cut pep length to no more than 1022 AAs

[Racccoon-Kevins]

I found the code cutting protein sequence to no more than 1022 AAs.

df_test['Protein'] = df_test['Protein'].apply(lambda x: x[:1022] if len(x) > 1022 else x)
Would you please help explaining the reason of any other consideration?

[HamidHadipour]

That's the limit that applies when using the ESM model.