chemprop
Message Passing Neural Networks for Molecule Property Prediction (by chemprop)
ml-psychs
By comp-pharm
| chemprop | ml-psychs | |
|---|---|---|
| 1 | 2 | |
| 1,558 | 4 | |
| 3.5% | - | |
| 9.9 | 0.0 | |
| 3 days ago | about 2 years ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 or later | - |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
chemprop
Posts with mentions or reviews of chemprop.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-02-25.
-
Project Update 20201131
There have been many attempts at this, the most sucessful of which is MIT's ChemProp, which we are actively working on tuning for our goals!
ml-psychs
Posts with mentions or reviews of ml-psychs.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-04-14.
-
Small update on ML Psychs project
The project to use machine learning models to try to identify novel psychedelics has had small, incremental progress: until now. We've had a fairly large improvement in model performance from better, cleaner data. We've moved from ~60% accuracy to ~90% accuracy. We have big plans on further improving the results with augmented data, and once we're happy with model performance we hope to launch our large scale project to run the model against the large ZINC15 database (possibly setting up our own BOINC project to get the community involved in helping). Watch this space!
-
Project Update 20201131
The repository for our project where we are re-training ChemProp for 5HT2A agonists is here: https://github.com/comp-pharm/ml-psychs/
What are some alternatives?
When comparing chemprop and ml-psychs you can also consider the following projects:
hummingbird - Hummingbird compiles trained ML models into tensor computation for faster inference.
boinc - Open-source software for volunteer computing and grid computing.
pyod - A Comprehensive and Scalable Python Library for Outlier Detection (Anomaly Detection)
Keras - Deep Learning for humans
libRL - A Python library for characterizing Microwave Absorption
faceswap - Deepfakes Software For All
chemiscripts - translate ASCII chemical formulas into Unicode