File size: 1,622 Bytes
7b093ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
import gradio as gr
from transformers import AutoTokenizer, EsmForProteinFolding
from transformers.models.esm.openfold_utils.protein import to_pdb, Protein as OFProtein
from transformers.models.esm.openfold_utils.feats import atom14_to_atom37
import torch

def convert_outputs_to_pdb(outputs):
    final_atom_positions = atom14_to_atom37(outputs["positions"][-1], outputs)
    outputs = {k: v.to("cpu").numpy() for k, v in outputs.items()}
    final_atom_positions = final_atom_positions.cpu().numpy()
    final_atom_mask = outputs["atom37_atom_exists"]
    pdbs = []
    for i in range(outputs["aatype"].shape[0]):
        aa = outputs["aatype"][i]
        pred_pos = final_atom_positions[i]
        mask = final_atom_mask[i]
        resid = outputs["residue_index"][i] + 1
        pred = OFProtein(
            aatype=aa,
            atom_positions=pred_pos,
            atom_mask=mask,
            residue_index=resid,
            b_factors=outputs["plddt"][i],
            chain_index=outputs["chain_index"][i] if "chain_index" in outputs else None,
        )
        pdbs.append(to_pdb(pred))
    return pdbs

def fold_prot_locally(sequence):
    tokenized_input = tokenizer([sequence], return_tensors="pt", add_special_tokens=False)['input_ids']

    with torch.no_grad():
        output = model(tokenized_input)
    pdb = convert_outputs_to_pdb(output)
    return pdb

tokenizer = AutoTokenizer.from_pretrained("facebook/esmfold_v1")
model = EsmForProteinFolding.from_pretrained("facebook/esmfold_v1", low_cpu_mem_usage=True)

iface = gr.Interface(fn=fold_prot_locally, inputs="text", outputs="text")
iface.launch()