This model is used to predict signal peptides on each site of amino acid sequences.

Residue level clssification

The dataset is from SignalP 6.0 predicts all five types of signal peptides using protein language models. This dataset contains 7 classes:

S (0): Sec/SPI signal peptide | T (1): Tat/SPI or Tat/SPII signal peptide | L (2): Sec/SPII signal peptide | P (3): Sec/SPIII signal peptide | I (4): cytoplasm | M (5): transmembrane | O (6): extracellular

Amino acid sequence

test_acc: 0.96

lora_dropout: 0.0

lora_alpha: 16

target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"]

modules_to_save: ["classifier"]

class: AdamW

betas: (0.9, 0.98)

weight_decay: 0.01

learning rate: 1e-4

epoch: 10

batch size: 100

precision: 16-mixed