equivalent complete specification of a traditional molecular mechanics force field such as GAFF38,39/AM1-BCC55,56 in that it encodes the equivalent of traditional typing rules, parameter assignment tables, and even partial charge models. Reproduced from ref. 49 with permission from the Royal Society of Chemistry.
February 19, 2025 at 7:30 PM
Reposted by Ivy Zhang
wpwalters.bsky.social
I'm thrilled to announce a new preprint describing collaborative work with Ajay Jain and Ann Cleves Jain, "Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows".

arxiv.org/abs/2412.02889
Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows
The diffusion learning method, DiffDock, for docking small-molecule ligands into protein binding sites was recently introduced. Results included comparisons to more conventional docking approaches, wi...
arxiv.org
December 5, 2024 at 4:21 PM
Reposted by Ivy Zhang
jchodera.bsky.social
CADD community, here's your chance to test how well your prediction models for affinity and ADMET *really* work in a real drug discovery program where all the data and protocols will be released openly!
asapdiscovery.bsky.social The ASAP Discovery Consortium @asapdiscovery.bsky.social · Dec 3
We're excited to work with @omsf.io OpenADMET and @polarishub.io to bring you this blind predictive modeling community challenge!

If you're developing predictive models for drug discovery---potency or ADMET---here's your chance to test them prospectively on real discovery data from ASAP!
polarishub.io Polaris @polarishub.io · Dec 3
🦠 We’re excited to announce our first competition in partnership with @asapdiscovery.bsky.social and @omsf.io!

Test your skills across three sub-challenges revolving around SARS-CoV-2 and MERS-CoV Mpro🧵

Full details: polarishub.io/competitions
Blog: polarishub.io/blog/antivir...
December 3, 2024 at 4:47 PM
Reposted by Ivy Zhang
sukritsingh92.bsky.social
With the help of new technician @markpolk.bsky.social, we've got our wet lab robots rapidly (and consistently) measuring kinase-inhibitor binding! Stay tuned for more:
A graph plotting a series of fluorescence spectra, each curve measuring kinase-inhibitor at a different drug concentration (the drug concentration is indicated in the color legend on the right). A dose-response curve from the full spectra, corrected for native ligand fluorescence, reporting drug binding over a series of inhibitor concentrations
December 3, 2024 at 9:42 PM