Xiaoguang Xue @cygx1xue

Structural immunology • Opinions are my own Utrecht, The Netherlands Joined April 2015

Tweets

825
Followers

275
Following

1K
Likes

3K

Namrata Anand @namrata_anand2

2 months ago

New features available now on our protein GenAI platform DiffuseSandbox! scFv design with DSG2-mini is now live. We’ve also made open-source models RFAntibody + pMPNN available. diffusesandbox.com 1/

2 37 220 15K 111

Download Image

Daniel Hurdiss @DanielHurdiss

2 months ago

Microfluidics combined with electron microscopy for rapid and high-throughput mapping of antibody–viral glycoprotein complexes nature.com/articles/s4155…

0 20 84 6K 32

Dr.Wang @HotmailfromSH

6 months ago

悲观者永远正确，乐观者永远前行！其实，你一直在寻找的奇迹就隐藏在你一直逃避的行动里...

40 451 2K 574K 747

Download Image

Joost Snijder @joostsnijder

6 months ago

Excited to be giving this webinar soon. Hope to see you then!

1 7 27 889 5

Download Image

Eric Topol @EricTopol

6 months ago

Today marks the beginning of OpenRxiv, which replaces bioRxiv and medRxiv, the world's largest preprint platform for life and medical science @openrxiv

20 509 2K 173K 264

Download Image

Biotech is far too political and entrenched in managerial culture - a combination of its influence and overlap with academic biology, the speed/expense of trying new ideas and who controls the money. Startup executives and founders often sit on the board of many companies,…

12 26 229 35K 109

nature @Nature

10 months ago

Tools such as Rosetta and AlphaFold have redefined the protein-engineering landscape. But some problems remain out of reach — for now go.nature.com/3YT7zgN

3 132 418 39K 149

The Clevers Lab @TheCleversLab

12 months ago

One bacterial protein as a complement to #Matrigel/#BME: The #integrin -binding domain of the Yersinia bacterial protein Invasin, coated as a single protein, maintains a defined long-term culture of various epithelial cells as “2D #organoid sheets”. biorxiv.org/content/10.110…

0 15 47 4K 10

Download Video

Debora Marks @deboramarks

a year ago

@pranamanam You might find this ‘old’ paper interesting cell.com/cell/pdf/S0092…

1 7 31 3K 22

Download Image

Pranam Chatterjee @pranamanam

12 months ago

A beautiful thread from @rohitsingh8080!! 🧵 It really captures my feelings/frustration about current "trends" in protein design. As Rohit mentioned, the aftermath of sequencing the human genome has been a huge huge disappointment. Genomics has really not lived up to the hype,…

Rohit Singh @rohitsingh8080

12 months ago

9 70 427 116K 501

17 38 288 78K 251

Rohit Singh @rohitsingh8080

12 months ago

Let me tell you a story. It'll end up at the current tech-bio and protein design scene. But the story starts about 25 years earlier. Did you know that, commercially, the human genome project precipitated the end and not the start of a genomics boom? 1/

9 70 427 116K 501

owl @owl_posting

12 months ago

o1-preview is decent at protein folding, roughly matching ESMFold. not great, still room for improvement, but cool nonetheless. funny that OpenAI refuses to pay for pymol and is running the trial version

18 33 450 134K 157

Download Image

Biology+AI Daily @BiologyAIDaily

12 months ago

Massive sampling strategy for antibody-antigen targets in CAPRI Round 55 with MassiveFold - This paper presents a massive sampling strategy using the AlphaFold2-based tool, MassiveFold, for predicting antibody-antigen targets in the CAPRI Round 55 competition. Over 6,000…

0 7 19 2K 20

Download Image

Shreyansh Singh @shreyansh_26

a year ago

FlexAttention is a game-changer! 🔥 I was revisiting the Longformer paper, and I decided to implement its attention patterns using FlexAttention. Tested it out and it’s faster than F.sdpa/xFormers with masking and even FlashAttention-2 (full/causal) for both the forward and…

3 37 370 43K 287

Download Image

Marcel Müller @MrclMllr

12 months ago

"Mindless molecules" are making a comeback! 🚀 We’ve launched a fresh SotA Python implementation inspired by the original 2009 paper. In our minds, essential molecule data points for building truly transferable SQM or MLFF models! 🔬📊 github.com/grimme-lab/Min…

7 20 102 7K 46

Download Image

Diego del Alamo @DdelAlamo

a year ago

Another group has more or less reproduced AF3, but has built in a way to add spatial constraints for PPI prediction. These constraints lead to huge increases in fraction of models that are correct-ish, without changing fraction that is high-accuracy chaiassets.com/chai-1/paper/t…

2 35 176 12K 73

Download Image

Diego del Alamo @DdelAlamo

a year ago

Diffold, which uses AF2 fine-tuned w diffusion to sample multiple protein conformations, got renamed to UFConf and performs about as well as AlphaFlow and much better than AF-cluster, MSA subsampling, etc biorxiv.org/content/10.110…

3 31 132 11K 84

Download Image

Google DeepMind @GoogleDeepMind

a year ago

We’re presenting AlphaProteo: an AI system for designing novel proteins that bind more successfully to target molecules. 🧬 It could help scientists better understand how biological systems function, save time in research, advance drug design and more. 🧵 dpmd.ai/3XuMqbX

69 814 3K 1.1M 669

Download Gif

Arda Göreci @ArdaGoreci

a year ago

🚀Excited to announce: Open-source AlphaFold3 implementation! 🚀 I am thrilled to announce one of the models we have been building for the last 8-weeks at Ligo - an open-source implementation of DeepMind’s frontier model, AlphaFold3! Here’s what we have learned, a thread (1/11):

33 372 2K 340K 849

Download Video

Alex Naka @gottapatchemall

a year ago

1/ I did my own little hackathon last weekend designing EGFR binders for @adaptyvbio's protein design competition. I was really excited to see that my submissions took the top 10 spots in the virtual scoring phase! I got some DMs asking about my process so here's a thread: