This model is trained on a sigle site deep mutation scanning dataset and can be used to predict fitness score of mutant amino acid sequence of protein AsCas12f.

AsCas12a is widely utilized as genome-editing tools in human cells.

protein level regression

The dataset is from An AsCas12f-based compact genome-editing tool derived by deep mutational scanning and structural analysis.

Label means fitness score of each mutant amino acid sequence. Ranging from negative infinity to positive infinity. The wildtype sequence has fitness 1. If the effect larger than 1 represents high fitness, smaller than 1 represents low fitness.

Amino acid sequence

0.60 Spearman's ρ

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: 50

batch size: 36

precision: 16-mixed