conda create -n SaProt python=3.10
conda activate SaProt

bash environment.sh  

from transformers import EsmTokenizer, EsmForMaskedLM

model_path = "/your/path/to/SaProt_650M_AF2" # Note this is the directory path of SaProt, not the ".pt" file
tokenizer = EsmTokenizer.from_pretrained(model_path)
model = EsmForMaskedLM.from_pretrained(model_path)

#################### Example ####################
device = "cuda"
model.to(device)

seq = "M#EvVpQpL#VyQdYaKv" # Here "#" represents lower plDDT regions (plddt < 70)
tokens = tokenizer.tokenize(seq)
print(tokens)

inputs = tokenizer(seq, return_tensors="pt")
inputs = {k: v.to(device) for k, v in inputs.items()}

outputs = model(**inputs)
print(outputs.logits.shape)

"""
['M#', 'Ev', 'Vp', 'Qp', 'L#', 'Vy', 'Qd', 'Ya', 'Kv']
torch.Size([1, 11, 446])
"""

from utils.esm_loader import load_esm_saprot

model_path = "/your/path/to/SaProt_650M_AF2.pt"
model, alphabet = load_esm_saprot(model_path)

from utils.foldseek_util import get_struc_seq
pdb_path = "example/8ac8.cif"

# Extract the "A" chain from the pdb file and encode it into a struc_seq
# pLDDT is used to mask low-confidence regions if "plddt_mask" is True. Please set it to True when
# use AF2 structures for best performance.
parsed_seqs = get_struc_seq("bin/foldseek", pdb_path, ["A"], plddt_mask=False)["A"]
seq, foldseek_seq, combined_seq = parsed_seqs

print(f"seq: {seq}")
print(f"foldseek_seq: {foldseek_seq}")
print(f"combined_seq: {combined_seq}")

from model.saprot.saprot_foldseek_mutation_model import SaprotFoldseekMutationModel


config = {
    "foldseek_path": None,
    "config_path": "/your/path/to/SaProt_650M_AF2", # Note this is the directory path of SaProt, not the ".pt" file
    "load_pretrained": True,
}
model = SaprotFoldseekMutationModel(**config)
tokenizer = model.tokenizer

device = "cuda"
model.eval()
model.to(device)

seq = "M#EvVpQpL#VyQdYaKv" # Here "#" represents lower plDDT regions (plddt < 70)

# Predict the effect of mutating the 3rd amino acid to A
mut_info = "V3A"
mut_value = model.predict_mut(seq, mut_info)
print(mut_value)

# Predict all effects of mutations at 3rd position
mut_pos = 3
mut_dict = model.predict_pos_mut(seq, mut_pos)
print(mut_dict)

# Predict probabilities of all amino acids at 3rd position
mut_pos = 3
mut_dict = model.predict_pos_prob(seq, mut_pos)
print(mut_dict)

"""
0.7908501625061035

{'V3A': 0.7908501625061035, 'V3C': -0.9117952585220337, 'V3D': 2.7700226306915283, 'V3E': 2.3255627155303955, 'V3F': 0.2094242423772812, 'V3G': 2.699633836746216, 'V3H': 1.240191102027893, 'V3I': 0.10231903940439224, 'V3K': 1.804598093032837,
'V3L': 1.3324960470199585, 'V3M': -0.18938277661800385, 'V3N': 2.8249857425689697, 'V3P': 0.40185314416885376, 'V3Q': 1.8361762762069702, 'V3R': 1.1899691820144653, 'V3S': 2.2159857749938965, 'V3T': 0.8813426494598389, 'V3V': 0.0, 'V3W': 0.5853186249732971, 'V3Y': 0.17449656128883362}

{'A': 0.021275954321026802, 'C': 0.0038764977362006903, 'D': 0.15396881103515625, 'E': 0.0987202599644661, 'F': 0.011895398609340191, 'G': 0.14350374042987823, 'H': 0.03334535285830498, 'I': 0.010687196627259254, 'K': 0.058634623885154724, 'L': 0.03656982257962227, 'M': 0.00798324216157198, 'N': 0.16266827285289764, 'P': 0.014419485814869404, 'Q': 0.06051575019955635, 'R': 0.03171204403042793, 'S': 0.08847439289093018, 'T': 0.023291070014238358, 'V': 0.009647775441408157, 'W': 0.017323188483715057, 'Y': 0.011487090960144997}
"""

# Fine-tune SaProt on the Thermostability task
python scripts/training.py -c config/Thermostability/saprot.yaml

# Fine-tune ESM-2 on the Thermostability task
python scripts/training.py -c config/Thermostability/esm2.yaml

# Evaluate the zero-shot performance of SaProt on the ProteinGym benchmark
python scripts/mutation_zeroshot.py -c config/ProteinGym/saprot.yaml

# Evaluate the zero-shot performance of ESM-2 on the ProteinGym benchmark
python scripts/mutation_zeroshot.py -c config/ProteinGym/esm2.yaml

# Evaluate the zero-shot performance of SaProt on the ClinVar benchmark
python scripts/mutation_zeroshot.py -c config/ClinVar/saprot.yaml
python scripts/compute_clinvar_auc.py -c config/ClinVar/saprot.yaml

@article{su2023saprot,
  title={SaProt: Protein Language Modeling with Structure-aware Vocabulary},
  author={Su, Jin and Han, Chenchen and Zhou, Yuyang and Shan, Junjie and Zhou, Xibin and Yuan, Fajie},
  journal={bioRxiv},
  year={2023},
  publisher={Cold Spring Harbor Laboratory}