Comments (4)
Hi this error is due to not decoding any molecules and so since you try to plot the resulting molecules (None) you get an error.
The non-decoding could be due to the z vector, or the smiles or the number of decoding attempts.
What z-vector/molecule are you trying to decode?
from chemical_vae.
Thank you! I also found this reason, because I found this on my command line,
[10:45:10] SMILES Parse Error: syntax error for input: 'CC1ccc(c1cc@NH2)N[3H]2(CCO)C'
[10:45:10] SMILES Parse Error: syntax error for input: 'Ccccccc(=O)[NHOH+]3CCC@=O- C'
[10:45:10] SMILES Parse Error: syntax error for input: 'CCc1cN(=O=N+2(C[OC[NCO)n21)'
[10:45:10] SMILES Parse Error: syntax error for input: 'Cc1C(=(=C@)[C@H]1Nc1)1 ='
I selected a few SMILES randomly from the csv file, what I used here is CC(=O)c1c(O)cccc1COc1ccccc1 and CCCN(CC)c1cc[nH+]c(C(=O)[O-])c1 . I also try to find the middle of the z-vector of the two SMILES, but the output is OC(C1cc(c(O)cccccc(F)F)c1c1 , this is obviously an invalid SMILES , so what should I do to get more valid SMILES output. Thanks!
from chemical_vae.
What do you mean by middle of the z-vector of two smiles?
To get more valid smiles, you should increase the number of decoding attempts (how many are you using?) or slightly increase the noise radius (how much are you using?).
from chemical_vae.
HI !I don't know middle of the z-vector. But, Isn't Z-vector Z-distance?
Z-distance is three -dimensional distance (euclidian metric of three material property values) ,right?
from chemical_vae.
Related Issues (20)
- Cannot reproduce the h5 files of the zinc_properties example HOT 1
- NameError: name 'TerminalGRU' is not defined HOT 2
- Decoder expects 3 inputs but it received 2 inputs
- ...For time-series...
- Exact Python package versions
- I am trying to use your model to get the encoded representation of the smiles. HOT 1
- name 'vae' is not defined
- Is the Gaussian process for optimization of molecules included in the repository? HOT 1
- trying using the conda method HOT 3
- intro_to_chemvae.ipynb loading model AttributeError: 'str' object has no attribute 'decode' HOT 3
- Dense layer in variational_layers is not saved and cannot be used to generate latent variables
- AttributeError: 'TerminalGRU' object has no attribute 'preprocess_input' HOT 1
- GPU Support
- FileNotFoundError: [Errno 2] No such file or directory: 'zinc.json' HOT 1
- Hello
- updated version of this VAE?
- Paper
- Where can I find the model prediction result?
- Which RDkit version is used in this project?
- Version incompatible
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 chemical_vae.