@DrorLab

The Dror Lab at Stanford. For all your computational needs: MD, ML, HPC... Applied to biochemistry, cell biology, drug discovery, and more!

 Stanford, California
drorlab.stanford.edu
Joined October 2019
  • Tweets25
  • Following17
  • Followers1.4K
3Media
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
How accurately can one predict drug binding modes using AlphaFold models? New work from our lab reveals AF2's improved accuracy in capturing binding pocket structures, but the results of docking are not a slam dunk. 💥🧐 Check out the preprint: biorxiv.org/content/10.1101/…

How accurately can one predict drug binding modes using AlphaFold models?

Computational prediction of protein structure has been pursued intensely for decades, motivated largely by the goal of using structural models for drug discovery. Recently developed machine learning...

biorxiv.org
15
64
10,787
A new paper from our lab, @MIPS_Australia, and @KarunaPharma uses atomic-level simulations to reveal a molecular mechanism by which a ligand can achieve selectivity between nearly identical receptors. Open access: nature.com/articles/s41589-0…

Structural basis of efficacy-driven ligand selectivity at GPCRs

Nature Chemical Biology - The use of atomic-level simulations reveals a molecular mechanism by which a ligand can achieve selectivity between nearly identical receptors, enabling the rational...

nature.com
16
75
6,570
Now out on the cover of @ScienceMagazine: Our work with @RDasLab on predicting 3D RNA structures! science.sciencemag.org/conte… Check out the official press release: news.stanford.edu/2021/08/26… and our earlier work on protein complexes: doi.org/10.1002/prot.26033
16
1
65
AlphaFold for RNA? Excited to share our @StanfordAILab work on deep learning for predicting 3D RNA structure, out today on the cover of @ScienceMagazine! science.sciencemag.org/conte… Sound interesting? Join us at atomic.ai to bring this work to life! More news soon!
16
363
50
1,233
Check out our latest paper exploring the effects of GPCR phosphorylation on arrestin signaling with great collaborators @MattMasureel, Kobilka lab, and @Michel_Bouvier!
1
2
14
We benchmark 3 prototypical architectures - 3D conv. networks, graph networks and equivariant networks - and compare them to 1D/2D baselines. We find that 3D info can strongly improve model performance, but it depends on the choice of architecture for a particular task. [4/4]
1
5
Machine Learning in Structural Biology (@workshopmlsb) is accepted at #NeurIPS2020! Come check out the exciting line-up of speakers and dates for the call for papers at mlsb.io (more details coming soon). Register interest at forms.gle/zLyQupP93TDqpAf39
34
2
94
Excited to present our latest work on geometric prediction: the class of prediction problems for (non-scalar) geometric tensors! We show the first real-world demonstration of geometric prediction without the need for scalar approximations. arxiv.org/abs/2006.14163 [1/n]
1
26
76
Somehow this slipped my radar. Very cool looking work from the @DrorLab: Hierarchical, rotation-equivariant neural networks to predict the structure of protein complexes. arxiv.org/abs/2006.09275
9
59
Such a method is readily applicable to other tasks involving learning on 3D structures of large atomic systems. (3/3)
2
3
Starting with just the element type of each atom, we learn features at different levels of structural coarseness and aggregate this information hierarchically. The rotation-equivariant network recognizes molecular motifs independent of their orientation. (2/3)
2
2
3
Excited to share our work on learning from the 3D structure of macromolecules! Our neural network architecture enables us to learn directly from all atoms in protein complexes containing tens of thousands of atoms: arxiv.org/abs/2006.09275 (1/3)
1
10
45
science.sciencemag.org/conte…
1
1
9
Excited to present two papers just out in Science on how to create more effective drugs with fewer side effects! science.sciencemag.org/conte…
1
14
1
54
We have 2 papers published in @nature today! 🎉 One describes AlphaFold, which uses deep neural networks to predict protein structures with high accuracy. AlphaFold made the most accurate predictions at the 2018 scientific community assessment CASP13. 1/4 deepmind.com/blog/article/Al…

AlphaFold: Using AI for scientific discovery

In our study published in Nature, we demonstrate how artificial intelligence research can drive and accelerate new scientific discoveries. We’ve built a dedicated, interdisciplinary team in hopes of...

deepmind.google
13
510
55
1,374
The rebirth of #MLCB2019 was great. Great posters and talks all around. Thanks to the organizers and everyone who came up for making it awesome. Let's make this happen every year---but with coffee during the coffee break in the future.
1
5
31
Lots of fun co-organizing the Biology @ #NeurIPS2019 meetup with @jpq79743104 last night—the level of interest in such a last-minute event was truly stunning! Thanks to all who attended!
1
1
9
Dror Lab is at #NeurIPS2019! @raphaeljlt @rishibedi @PatriciaSuriana presented our work on protein interface prediction yesterday (arxiv.org/abs/1807.01297). Come check out our poster today at noon @lmrl_bio as well!
2
21
This is a great summary of the potential of the next 10 years. It's a great time to be alive! Biology is Eating the World: A Manifesto - Andreessen Horowitz a16z.com/2019/10/28/biology-…

Biology is Eating the World: A Manifesto | Andreessen Horowitz

We are at the beginning of a new era, where biology has shifted from an empirical science to an engineering discipline. After a millennia of using man-made approaches for controlling or manipulating...

a16z.com
1
10
1
36
Hello world, the Dror Lab is on Twitter! We are excited to present our NeurIPS work on deep learning for protein interactions (arxiv.org/abs/1807.01297), including the new 100x-sized DIPS dataset. Come check out our publications (5 Nature+Cell this year) at drorlab.stanford.edu
2
16
60
Load more