Dror Lab

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

[Dror Lab @DrorLab]

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:
https://t.co/eS38wMoSoF

[Dror Lab @DrorLab]

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:
https://t.co/GAB1vRGl3H

[Dror Lab @DrorLab]

Now out on the cover of @ScienceMagazine:
Our work with @RDasLab on predicting 3D RNA structures!
https://t.co/4iTjfb7G2f
Check out the official press release:
https://t.co/4Faqa0MtTC
and our earlier work on protein complexes:
https://t.co/Aua3f31Ip9

[Raphael Townshend @raphaeljlt]

AlphaFold for RNA? Excited to share our @StanfordAILab
work on deep learning for predicting 3D RNA structure, out today on the cover of @ScienceMagazine!

https://t.co/5T9rzHmRP2

Sound interesting? Join us at https://t.co/6Yv5OUqGoX to bring this work to life! More news soon!

[Dror Lab @DrorLab]

We are excited to present our work on Geometric Vector Perceptrons, an equivariant GNN architecture for residue-level protein graphs, at ICLR! Check out our spotlight talk https://t.co/gp8sD0rmIS and Github repo https://t.co/fVriL7ZD9f.

[Dror Lab @DrorLab]

@Hypat1aYu @MattMasureel @Michel_Bouvier Whoops, here we go! https://t.co/FVMM6wqifu

[Dror Lab @DrorLab]

Check out our latest paper exploring the effects of GPCR phosphorylation on arrestin signaling with great collaborators @MattMasureel, Kobilka lab, and @Michel_Bouvier!

[Dror Lab @DrorLab]

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]

[Dror Lab @DrorLab]

Looking for new challenges for machine learning in structural biology?
Check out our recent release: ATOM3D, a unified collection of diverse benchmark datasets for biological problems that deal with atom coordinates in 3D space. ⚛️⚛️⚛️
https://t.co/kmf9lVo1rq [1/4]

[Dror Lab @DrorLab]

The corresponding code to load, filter, and split the ATOM3D datasets is maintained on @github: https://t.co/9Ko3mylkYN.
We hope this lowers the entry barrier for algorithm developers and promotes 3D atomic data as a “machine learning datatype” in its own right. [3/4]

[Raphael Townshend @raphaeljlt]

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 https://t.co/blpB8vVz2M (more details coming soon). Register interest at https://t.co/1Cv0UGB12l

[Raphael Townshend @raphaeljlt]

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. https://t.co/fwUD01NowW [1/n]

[Mohammed AlQuraishi @MoAlQuraishi]

Somehow this slipped my radar. Very cool looking work from the @DrorLab: Hierarchical, rotation-equivariant neural networks to predict the structure of protein complexes. https://t.co/Wi97CFMMv8

[Dror Lab @DrorLab]

Such a method is readily applicable to other tasks involving learning on 3D structures of large atomic systems. (3/3)

[Dror Lab @DrorLab]

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: https://t.co/LkGNkEIIMH (1/3)

[Dror Lab @DrorLab]

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)

[Dror Lab @DrorLab]

https://t.co/Fp7DAkIDXl

[Dror Lab @DrorLab]

Excited to present two papers just out in Science on how to create more effective drugs with fewer side effects!

https://t.co/Qc63Kab3n0

[Google DeepMind @GoogleDeepMind]

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 https://t.co/TW1zZypsUT