search

learningmatter-mit / peptimizer

Peptide optimization with Machine Learning
68 stars 24 forks source link

PMO-CPP library and activity dataset #6

Closed Jiacheng06 closed 2 years ago

Jiacheng06 commented 2 years ago

Hi pikulsomesh,

I was wondering if the dataset of PMO-CPP library and activity (from the paper: Deep Learning Enables Discovery of a Short Nuclear Targeting Peptide for Efficient Delivery of Antisense Oligomers) is open to public? If so, could you please tell me how to download it because I could not find it in the current dataset.

Thanks a lot, Jiacheng

pikulsomesh commented 2 years ago

Hi @Jiacheng06 The dataset of PMO-CPP library consists of both the dataset in the GitHub repository, and the sequences published in the original paper, specifically in Table 13 of Supplementary Information. Best Somesh

Jiacheng06 commented 2 years ago

Hi Somesh,

Thank you very much for your promptly reply! I was also wondering about the meaning of some numbers (like 2 and 3) in the sequences of the cpp_predictor_dataset. BTW, does the dataset of PMO-CPP library only include the sequences of CPPs without PMO (which means during the training of the model, it only uses the sequences of CPPs)?

Kind regards, Jiacheng