metadata
license: mit
from transformers import AutoTokenizer, AutoModelForTokenClassification, TokenClassificationPipeline
import re
pipeline = TokenClassificationPipeline(
model=AutoModelForTokenClassification.from_pretrained("virtual-human-chc/prot_bert_bfd_ss3"),
tokenizer=AutoTokenizer.from_pretrained("virtual-human-chc/prot_bert_bfd_ss3", skip_special_tokens=True),
device=0
)
sequences_Example = ["M G A E E E D T A I L Y P F T I S G N D R N G N F T I N F K G T P N S T N N G C I G Y S Y N G D W E K I E W E G S C D G N G N L V V E V P M S K I P A G V T S G E I Q I W W H S G D L K M T D Y K A L E H H H H H H",
"M N K Y L F E L P Y E R S E P G W T I R S Y F D L M Y N E N R F L D A V E N I V N K E S Y I L D G I Y C N F P D M N S Y D E S E H F E G V E F A V G Y P P D E D D I V I V S E E T C F E Y V R L A C E K Y L Q L H P E D T E K V N K L L S K I P S A G H H H H H H"]
sequences_Example = [re.sub(r"[UZOB]", "X", sequence) for sequence in sequences_Example]
print(pipeline(sequences_Example))