Comments (10)
I must look into that deeper, although there seam to be an issue with implicit arguments order. The code was fully functioning and tested. For now try changing dock method call to explicitly give auto_ligand parameter:
pipeline.dock('autodock_vina', 'ampc/receptor.pdbqt', auto_ligand='ampc/crystal_ligand.mol2')
from oddt.
Please upgrade ODDT from pip. The bug is fixed.
pip install -U --no-deps oddt
from oddt.
Thanks! it works now.
On Mon, Jul 13, 2015 at 10:38 AM, Maciej Wójcikowski <
[email protected]> wrote:
—
Reply to this email directly or view it on GitHub
#5 (comment).
from oddt.
Hi,
Thanks for your code,
When I try to use it every thing is OK but when I reach pipeline.write('mol2', 'ampc_docked.mol2', overwrite=True, opt={'c':None}) nothing appear even the prompt the terminal of python is latch like you see in the attachment
and when I interrupt it I get this error:
I appreciate any help ....
from oddt.
Sorry, but I forget to tell you that the software is up-to-date that you can see here
from oddt.
Pipelines are lazy. This means that unless you execute the chained pipeline by fetching the ligands or writing to the output file actually no computation is done.
So in your case the docking is being done when you enter pipeline.write(...) command. Be patient and check the top/htop for the running processes.
from oddt.
Thank you for your answer ,you are right I wait and finally get a result but I face another problem :
When I read the journal and the code I understand that there is no pickle files but I am newbie in this field and couldn't resolve it.
Thanks a lot for explanation.
from oddt.
Pickle is a Python object saved to a file for later use. It is not recommended to use pickle files from unknown sources because of security reasons. Other than that all the libraries version must match.
Considering this scoring functions in ODDT have to be built upon first run. The RF-score is really fast, but NNscore can be veeery slow (it might take over an hour to build). According to original release of NNScore 2.0 there are 1000 neural-netwoks being built, then the best are selected.
To sum up - just be patient once again.
PS.
We are working hard to do something about it, like switching to netter neural-network library, although it's not that straightforward.
from oddt.
Thanks for your quick response,
when I wait nnscore an error appear and nothing happened because I check the htop.
and when I try to write to the _csv file the file exist but it is 0 byte.
then I try to score the result only with rfscore I get this error when I want to write the result to _csv file
and this error appear many times:
AttributeError: Molecule has no such property: atom_dict
Then I repeat the scoring by these two function this time have no error
but when I start writing nothing happened and 0byte file exist
from oddt.
First of all please move that question to the mailing list [[email protected]], since that has nothing to do with current closed issue.
Secondly, as you can see the NNScore has trained itself. There should be .pickle file in working directory.
Third thing - the Molecule class is somehow loaded from outside of ODDT, since it has some attributes missing (most probable from pybel/cinfony). Have you tried clean terminal or assembling a script and executing the pipeline separately?
from oddt.
Related Issues (20)
- Could there be a new release? HOT 2
- Ring normal vector is calculated incorrectly in pip package HOT 1
- Please do not install tests into the 'test' directory
- failure in completing HOT 4
- Protein structure used does not change when using autodock_vina_descriptor.build()
- PIP distribution does not correspond to github version HOT 1
- Installing oddt from poetry is not possible HOT 3
- TypeError: in method 'new_OBMol' HOT 2
- RDKIT molecule HOT 1
- Training scoring functions and updated version of PDBBind HOT 2
- oodt syntax error HOT 1
- pip installation failed -
- you have a mol2 parser in there? HOT 3
- Docking Issues Between MacOS and Windows HOT 1
- AttributeError: module 'openbabel.openbabel' has no attribute 'OBElementTable' HOT 1
- toolkit not being recognised
- rf = RFScore() TypeError: 'module' object is not callable HOT 2
- for mol in ligands: TypeError: 'NoneType' object is not iterable
- Question about retrain your model on PDBbind-2016 by modifying the 'act' column
- Descriptors calculation with PLEC
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from oddt.