search

GainGod-Xu / ACMLProject

Asymmetric Contrastive Multimodal Learning for Advancing Chemical Understanding, Under Review
2 stars 0 forks source link

Dataset request. #1

Open realfenston opened 2 months ago

realfenston commented 2 months ago

Dear authors,

Thanks for the brilliant work you have done. Our team is working on molecular modalities in this case we will highly appreciate it if the datasets used in your pipeline can be shared for academic use, totally under your license.

Many thanks in advance.

GainGod-Xu commented 2 months ago

Hi, Thank you for your kind words. The pre-training data from NPMRD and MoNA, as well as the zero-shot PubChem dataset, are publicly accessible online. These datasets are meticulously organized and can be readily downloaded. RDKit can be utilized to parse these datasets into individual samples.

However, as two papers based on these datasets are currently under review, we do not plan to release the dataset at this point. If you would like to collaborate, I am happy to assist you in accessing these datasets and beyond. Please feel free to email me at haoxu0303@gmail.com and introduce yourself.

Best regards, Hao