search

oxpig / AbLang

AbLang: A language model for antibodies
BSD 3-Clause "New" or "Revised" License
127 stars 24 forks source link

Clarification Question #8

Closed fergusonscripps closed 1 year ago

fergusonscripps commented 1 year ago

Cool code trying it for a few things in the lab.

For the "Residue likelihood" I wanted to check. The first and last probabilitiy arrays are the SOS and EOS and do not correspond to a "real" amino acid residue?

Are the probabilities in alphabetical for the 20 essential amino acids?

TobiasHeOl commented 1 year ago

Thanks! You are correct that the output also returns the vector of likelihoods for SOS and EOS (not real aa's), however; the vector of likelihoods for each position only contain values for the 20 aa's. This was a design choice based on how we are using the model.

The likelihoods are not ordered alphabetically, but you can view the order with the following:

print(model.tokenizer.vocab_to_aa) I hope this answers your questions!

fergusonscripps commented 1 year ago

Great thank you!

Sent from Outlook for iOShttps://aka.ms/o0ukef

From: Tobias Hegelund Olsen @.> Sent: Wednesday, July 26, 2023 6:30:14 AM To: oxpig/AbLang @.> Cc: James Ferguson @.>; Author @.> Subject: Re: [oxpig/AbLang] Clarification Question (Issue #8)

Closed #8https://github.com/oxpig/AbLang/issues/8 as completed.

— Reply to this email directly, view it on GitHubhttps://github.com/oxpig/AbLang/issues/8#event-9924188889, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AZ7U2ZTY7OZACMXXD2LERYDXSELWNANCNFSM6AAAAAA2XVBZWE. You are receiving this because you authored the thread.Message ID: @.***>