search

Ramprasad-Group / polygnn

polyGNN is a Python library to automate ML model training for polymer informatics.
Other
30 stars 5 forks source link

whole data access #21

Closed shijiale0609 closed 5 months ago

shijiale0609 commented 5 months ago

how to get the whole data used in this paper

rishigurnani commented 5 months ago

@shijiale0609 Thanks for your interest in this repo. The sources of each data are listed in the section titled "Data Set and Preparation" of the companion paper. Hope this helps.

shijiale0609 commented 5 months ago

Is there any possibility that part of the training data (like DFT) can be shared?

rishigurnani commented 5 months ago

Sure @shijiale0609! A superset of the DFT data used in the polyGNN paper can be found at this link on Khazana.

The following citations are relevant for the data linked above: 1) Huan, T. D.; Mannodi-Kanakkithodi, A.; Kim, C.; Sharma, V.; Pilania, G.; Ramprasad, R. A Polymer Dataset for Accelerated Property Prediction and Design. Sci. Data 2016 31 2016, 3 (1), 1–10. https://doi.org/10.1038/sdata.2016.12. 2) Kuenneth, C.; Rajan, A. C.; Tran, H.; Chen, L.; Kim, C.; Ramprasad, R. Polymer Informatics with Multi-Task Learning. Patterns 2021, 2 (4). https://doi.org/10.1016/j.patter.2021.100238. 3) Gurnani, R.; Kuenneth, C.; Toland, A.; Ramprasad, R. Polymer Informatics at Scale with Multitask Graph Neural Networks. Chem. Mater. 2023, 35 (4), 1560–1567. https://doi.org/10.1021/acs.chemmater.2c02991.

rishigurnani commented 5 months ago

Closing this issue.