Share this page!

Sergey Ovchinnikov 🇺🇦 Profile picture
Twitter logo
Aug 4 • 5 tweets • 3 min read
Found an example from @Alexis_Verger that OmegaFold fails on (and has low confidence). But if you hack OmegaFold to use an MSA input, it gets it right (and has high confidence)!
@Alexis_Verger
@Alexis_Verger another example: a homo-tetramer that fails with OmegaFold. But if you add an MSA, it works! 🙃
@Alexis_Verger Experimental notebook, if anyone wants to try! 😎
colab.research.google.com/github/sokrypt…
Example from #joe90
(please share more examples where OmegaFold fails that AlphaFold works on) 🤓

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Sergey Ovchinnikov 🇺🇦

Sergey Ovchinnikov 🇺🇦 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @sokrypton

Sergey Ovchinnikov 🇺🇦 Profile picture
Aug 3
Seems to be working 😅
Now to test the limits on Colab!
colab.research.google.com/github/sokrypt…
In the spirit of hacking methods for what they were not trained to do. I added support for chain breaks using the residue index offset trick! 😇
Seems for single-chain proteins, 1 cycle is often enough, but for multichain proteins you more than 1.

Which I think this means the ability to predict (at least homo-oligomers) is not coming from the language model but from geoformer/structure_module?
Read 4 tweets
Sergey Ovchinnikov 🇺🇦 Profile picture
Jun 15
We've (including @thesteinegger @milot_mirdita ) updated ColabFold to use the latest optimized AlphaFold implementation that reduces compile time from ~4.5mins to ~30 seconds! We've confirmed the results are identical for both monomer and multimer predictions. Try it out! (1/2)
Here is the Pseudo-code of the changes we made and the effects on compile time. (2/2)
Rough runtime differences on mono/multi-mer predictions (on the cluster, with other jobs running) from @milot_mirdita . For a mulit-hour run (large proteins or batch-mode that avoids recompiling between preds), a few mins saved isn't much, but for interactive colab use, it is! 😅
Read 4 tweets
Sergey Ovchinnikov 🇺🇦 Profile picture
Jun 12
For my latest attempt at introducing proteins to students, I made a Google Colab Notebook that predicts proteins from a single sequence. I asked the students to tweak the sequence to get a helix or two helices or... (1/5)
colab.research.google.com/github/sokrypt…
I gave them the following cheat sheet: 😅 (2/5)
To make this practical, I had to make various tweaks to AlphaFold to make it compile as fast as possible (~10 seconds) and run as fast as possible (<1 second) and to avoid recompiling if the sequence length changes or the number of recycles changes. (3/5)
Read 10 tweets
Sergey Ovchinnikov 🇺🇦 Profile picture
Oct 24, 2021
End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman
biorxiv.org/content/10.110…
A fun collaboration with Samantha Petti, Nicholas Bhattacharya, @proteinrosh, @JustasDauparas, @countablyfinite, @keitokiddo, @srush_nlp & @pkoo562 (1/8)
Many methods like GREMLIN, MSA_transformer, RosetTTAFold and AlphaFold rely on input MSA generated by non-differentiable methods. (2/8)
We ask the question, what if we make the red arrow differentiable and optimize end-to-end. (3/8)
Read 12 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(