Top Tweets for #proteinAI
Proteins are the building blocks of life, and now AI can predict their hidden patterns. ESM2-150M is a fill-mask model for protein sequences, ready to power your research. #ProteinAI #Bioinformatics

Meet ESM2-3B, a protein language model that predicts masked amino acids. With 3 billion parameters, it's a powerful tool for computational biology, and it's ready to use with transformers. #ProteinAI

Meet ESMFold2-Fast, a protein language model that turns sequences into rich features at lightning speed. Built for feature extraction, it's your shortcut to protein AI without the heavy lifting. #ProteinAI #Bioinformatics

Prot-LAMBDA: a protein language model taught to reason in 3D, reportedly matching one 5x its size. Efficiency over scale. Read the breakdown. #ProteinAI #ESMFold #CompBio
https://t.co/ie3yXB1Z1B
A new way to derive protein conformational diversity (looks very competitive or even beating other methods) rapidly from @m1nj12 in @MoAlQuraishi group #proteinai #ai
We introduce ConforNets, a mechanism for conformational control in AlphaFold3 models
- SoTA at producing diverse conformations on every multistate benchmark (N=104)
- Novel capability: transfer state from one protein to another
Outperforms BioEmu, ConforMix and AFsample3
🧵1/8
Meta's ESMFold predicts protein structures in SECONDS — no MSA needed.
AlphaFold 2 takes hours.
The trick? A 15B-param language model (ESM-2) trained on 65M protein sequences learns evolutionary patterns implicitly through masked prediction.
#ProteinAI #LLM

The 2024 Nobel Prize in Chemistry went to AI researchers.
AlphaFold 2 went from conference paper to Nobel in just 3 years — the fastest recognition in modern history.
The architectures? Standard ML: transformers, diffusion models, GNNs.
#ProteinAI #AlphaFold #NobelPrize

EvolutionaryScale trained its ESM3 model on 2.78B proteins - an enormous compute challenge. With distributed cloud supercomputing and utilizing idle cloud GPUs, models can train faster while saving hundreds of thousands in costs.
#SparkAI #ProteinAI #AIBiology

Quasi‑single methods live or die by their reference set.
When StrMQA’s DMFold references captured the wrong conformation, it ranked a poor model first (TM‑score 0.377) while the best was 0.979, and correlation turned negative (single point of failure).
#CASP16 #ProteinAI

🔥 The protein Model‑Selection Era is here.
MViewEMA learns micro→macro cues to rank any complex (no MSA, template or embedding)
📈 CASP16: Pearson 0.54, best of all single‑model EMAs,⚡️ 23 s/model, 10 × faster than DeepUMQA3 (CPU) #ProteinAI #CASP16

I think Protein Hallucination is a good name for a street wear brand in 2030.
#proteindesign #proteinAI #biomaterials #alphafold

@MoAlQuraishi Congrats! I took the liberty of QT'ing you on to @joinmastodon FYI #biotech #proteinai #alphafold
Openfold preprint is up! Beautiful training analysis shows lots can be done with short training and less data, surprising to many #biotech #proteinai #ai
Our preprint on OpenFold, our trainable reproduction of AlphaFold2, is finally up (https://t.co/3EoTzE3Xdb)! Since we open-sourced parameters in June, we've trained the model to high accuracy more than 50 times, on a variety of datasets. Here's what we learned (a lot) -> (1/19)
My 1st single-first-authored paper on generative protein sequence modeling published @NatureComms: https://t.co/qnujGS0G0D
Thanks to @ahalda @carnevalelab @SlobodanVuceti4 @SHauri79275203 #TempleBioinformatics #proteinAI
Last Seen Hashtags on Sotwe
วิจารณ์เสียว
Seen from Thailand
sex in school
Seen from United States
ensest(*)filter:native_video
Seen from Turkey
mgai((*))(())()((*)*()*()(*********))(*)filter:videos
Seen from United Kingdom
randomchat(())**********filter:videos
Seen from Turkey
brosis(**) filter:videos
Seen from Netherlands
ควยนักเรียน
Seen from Thailand
كحبه
minichatt
Seen from Belgium
Most Popular Users

Elon Musk 
@elonmusk
241.5M followers

Barack Obama 
@barackobama
118.8M followers

Cristiano Ronaldo 
@cristiano
114.5M followers

Donald J. Trump 
@realdonaldtrump
111.9M followers

Narendra Modi 
@narendramodi
107.1M followers

Rihanna 
@rihanna
98.7M followers

NASA 
@nasa
92.3M followers

Justin Bieber 
@justinbieber
91.8M followers

KATY PERRY 
@katyperry
90M followers

Taylor Swift 
@taylorswift13
84M followers

Lady Gaga 
@ladygaga
75.5M followers

Virat Kohli 
@imvkohli
73.4M followers

Kim Kardashian 
@kimkardashian
70.8M followers

YouTube 
@youtube
68.8M followers

Neymar Jr 
@neymarjr
66.4M followers

Bill Gates 
@billgates
65.2M followers

Selena Gomez 
@selenagomez
63.1M followers

The Ellen Show
@theellenshow
62.2M followers

CNN 
@cnn
61.7M followers

X 
@x
60.7M followers









