metadata
license: mit
Base model: westlake-repl/SaProt_650M_AF2
Task type: pair protein-level regression
Structure Similarity Prediction predicts the (aligned) Local Distance Difference Test (LDDT) of the structures given an unaligned pair of proteins. Target values are computed after alignment with TM-align for all pairs of 1000 randomly sampled single-chain proteins.
Dataset: SaProtHub/Dataset-Structural_Similarity-ProteinShake
Model input type: SA(Structure-aware) sequence
Performance (on test set): 0.695 Spearman's ρ
LoRA config:
- r: 8
- lora_dropout: 0.1
- lora_alpha: 8
- target_modules: ["query", "key", "value", "intermediate.dense", "output.dense"]
- modules_to_save: ["classifier"]
Training config:
- optimizer:
- class: AdamW
- betas: (0.9, 0.98)
- weight_decay: 0.01
- learning rate: 5e-4
- epoch: 3
- batch size: 64
- precision: 16-mixed