I want to use PubChem data, such as toxicity data and chemical formulas, to train machine learning models that identify toxic functional groups.
Can anyone guide me on the following:
- Are there licensing agreements or restrictions for commercial use?
- What are the attribution requirements?
- Are additional permissions or approvals needed from PubChem?
PubChem collects data from various sources and provides different licenses for its content. The overall licensing requirements are still not entirely clear. However, I have seen numerous publications where models are train based on the PubChem data.
Thanks!
New contributor