Tim (@timt1630) profile picture

Tim

@timt1630
Joined June 2020
  • Tweets23
  • Following50
  • Followers29
Antibody discovery workflow, streamlined: CDR annotation, germline calls, and liability flags, clustering by sequence similarity, and developability and activity scoring, all in one dataset. Sign up link in the comments!
2
2
4
350
PSA to check if your health insurance gives gym membership rebates. It probably does! Use an AI assistant to check quickly, then verify on the plan site.
1
2
213
🚨ICML Paper Alert🚨 What if finding the right protein homologs wasn't a slow search, but a learned part of the model itself? We introduce 𝐏𝐫𝐨𝐭𝐫𝐢𝐞𝐯𝐞𝐫, an end-to-end framework that learns to retrieve the most useful homologs for self-supervised reconstruction! (1/12)
Image from Ruben Weitzman (@ruben_weitzman)
5
20
4
99
16,809
🧬 Announcing PoET-2: A breakthrough protein language model that achieves trillion-parameter performance with just 182M parameters, transforming our ability to understand proteins.
Image from OpenProtein.AI (@openprotein)
1
9
21
1,592
Excited to share PoET-2, our next breakthrough in protein language modeling. It represents a fundamental shift in how AI learns from evolutionary sequences. 🧵 1/13
1
38
5
204
29,149
Turns out PoET embeddings are powerful for protein representation learning, especially with small mutagenesis datasets. With PoET, we match the performance of ProteinNPT with 15x less data! 1/4
Image from tbepler (@tbepler1)
2
4
38
4,257
✒️PoET is our generative protein language model for controllable sequence generation, zero-shot protein mutagenesis & clinical variant effect prediction. ⚡️Unparalleled accuracy, speed, & generalizability 🧬Learn more in our latest blog post: openprotein.ai/poet-a-high-p…
PoET: A High-Performing Protein Language Model for Zero-Shot Prediction | OpenProtein.AI

PoET: A High-Performing Protein Language Model for Zero-Shot Prediction | OpenProtein.AI

PoET, our new generative protein language model, can controllably generate protein sequences de novo, and make zero-shot variant effect predictions for protein engineering and clinical variant...

openprotein.ai
4
11
676
In a new blogpost for @openprotein, @TimT51 and I dive into some new results for PoET. Turns out PoET reaches perplexities on heldout UniRef50 sequences that would require 500 billion parameters with a typical masked protein language model! 🤯 openprotein.ai/poet-a-high-p…
Image from tbepler (@tbepler1)
4
13
5
64
8,364
👑New model topping the ProteinGym leaderboard👑 Congrats to the SaProt team! @duguyuan @LTEnjoy Exciting to see the progress happening at the intersection of protein sequence & structure modeling.
Image from Pascal Notin (@NotinPascal)
1
8
1
55
6,621
It's remarkable how much functional and structural information is captured by protein language models, despite being trained only on sequences. @curcuas and I dive into this in a new blog post for @openprotein. More to come! openprotein.ai/learning-the-…

Learning the Grammar of Biology: Why Protein Machine Learning Works | OpenProtein.AI

Machine Learning models have transformed our understanding of protein structure and function, predicting complex biophysical properties from sequence alone and generating novel sequences with desired...

openprotein.ai
10
1
48
2,984
Excited to announce PoET, our (@timt1630, @tbepler1) retrieval-augmented generative protein language model that achieves state-of-the-art unsupervised variant function prediction performance on #ProteinGym. #MachineLearning #ProteinML 1/9 arxiv.org/abs/2306.06156
Image from tbepler (@tbepler1)
1
31
1
117
16,807
Load more