Michael Jendrusch

260 posts

Michael Jendrusch banner
Michael Jendrusch

Michael Jendrusch

@majendrusch

Confused synthetic biologist, math & machine learning person at EMBL (Korbel Group). Dabbling in category theory. (he/him)

Katılım Aralık 2017
203 Takip Edilen173 Takipçiler
Michael Jendrusch retweetledi
Mohammed AlQuraishi
Mohammed AlQuraishi@MoAlQuraishi·
Introducing Genie 2, our latest protein design model! Genie 2 sets a new state of the art on key design metrics and supports motif scaffolding, including that of multiple motifs with undefined geometric relationships, a feature new to protein diffusion models. (1/5)
GIF
English
5
126
593
78K
Michael Jendrusch retweetledi
Pushmeet Kohli
Pushmeet Kohli@pushmeet·
We love the excitement & results from the community on AlphaFold 3 and are doubling the AF Server daily job limit to 20. Happy to also share that we're working on releasing the AF3 model (incl weights) for academic use, which doesn’t depend on our research infra, within 6 months.
English
27
186
892
374.2K
Michael Jendrusch retweetledi
Catherine
Catherine@whitequark·
I finally did it!!! a complete FPGA toolchain (synthesis, placement, routing, and programming) running entirely in the browser
English
52
333
2.5K
228.4K
Michael Jendrusch retweetledi
Giovanni Luca Marchetti
Giovanni Luca Marchetti@giovannimarchet·
Glad to announce our new preprint with C. Hillar, D. Kragic, and @naturecomputes ! arxiv.org/abs/2312.08550 We show via group theory how Fourier features emerge in invariant neural networks -- a step towards a mathematical understanding of representational universality. 🧵1/n
English
8
118
562
135.5K
Michael Jendrusch retweetledi
Adam Tauman Kalai
Adam Tauman Kalai@adamfungi·
This new paper with Santosh Vempala gives a simple statistical justification for why and when Language Models *should* hallucinate using standard pretraining, even under ideal in-distribution training conditions. [1/7] arxiv.org/abs/2311.14648
English
18
81
552
149.6K
Michael Jendrusch retweetledi
Chang Liu
Chang Liu@chang_c_liu·
In this work, we bring OrthoRep’s mutation rate up to 10^-4 substitutions per base, allowing us to durably hypermutate and evolve chosen genes in vivo at 1-million times the genomic mutation rate of the host yeast cell. What does this afford? biorxiv.org/content/10.110…
English
4
47
197
92.7K
Michael Jendrusch retweetledi
Andrew Beam
Andrew Beam@AndrewLBeam·
1/n: We are excited to share that our paper on Chroma, a general purpose diffusion model for proteins, is out today in @Nature! nature.com/articles/s4158… A couple of my favorite highlights in the 🧵below 👇
English
13
292
1.3K
362.1K
Michael Jendrusch retweetledi
Generate:Biomedicines
Generate:Biomedicines@generate_biomed·
Today we release Chroma, our generative model for protein design, open-source on Github with a Nature publication describing its biophysical and crystallographic validation. Chroma Conditioners enable one model to target multiple protein design objectives. generatebiomedicines.com/chroma
English
2
71
258
68.2K
Michael Jendrusch retweetledi
Oane Gros
Oane Gros@GrosOane·
Are you looking to make your microscopy images pop? I've been working on an add-on to make loading tifs in @Blender more accessible! With tif2blender, 3D animations of z-stacks are hopefully easier to make in open-source format.🌈 Try it at: github.com/oanegros/tif2b…
Oane Gros tweet media
English
7
116
532
56.8K
Michael Jendrusch retweetledi
Dari Kimanius
Dari Kimanius@kimanius·
Super excited to present #Blush and with it expand the applicability of cryo-EM. We reconstruct one of the smallest complexes ever with cryo-EM. A 40 kDa protein-RNA complex. biorxiv.org/content/10.110… But how do we make sure we’re not overfitting? 🧵1/4
Dari Kimanius tweet media
English
6
82
348
33K
Michael Jendrusch retweetledi
Jason Yim
Jason Yim@json_yim·
Sharing an early preprint of my Microsoft AI4Science summer internship project. We developed SE(3) flow matching for protein backbone generation. Compared to SE(3) diffusion, we find our method achieves higher designability, faster sampling, with a way simpler implementation. 1/8
GIF
English
6
112
626
94.6K
Michael Jendrusch retweetledi
Rohith Krishna
Rohith Krishna@r_krishna3·
Very excited to share RoseTTAFold All-Atom and RFdiffusion All-Atom, methods for structure prediction and design of biomolecular assemblies! biorxiv.org/content/10.110… 1/n
Rohith Krishna tweet media
English
10
165
571
182.8K
Michael Jendrusch retweetledi
Sergey Ovchinnikov
Sergey Ovchinnikov@sokrypton·
RoseTTAFold updated to be All-Atom... biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications ... and diffusion🤯biorxiv.org/content/10.110…
Sergey Ovchinnikov tweet media
English
7
229
817
142.5K
Michael Jendrusch retweetledi
Gustaf Ahdritz
Gustaf Ahdritz@gahdritz·
We've added a lot more MSAs to OpenProteinSet since the original release last year and so we wrote up a standalone manuscript. To our knowledge, it's the largest and most accurate database of MSAs in the open. arxiv.org/abs/2308.05326
English
2
24
102
11.5K
Michael Jendrusch retweetledi
sk
sk@compchemm·
Exciting news for the molecular dynamics community! 🧬 The Molecular Dynamics Data Bank aka MDDB is going to launch. 🚀 Here's what you need to know about this new European repository for molecular dynamics simulations data👇 #structuralbiology #moleculardynaimcs #drugdesign
sk tweet media
English
3
83
287
28.8K
Michael Jendrusch retweetledi
Andrew York
Andrew York@AndrewGYork·
We discovered a surprisingly easy way to control the brightness of fluorescent proteins via magnetic fields: andrewgyork.github.io/gfp_magnetoflu… This raises fascinating scientific questions about the mechanism, and tantalizing technological opportunities for bioengineering.
GIF
English
45
307
1.3K
230.6K