Hi everybody,
As one of the persons playing with the CASP14 data before all news came
out, I can answer some of the questions raised in this thread.
- "Does anyone know how AlphaFold performs on sequences with little
conservation?"
One of the things we looked at was how the accuracy of the models was
dependent on the Neff (number of effective sequences, relates to how
deep alignments are for that sequence and, thus, to the number of
homologs and the conservation of the sequence). What we could see is
that, basically, in CASP14 it does not anymore and that (near-)singleton
sequences could be modeled with a pretty good accuracy.
- "It would be interesting to know how it performs with structures of
new or uncertain fold."
It does pretty well! Similarly to the Neff relationship, we also see a
basically flat line at a GDT of 70-80 at any level of target difficulty.
Of course the accuracy is slightly higher for easy targets (those for
which there are templates in the PDB), but to have a GDT of around 70 in
Free-Modelling, hard targets, is quite impressive.
- "I don't think they have all the side chain placement so perfect as to
be able to predict the fold _and_ how a compound or another protein binds"
Yap, sidechains remain the poorest modeled parts. Still, those modeled
by AlphaFold were the closest to the "reality" of the target...
- "I'm curious how well AlphaFold would do on an*Intrinsically
Disordered Protein (IDP)*"
Oh yes, that is a super good point and I have been thinking about it
too. Maybe one should start throwing some IDPs into CASP too :) There's
the CAID experiment but, on its current state, AlphaFold would not be
possible to test.
Best wishes
Joana
---
Dr. Joana Pereira
Postdoctoral Researcher
Department of Protein Evolution
Max Planck Institute for Developmental Biology
Max-Planck-Ring 5
72076 Tübingen
GERMANY
On 03.12.20 23:46, Reza Khayat wrote:
Does anyone know how AlphaFold performs on sequences with little
conservation? Virus and phage proteins are like this. Their structures
are homologous, but sequence identity can be less than 10%.
Reza
Reza Khayat, PhD
Associate Professor
City College of New York
Department of Chemistry and Biochemistry
New York, NY 10031
------------------------------------------------------------------------
*From:* CCP4 bulletin board <CCP4BB@JISCMAIL.AC.UK> on behalf of
Anastassis Perrakis <a.perra...@nki.nl>
*Sent:* Thursday, December 3, 2020 5:31 PM
*To:* CCP4BB@JISCMAIL.AC.UK
*Subject:* [EXTERNAL] Re: [ccp4bb] AlphaFold: more thinking and less
pipetting (?)
AlphaFold - or similar ideas that will surface up sooner or later -
will beyond doubt have major impact. The accuracy it demonstrated
compared to others is excellent.
“Our” target (T1068) that was not solvable by MR with the homologous
search structure or a homology model (it was phased with Archimboldo,
rather easily), is easily solvable with the AlphaFold model as a
search model. In PHASER I get Rotation Z-score 17.9, translation
Z-score 26.0, using defaults.
imho what remains to be seen is:
a. how and when will a prediction server be available?
b. even if training needs computing that will surely unaccessible to
most, will there be code that can be installed in a “reasonable”
number of GPUs and how fast will it be?
c. how do model quality metrics (that do not compared with the known
answer) correlate with the expected RMSD? AlphaFold, no matter how
impressive, still gets things wrong.
c. will the AI efforts now gear to ligand (fragment?) prediction with
similarly impressive performance?
Exciting times.
A.
On 3 Dec 2020, at 21:55, Jon Cooper
<0000488a26d62010-dmarc-requ...@jiscmail.ac.uk
<mailto:0000488a26d62010-dmarc-requ...@jiscmail.ac.uk>> wrote:
Hello. A quick look suggests that a lot of the test structures were
solved by phaser or molrep, suggesting it is a very welcome
improvement on homology modelling. It would be interesting to know
how it performs with structures of new or uncertain fold, if there
are any left these days. Without resorting to jokes about artificial
intelligence, I couldn't make that out from the CASP14 website or the
many excellent articles that have appeared. Best wishes, Jon Cooper.
