-
I can't seem to find version information on the packages used.
Additionally, the README seems to refer to folders like scripts/save_features.py
I assume ChemProp was change, but clarification would…
-
Dear developer,
We are getting the molecule results from synthemol in the step of molecule generation. However, we noticed that some high-score molecules have missing information for the building …
-
Start from the antibiotic prediction paper and see whether we can reproduce a similar approach of building a prediction model using chemoprop, and then add features extracted from RDkit from all molec…
-
Are there any experiments that benchmark MAT against [chemprop](https://github.com/chemprop/chemprop)? Have the folks over at Ardigen already tried this comparison?
-
People have asked for how to serve Chemprop models via a web API (see #591). Part of this is how to save both the featurizer/preprocessing in addition to the model for delivering to others. It looks l…
-
Summary:
- RMG currently uses `chemprop` version 0.0.1 to perform machine learning prediction of molecular thermochemistry
- This version only supports Python version 3.7 and 3.8, so it is blockin…
-
Hi Kyle, thanks so much for putting this togther. I have encounterd a "Depreciation warning: please use MorganGenerator." as a repeated error message when running the local python version.
I think …
-
`python finetune_generator.py --train ${ACTIVE_MOLECULES} --vocab data/chembl/vocab.txt --generative_model ckpt/chembl-pretrained/model.ckpt --chemprop_model ${YOUR_PROPERTY_PREDICTOR} --min_similarit…
-
The pretrained model weights at ML_UVvisModels/UVvis-MPNN/original are missing in the repo (they are there for the other chemprop models with e.g. 3D distances as input features).
I would love to t…
-
**The Kaggle challenge has officially finished. Our best model is the chemprop model that receives 0.410 public score (rank 911/1984) and 0.232 private score (rank 973/1984).** Public score considered…