Physics-based design of efficient Kemp eliminases
@lynnkamerlin.bsky.social
www.nature.com/articles/s41...
@zacharywu.bsky.social
Researcher at Google DeepMind. Previously Arnold group at Caltech. Making useful molecules!
Physics-based design of efficient Kemp eliminases
@lynnkamerlin.bsky.social
www.nature.com/articles/s41...
The White House website has been wiped clean, but thanks to @erichorvitz.bsky.social , all the Biden #PCAST reports are available below. I want to thank the #PCAST members, all of whom donated their time and expertise to helping policy be science-based. tinyurl.com/2acnv2nh
20.01.2025 22:53 โ ๐ 95 ๐ 25 ๐ฌ 3 ๐ 5Fun read, even though I was too engrossed and ended up getting lost in the office
19.12.2024 18:07 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0In-context genomic modeling and design with Evo.
120 billion base pairs of AI-generated genomic sequences with SynGenome.
Evo generates functional anti-CRISPR proteins with no homology to known proteins.
Evo generates functional toxin-antitoxin protein-protein interactions with remote homology to nature.
A protein's position in the genome in relation to other genes is informative about function, so a genomic language model can be prompted to generate
- toxin/antitoxin pairs
- anti-CRISPR proteins
+ a database of 120B synthetic base pairs
www.biorxiv.org/content/10.1...
@brianhie.bsky.social
Protein language models excel at generating functional yet remarkably diverse artificial sequences.
They however fail to naturally sample rare datapoints, like very high activities.
In our new preprint, we show that RL can solve this without the need for additional data:
arxiv.org/abs/2412.12979
Here's Veo 2, the latest version of our video generation model, as well as a substantial upgrade for Imagen 3 ๐งโ๐ณ๐ข
(Did I mention we are hiring on the Generative Media team, btw ๐)
blog.google/technology/g...
I recently made a new twitter account to reserve a username. The baseline feed is quite scary and a good push ๐ฌ
13.12.2024 23:17 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0*and congrats!!
13.12.2024 19:07 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0Looks like the focus is on small molecule chemical hazards? Or will macromolecule hazards also be of interest?
13.12.2024 19:06 โ ๐ 0 ๐ 0 ๐ฌ 2 ๐ 0Famous? The description made it seem like one of many ๐
13.12.2024 19:03 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0new preprint on chemical synthesis ML models
- showing how to combine multiple models in a principled way
- modern Transformers + GNN to featurize chemical reaction:
- new insights in where the models shine
+ bonus: find the quirky named reaction!
Feedback welcome!
arxiv.org/abs/2412.05269
overview of results for PLAID!
1/๐งฌ Excited to share PLAID, our new approach for co-generating sequence and all-atom protein structures by sampling from the latent space of ESMFold. This requires only sequences during training, which unlocks more data and annotations:
bit.ly/plaid-proteins
๐งต
Lots coming for protein design!
08.12.2024 10:33 โ ๐ 4 ๐ 1 ๐ฌ 0 ๐ 0Introducing Biomolecular Emulator (BioEmu). We build on AlphaFold evoformer representation of protein sequence, then sample 3D structures from equilibrium ensemble with diffusion model. From this sample, we can compute states, probabilities and understand mechanisms.
06.12.2024 08:38 โ ๐ 29 ๐ 4 ๐ฌ 1 ๐ 0Can a single small molecule rescue the stability of nearly all mutations in a protein?
Our new preprint by Taylor Mighell
www.biorxiv.org/content/10.1...
thread on the other place: x.com/taylor_mighe...
This blog post by @drscotthawley.bsky.social provides a very accessible overview of flow matching / rectified flow and reflow, based on intuitions from physics, rather than starting from probability distributions. The visualisations and animations are excellent, and the whole thing is also a colab!
15.11.2024 20:31 โ ๐ 79 ๐ 15 ๐ฌ 1 ๐ 1We also have an opening in Materials! Reminder: our London Wetlab position application closes Wednesday
25.11.2024 17:25 โ ๐ 5 ๐ 0 ๐ฌ 0 ๐ 0Discovery of a biodegradable, fully recyclable plastic
www.science.org/doi/10.1126/...
Figure 1: RFpeptides is a diffusion-based pipeline for the de novo design of protein-binding macrocycles.
RFdiffusion for macrocycles www.biorxiv.org/content/10.1...
20.11.2024 18:48 โ ๐ 60 ๐ 8 ๐ฌ 1 ๐ 0Come join our London wet-lab team! Deadline to apply is next Wednesday boards.greenhouse.io/deepmind/job...
18.11.2024 15:47 โ ๐ 1 ๐ 1 ๐ฌ 0 ๐ 0