Sent from ProtonMail mobile
-------- Original Message --------
On 3 Dec 2020, 11:17, Isabel Garcia-Saez < isabel.gar...@ibs.fr
<mailto:isabel.gar...@ibs.fr>> wrote:
Dear all,
Just commenting that after the stunning performance of AlphaFold
that uses AI from Google maybe some of us we could dedicate
ourselves to the noble art of gardening, baking, doing Chinese
Calligraphy, enjoying the clouds pass or everything together
(just in case I have already prepared my subscription to Netflix).
https://www.nature.com/articles/d41586-020-03348-4
<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.nature.com_articles_d41586-2D020-2D03348-2D4&d=DwMGaQ&c=4NmamNZG3KTnUCoC6InoLJ6KV1tbVKrkZXHRwtIMGmo&r=1DzJFW0v6TgEhkW1gy_-ke-RbtvS1fzEbD5_hcb9Up0&m=5lc5MUokcPdJZuiKvx3xkaHGMFTkSQHuwMu3HoQZUNA&s=FjJEUNt1oYyfCSZk105Z-QvYSPRKxaj1NGZOmqJsXKw&e=>
Well, I suppose that we still have the structures of complexes
(at the moment). I am wondering how the labs will have access to
this technology in the future (would it be for free coming from
the company DeepMind - Google?). It seems that they have already
published some code. Well, exciting times.
Cheers,
Isabel
Isabel Garcia-SaezPhD
Institut de Biologie Structurale
Viral Infection and Cancer Group (VIC)-Cell Division Team
71, Avenue des Martyrs
CS 10090
38044 Grenoble Cedex 9
France
Tel.: 00 33 (0) 457 42 86 15
e-mail: isabel.gar...@ibs.fr <mailto:isabel.gar...@ibs.fr>
FAX: 00 33 (0) 476 50 18 90
http://www.ibs.fr/
<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.ibs.fr_&d=DwMGaQ&c=4NmamNZG3KTnUCoC6InoLJ6KV1tbVKrkZXHRwtIMGmo&r=1DzJFW0v6TgEhkW1gy_-ke-RbtvS1fzEbD5_hcb9Up0&m=5lc5MUokcPdJZuiKvx3xkaHGMFTkSQHuwMu3HoQZUNA&s=YlBw2nUGdJg2OpSa9WKUs8bJxcGcNDihK6rZy-M-d0Q&e=>
------------------------------------------------------------------------
To unsubscribe from the CCP4BB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1
<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.jiscmail.ac.uk_cgi-2Dbin_WA-2DJISC.exe-3FSUBED1-3DCCP4BB-26A-3D1&d=DwMGaQ&c=4NmamNZG3KTnUCoC6InoLJ6KV1tbVKrkZXHRwtIMGmo&r=1DzJFW0v6TgEhkW1gy_-ke-RbtvS1fzEbD5_hcb9Up0&m=5lc5MUokcPdJZuiKvx3xkaHGMFTkSQHuwMu3HoQZUNA&s=x-2GXzG8eqhqC4BAqzPekybM7m-MvbZCTkuEasQNook&e=>
------------------------------------------------------------------------
To unsubscribe from the CCP4BB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1
<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.jiscmail.ac.uk_cgi-2Dbin_WA-2DJISC.exe-3FSUBED1-3DCCP4BB-26A-3D1&d=DwMGaQ&c=4NmamNZG3KTnUCoC6InoLJ6KV1tbVKrkZXHRwtIMGmo&r=1DzJFW0v6TgEhkW1gy_-ke-RbtvS1fzEbD5_hcb9Up0&m=5lc5MUokcPdJZuiKvx3xkaHGMFTkSQHuwMu3HoQZUNA&s=x-2GXzG8eqhqC4BAqzPekybM7m-MvbZCTkuEasQNook&e=>
------------------------------------------------------------------------
To unsubscribe from the CCP4BB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1
<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.jiscmail.ac.uk_cgi-2Dbin_WA-2DJISC.exe-3FSUBED1-3DCCP4BB-26A-3D1&d=DwMGaQ&c=4NmamNZG3KTnUCoC6InoLJ6KV1tbVKrkZXHRwtIMGmo&r=1DzJFW0v6TgEhkW1gy_-ke-RbtvS1fzEbD5_hcb9Up0&m=5lc5MUokcPdJZuiKvx3xkaHGMFTkSQHuwMu3HoQZUNA&s=x-2GXzG8eqhqC4BAqzPekybM7m-MvbZCTkuEasQNook&e=>
------------------------------------------------------------------------
To unsubscribe from the CCP4BB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1
--
Postdoctoral Researcher
Department of Protein Evolution
Max Planck Institute for Developmental Biology
Max-Planck-Ring 5
72076 Tübingen
GERMANY
########################################################################
To unsubscribe from the CCP4BB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=CCP4BB&A=1
This message was issued to members of www.jiscmail.ac.uk/CCP4BB, a mailing list
hosted by www.jiscmail.ac.uk, terms & conditions are available at
https://www.jiscmail.ac.uk/policyandsecurity/
