SaProtHub/Model-Solubility-prediction-650M

Base model: westlake-repl/SaProt_650M_AF2

Model Card for Model ID

This model is used to predict solubility of a amino acid sequence.

Task type

protein level classification

Dataset description

The dataset is from DeepSol: a deep learning framework for sequence-based protein solubility prediction. Binary label, 1 means soluble, 0 means insoluble.

Model input type

Amino acid sequence

Performance

test_acc: 0.74

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: 1

batch size: 100

precision: 16-mixed