SaProtHub/Model-DMS_UBC9_HUMAN-35M

Base model: westlake-repl/SaProt_35M_AF2

Model Card for Model ID

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 UBC9_HUMAN (SUMO-conjugating enzyme UBC9).

Protein Function

This proterin can accepts the ubiquitin-like proteins SUMO1, SUMO2, SUMO3, SUMO4 and SUMO1P1/SUMO5 from the UBLE1A-UBLE1B E1 complex and catalyzes their covalent attachment to other proteins with the help of an E3 ligase such as RANBP2, CBX4 and ZNF451.

Task type

protein level regression

Dataset description

The dataset is from Deep generative models of genetic variation capture the effects of mutations. And can also be found on SaprotHub dataset.

Label means fitness score of each mutant amino acid sequence. The wild‐type mutants receiving a score of one, larger value represents higher fitness.

Model input type

Amino acid sequence

Performance

0.60 Spearman's ρ

LoRA config

lora_dropout: 0.0

lora_alpha: 16

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

modules_to_save: ["classifier"]

Training config

class: AdamW

betas: (0.9, 0.98)

weight_decay: 0.01

learning rate: 1e-4

epoch: 100

batch size: 2

precision: 16-mixed