WesleyyC / Amino-Acid-Embedding

:microscope: Train an Amino Acid Embeddings (or a dragon?)
MIT License
17 stars 1 forks source link

Data set trained on? #1

Closed sidhomj closed 6 years ago

sidhomj commented 6 years ago

Can you specify which data-set you trained on to bring you to that t-SNE plot?

Thanks..

WesleyyC commented 6 years ago

Hi,

The data is from RefSeq: https://www.biostars.org/p/130274/

And you can pull them down with this python helper: https://github.com/WesleyyC/Amino-Acid-Embedding/blob/master/Data/getFileWeb.py

Cheers

zyxue commented 6 years ago

How many peptides were used exactly, please?