Comments (4)
Also, as you mentioned in ticket #45, if I want to generate large amount of molecules, which parameter shall I play around? multiple random seeds, n_examples, or n_samples? Thanks,
from ligan.
If you set the config option output: output_mols: True
, then the 3D molecules will be written to sdf files in the directory {out_dir}/molecules/
. Computed metrics for the generated molecules will be written to a file {out_prefix}.gen_metrics
. The metrics are not currently documented well, but any column name that begins with "lig_gen_*" is a metric computed on a generated grid/structure/molecule. For instance, lig_gen_fit_add_QED
is the drug-likeness score for the generated molecule.
The n_examples
option specifies the number of distinct input examples (receptor-ligand pairs) from your data file you would like to generate molecules for, and the n_samples
option specifies the number of random samples to generate for each input example. The total number of output molecules will be n_examples * n_samples
. The random_seed
option is for reproducibility.
from ligan.
@mattragoza Thanks for the reply. in the {out_dir}/molecules/, which is the final optimized 3D structure in terms of to the binding pocket. Is it *lig_gen_fit_add_gna.sdf? I have other sdf files in the same folder: *add_uff.sdf, *add_pkt.sdf, and *add.sdf
Thanks
from ligan.
Yes, the files ending in lig_gen_fit_add_gna.sdf
are the generated molecules after minimization in the binding pocket with gnina.
Here are all the output identifier types and what they mean:
lig_gen = generated density grid (from generative model)
lig_gen_fit = generated atoms (from atom fitting)
lig_gen_fit_add = generated molecule (from bond adding)
lig_gen_fit_add_uff = generated molecule after UFF minimization (internal energy)
lig_gen_fit_add_gna = generated molecule after gnina minimization (wrt binding pocket)
lig_gen_fit_add_pkt = receptor pocket used for gnina minimization
from ligan.
Related Issues (20)
- AttributeError: type object 'object' has no attribute 'dtype' HOT 9
- gnina minmize problem HOT 2
- Can not access to https://bits.csb.pitt.edu/files/ to download those files HOT 2
- Segmentation Fault when running tests HOT 1
- tests ValueError: File does not exist: data/test_pockets/xxx HOT 3
- change configuration file for prior (no lig) sampling HOT 1
- Error when run cmake of libmogrid HOT 4
- Errors when run pytest tests HOT 12
- how I can export embeddings HOT 3
- Get Stuck when runing generate.py HOT 2
- Train_file and test_file are missing HOT 1
- CUDNN Error (out of memory?): CUDNN_STATUS_EXECUTION_FAILED HOT 2
- Get killed when running generate.py HOT 5
- Cannot use model with `fit_atoms: True` HOT 8
- Changing parameters while testing the model HOT 6
- KeyError: 'minimizedAffinity' in tests HOT 6
- Environment.yml isnt complete and libmolgrid git command fails HOT 3
- Changes required to train the CGAN model
- Data link failure
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 ligan.