raimondilab / precogx Goto Github PK
View Code? Open in Web Editor NEWA predictor of GPCR couplings with G-proteins/B-arrs using Transformers
Home Page: https://precogx.bioinfolab.sns.it/
License: GNU General Public License v3.0
A predictor of GPCR couplings with G-proteins/B-arrs using Transformers
Home Page: https://precogx.bioinfolab.sns.it/
License: GNU General Public License v3.0
Hi Gurdeep,
yes, I think that 25 sequences is already pretty generous .... we should
also provide a refreshing page with the URL of the output, and possibly the
option to provide an email, in case the calculations will take a while.
We should probably also run the prediction for all the GPCR sequences at
least of the human GPCRome (and possibly from swissprot) and store this
information in a database (SQLite or MySQL), so to speed up the analysis
in those cases where a certain sequence was already analyzed or for the
mutation analysis case (the WT embeddings predictions should already be
there).
Talk to you on Thursday.
Best,
Francesco
On Tue, Dec 7, 2021 at 11:52 AM Gurdeep Singh @.***>
wrote:
Hi everybody @raimondifranc https://github.com/raimondifranc
@nataliarosa9 https://github.com/nataliarosa9 @maticmarin
https://github.com/maticmarinI remember that @nataliarosa9 https://github.com/nataliarosa9 had shown
us in the previous call input checks that she created (eg: only alphabets
in FASTA etc). So here I am making a list of other checks that we have to
make in the input.We all can edit (add more items) this checkbox-list and request
@nataliarosa9 https://github.com/nataliarosa9 to include them also:
- Input accepted only in FASTA formatted or precog format (eg:
DRD1/F61P)- If the input is FASTA, it cannot be more than 1024 residues long
(correct @maticmarin https://github.com/maticmarin?)- Use cannot input more than 25 sequences in one go (counting both WT
and MUT), right, @raimondifranc https://github.com/raimondifranc?โ
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#14, or unsubscribe
https://github.com/notifications/unsubscribe-auth/ACHY44PHFU6E6PYBPKZSHWTUPXRPLANCNFSM5JQ5ZCJQ
.
Triage notifications on the go with GitHub Mobile for iOS
https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675
or Android
https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
Originally posted by @raimondifranc in #14 (comment)
Hi @maticmarin, I think you will have to re-run the train script in my directory to save the PCA matrix of all the GPCRs (at least class A) against all the best models (G-proteins). Please note that I removed >
from your extract.sh
as I am already saving the NumPy format.
Thanks!
Though when you select only Wt and MUT individually, it works fine
/data/Users/marin/transformers/gpcr
This is the 33rd layer
Hi @maticmarin, @raimondifranc
Could any of you paste here the path to the file?
thanks
Hey @maticmarin , could you share the contact map pairs? thx!
Hi @nataliarosa9
Could you also provide an upload button on the home page?
Hi @nataliarosa9 , could I ask you to please fix the aesthetics of the slider? I am bad at HTML/CSS stuff
Thanks
Hi everybody @raimondifranc @nataliarosa9 @maticmarin
I remember that @nataliarosa9 had shown us in the previous call input checks that she created (eg: only alphabets in FASTA etc). So here I am making a list of other checks that we have to make in the input.
We all can edit (add more items) this checkbox-list and request @nataliarosa9 to include them also:
Hi @maticmarin, when you update the contacts file specific_position_score.txt
, please remember to add Barrs too. Also, could you provide Superfamily numbering? (see here)
Thanks
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.