guacamol
guacamol copied to clipboard
BenevolentAI
Benchmarks for generative chemistry
I would like to use Guacamol to benchmark 3rd party products for generative chemistry. I realize that some default Guacamol benchmarks may be unsuitable for this, such as those that...
When using `guacamol` with `PytorchLightning==1.6.5` and `PyTorch==1.12.0` I get a mysterious segfault when running the following code: ```Python import pytorch_lightning as pl from guacamol import standard_benchmarks as sb sb.valsartan_smarts() ```...
1. Changed `pytest .` to `python -m pytest .` 2. Changed python version from 3.6 to 3.7 and added the required libraries. 3. Have run the test code, and the...
Our guacamol scoring functions do not have a name as part of the object. Its also not straightforward to add a 'name' to the various ScoringFunction's. However each scoring function...
From what I understand you set isomericSmiles = False in your preprocessing (`filter_and_canonicalize` function). This means you don't take into account any isomeric information. Do you think this might be...
fcd has been ported to pytorch at https://github.com/insilicomedicine/fcd_torch How do you feel about supporting both fcd methods? You can use fcd by default and fallback to fcd_torch if fcd is...
It seems the code I wrote might be all we need for the similarity metric benchmark in Guacamol. We might not need this branch any more, but I keep this...
Dear all, could we please replace the hard-wired benchmark suites with a "benchmark factory" (software engineering) pattern. Here I chose a "singleton pattern" as "factory pattern". Any benchmark version self-registers...
Unit testing suite You can test your installation of the guacamol benchmarking library by running the unit tests from this directory: pytest . but how to use it ????
This is actually not an issue, but a type of "might be useful to know". This graph shows the effect of two variables on the FCD value: the sample size...
