Patrick Bryant
@Patrick18287926
Followers
1K
Following
509
Statuses
371
Dedicated scientist.
Stockholm, Sweden
Joined November 2020
@NaefLuca There is no information that can distinguish effectively between atomic interactions so what can even be learned here (regardless of algorithm)?
0
0
0
RT @NaefLuca: “I feel like they always talk about [...] we don’t have enough data [...] You do have enough data — if you were innovative en…
0
32
0
We are going through applications as they come in - apply now! We will expand the wet lab work significantly with this and other positions. We also have some new cool software on the way. Come join us:
I'm hiring a new postdoc in protein design (wet lab) at Stockholm University/SciLifeLab. The work will focus on expanding our work on binder design and using new AI models that we are developing. Apply here:
1
14
64
RT @marklundem: Our work using thermodynamic principles to link in vitro TF affinities and kinetics to single-molecule chromatin states in…
0
22
0
I'm hiring a new postdoc in protein design (wet lab) at Stockholm University/SciLifeLab. The work will focus on expanding our work on binder design and using new AI models that we are developing. Apply here:
2
45
201
We also do wet lab to validate an interesting immune evasive mechanism - check it out
0
0
4
RT @BiologyAIDaily: AI-first Structural Identification of Pathogenic Protein Targets 1. The study uses AlphaFold-based structure predict…
0
14
0
RT @MoreheadAlex: Excited to release FlowDock, an all-atom flow matching model for generative protein-ligand docking and affinity predictio…
0
15
0
RT @Stockholm_Uni: John Jumper, one of this year´s Nobel laureates in chemistry, visited Stockholm University on 11 December for a lecture…
0
3
0
🤣
Some words of wisdom from this year's chemistry laureate David Baker, whose work has made it possible to design new proteins from scratch. Read more and join us on tomorrow 8 December to hear his Nobel Prize lecture:
1
0
18
RT @FrankNoeBerlin: Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equili…
0
195
0
0
0
0
RT @alexrives: Information about protein structure in ESM C representations improves predictably with increasing training compute, demonstr…
0
6
0
This is great 👍 Now we only need a proper benchmark to see that none of these models actually work.
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with @jeremyWohlwend, @pas_saro and an amazing team at MIT and Genesis Therapeutics. A thread!
5
16
215
@chembioBryan @GonzaParra_ I second this. Blind w/o coevolution. However, coevolution can be predicted. It may be that tour binders don't make sense in an evolutionary context. PS. It is hard to know where the seqs end here: (write in e.g. fasta instead)
1
0
1
0
0
0