lee-cbg / catelmo Goto Github PK

Hi Pengfei,

I think your work is very impressive and I am eager to use your model in my research! Could you please provide more details regarding the format of the input file while using catELMo to calculate the embedding of TCR sequences?

To be more specific, in the instruction, you mentioned the input file 'dat = pd.read_csv('./path/of/binding/affinity/prediction/data.csv')', it would be very nice if you could provide an example of this 'data.csv' file. Besides, is it necessary to include peptide info in the input file? Can I only input TCR sequences and get their embedding, since that's what I am most interested in?

Thank you so much in advance! Looking forward to hearing from you soon.
Mingyao