← all datasets

20,000 molecules

Emerging
1papers using it
2023first seen

The '20,000 molecules' dataset contains a diverse set of molecular structures, varying in complexity and size, and is used to evaluate the accuracy of models predicting molecular properties such as the product of entropy and temperature (S × T) and zero point vibrational energy (ZPVE).

🔎 Find this dataset

Papers using 20,000 molecules (1)

20,000 molecules — datasets — graph-learning