Oke, the AlphaFlow paper is awesome: AlphaFold Meets Flow Matching for Generating Protein Ensembles Just watch how AlphaFlow's ensemble reproduces details of MD. Weights + code We have it in the reading group on Mon 11am EST! 1/2 Tweet added by Hannes Stärk @HannesStaerk

Hannes Stärk

4 months

Oke, the AlphaFlow paper is awesome: AlphaFold Meets Flow Matching for Generating Protein Ensembles Just watch how AlphaFlow's ensemble reproduces details of MD. Weights + code We have it in the reading group on Mon 11am EST! 1/2

15

151

762

Hannes Stärk

@HannesStaerk

4 months

Reading group link And may I solicit some expert opinions on the paper? :) @FrankNoeBerlin @jonkhler @drGregBowman @sokrypton @HWaymentSteele @fraser_lab @tangjianpku @tiwarylab @befcorreia @LindorffLarsen @PossuHuangLab @ShuiwangJi @MoAlQuraishi

Portal

Home of the TechBio community. Tune into our weekly reading groups (M2D2, LoGG, CARE), read community blogs, and join the discussion forum.

portal.valencelabs.com

1

0

7

Hannes Stärk

@HannesStaerk

4 months

More paper opinions? @GrantRotskoff @UWproteindesign @loukasa_tweet @KevinKaichuang @fra_grisoni @thesteinegger @marwinsegler @Blendenfleck @open_fold @nickpolizzi_ @inve_michele @AnimaAnandkumar @VStimper @jchodera @HeinzingerM @simonduerr @__kraemer__ @igashov @open_fold

9

0

7

Hannes Stärk

@HannesStaerk

4 months

I should also mention that my take may be a bit biased given that the paper is from my lab mate Bowen Jing, but I still feel confident in the claim 🙃

0

2

Yuanqi Du

@YuanqiD

4 months

@HannesStaerk Will Bowen talk about the details of this animation😉?

1

0

1

Hannes Stärk

@HannesStaerk

4 months

@YuanqiD For sure, whatever we ask him I suppose :) What are your questions (unless you prefer just joining on Mon and asking them only there)?

1

0

1

Frank Noe

@FrankNoeBerlin

4 months

@HannesStaerk Hey Hannes, can I sign you up to promote our papers? You're a real influencer :-)

2

0

14

Hannes Stärk

@HannesStaerk

4 months

@FrankNoeBerlin Can I see that as an offer for you to join my reading group on some Monday and present + discuss some of your work? ;)

1

0

3

Frank Noe

@FrankNoeBerlin

4 months

@HannesStaerk AlphaFlow and Distributional Graphormer are very similar for proteins. Flow matching vs diffusion, slightly different training data, but essentially the same representation and architecture. AlphaFlow is better validated and presented indeed.

1

5

Hannes Stärk

@HannesStaerk

4 months

@FrankNoeBerlin We also had Distributional Graphormer in the reading group! I suppose an important part of AlphaFlow is also training on the ATLAS dataset which was only released in Nov 2023 after Graphormer was published

Towards Predicting Equilibrium Distributions for Molecular Systems...

Valence Labs is a research engine within Recursion committed to advancing the frontier of AI in drug discovery. Learn more about our open roles: https://www....

www.youtube.com

2

1

4

Synthical

@synthical_ai

4 months

@HannesStaerk Dark mode for this paper for night readers 🌚

AlphaFold Meets Flow Matching for Generating Protein Ensembles

The biological functions of proteins often depend on dynamic structural ensembles. In this work, we develop a flow-based generative modeling approach for learning and sampling the conformational...

synthical.com

0

1

Greg Bowman

@drGregBowman

4 months

@HannesStaerk Thanks for starting this conversation. I've added the paper to my to-read list. I've been evaluating these methods as I would a new enhanced sampling algorithm. Big questions are... 1/n

2

0

4

Frank Noe

@FrankNoeBerlin

4 months

@HannesStaerk It’s a great approach 👏

0

3

Jonas Köhler

@jonkhler

4 months

@HannesStaerk Good stuff! Very nice!

0

1

Testing enthusiast

@apicoplast

4 months

@HannesStaerk @dr_alphalyrae

0

1

Xuhui Huang

@XuhuiHuangChem

4 months

@HannesStaerk It is super nice to be able to generate fluctuations similar to those in equilibrium MD simulations. I am curious whether it can predict large-scale functional conformational changes, like those demonstrated recently on KaiB by AlphaFold-2 + MSA clustering.

0

4

Jeevan GC

@jeebu9

4 months

@HannesStaerk It is great to see AlphaFold approaching Newtonian Era.

0

Chaitanya K. Joshi

@chaitjo

4 months

@HannesStaerk Eagerly waiting for the recording.

0

1

TW1989

@Tristian3133

4 months

@HannesStaerk @EMostaque Finally, some good sh*t in ny feed. Good job.

0

amelie_schreiber

@amelie_iska

4 months

@HannesStaerk Can this be done with AlphaFold-Multimer to better understand protein-protein interactions? Could be a really great next step and there are so few models that give good insight into PPIs and binding affinities. Perhaps there is some way to use ipTM scores for ensembles here?

3

0

Replies