Spaces:
Sleeping
Sleeping
| import re | |
| from pathlib import Path | |
| import gradio as gr | |
| from evodiff.pretrained import OA_DM_38M, D3PM_UNIFORM_38M, MSA_OA_DM_MAXSUB | |
| from evodiff.generate import generate_oaardm, generate_d3pm | |
| from evodiff.generate_msa import generate_query_oadm_msa_simple | |
| import py3Dmol | |
| from colabfold.download import download_alphafold_params, default_data_dir | |
| from colabfold.utils import setup_logging | |
| from colabfold.batch import get_queries, run, set_model_type | |
| from colabfold.plot import plot_msa_v2 | |
| def a3m_file(file): | |
| return "tmp.a3m" | |
| def predict_protein(sequence): | |
| download_alphafold_params("alphafold2_ptm", Path(".")) | |
| results = run( | |
| queries=[('evodiff_protein',sequence, None)], | |
| result_dir='evodiff_protein', | |
| use_templates=False, | |
| num_relax=0, | |
| msa_mode="mmseqs2_uniref_env", | |
| model_type="alphafold2_ptm", | |
| num_models=1, | |
| num_recycles=1, | |
| model_order=[1], | |
| is_complex=False, | |
| data_dir=Path("."), | |
| keep_existing_results=False, | |
| rank_by="auto", | |
| stop_at_score=float(100), | |
| zip_results=False, | |
| user_agent="colabfold/google-colab-main", | |
| ) | |
| return f"evodiff_protein/evodiff_protein_unrelaxed_rank_001_alphafold2_ptm_model_1_seed_000.pdb" | |
| def display_pdb(path_to_pdb): | |
| ''' | |
| #function to display pdb in py3dmol | |
| SOURCE: https://huggingface.co/spaces/merle/PROTEIN_GENERATOR/blob/main/app.py | |
| ''' | |
| pdb = open(path_to_pdb, "r").read() | |
| view = py3Dmol.view(width=500, height=500) | |
| view.addModel(pdb, "pdb") | |
| view.setStyle({'model': -1}, {"cartoon": {'colorscheme':{'prop':'b','gradient':'roygb','min':0,'max':1}}})#'linear', 'min': 0, 'max': 1, 'colors': ["#ff9ef0","#a903fc",]}}}) | |
| view.zoomTo() | |
| output = view._make_html().replace("'", '"') | |
| print(view._make_html()) | |
| x = f"""<!DOCTYPE html><html></center> {output} </center></html>""" # do not use ' in this input | |
| return f"""<iframe height="500px" width="100%" name="result" allow="midi; geolocation; microphone; camera; | |
| display-capture; encrypted-media;" sandbox="allow-modals allow-forms | |
| allow-scripts allow-same-origin allow-popups | |
| allow-top-navigation-by-user-activation allow-downloads" allowfullscreen="" | |
| allowpaymentrequest="" frameborder="0" srcdoc='{x}'></iframe>""" | |
| ''' | |
| return f"""<iframe style="width: 100%; height:700px" name="result" allow="midi; geolocation; microphone; camera; | |
| display-capture; encrypted-media;" sandbox="allow-modals allow-forms | |
| allow-scripts allow-same-origin allow-popups | |
| allow-top-navigation-by-user-activation allow-downloads" allowfullscreen="" | |
| allowpaymentrequest="" frameborder="0" srcdoc='{x}'></iframe>""" | |
| ''' | |
| def make_uncond_seq(seq_len, model_type): | |
| if model_type == "EvoDiff-Seq-OADM 38M": | |
| checkpoint = OA_DM_38M() | |
| model, collater, tokenizer, scheme = checkpoint | |
| tokeinzed_sample, generated_sequence = generate_oaardm(model, tokenizer, seq_len, batch_size=1, device='cpu') | |
| if model_type == "EvoDiff-D3PM-Uniform 38M": | |
| checkpoint = D3PM_UNIFORM_38M(return_all=True) | |
| model, collater, tokenizer, scheme, timestep, Q_bar, Q = checkpoint | |
| tokeinzed_sample, generated_sequence = generate_d3pm(model, tokenizer, Q, Q_bar, timestep, seq_len, batch_size=1, device='cpu') | |
| path_to_pdb = predict_protein(generated_sequence) | |
| molhtml = display_pdb(path_to_pdb) | |
| return generated_sequence, molhtml | |
| def make_cond_seq(seq_len, msa_file, model_type): | |
| if model_type == "EvoDiff-MSA": | |
| checkpoint = MSA_OA_DM_MAXSUB() | |
| model, collater, tokenizer, scheme = checkpoint | |
| tokeinzed_sample, generated_sequence = generate_query_oadm_msa_simple(msa_file.name, model, tokenizer, n_sequences=64, seq_length=seq_len, device='cpu', selection_type='random') | |
| path_to_pdb = predict_protein(generated_sequence) | |
| molhtml = display_pdb(path_to_pdb) | |
| return generated_sequence, molhtml | |
| usg_app = gr.Interface( | |
| fn=make_uncond_seq, | |
| inputs=[ | |
| gr.Slider(10, 100, label = "Sequence Length"), | |
| gr.Dropdown(["EvoDiff-Seq-OADM 38M", "EvoDiff-D3PM-Uniform 38M"], type="value", label = "Model") | |
| ], | |
| outputs=[ | |
| "text", | |
| gr.HTML() | |
| ], | |
| title = "Unconditional sequence generation", | |
| description="Generate a sequence with `EvoDiff-Seq-OADM 38M` (smaller/faster) or `EvoDiff-D3PM-Uniform 38M` (larger/slower) models." | |
| ) | |
| csg_app = gr.Interface( | |
| fn=make_cond_seq, | |
| inputs=[ | |
| gr.Slider(10, 100, label = "Sequence Length"), | |
| gr.File(file_types=["a3m"], label = "MSA File"), | |
| gr.Dropdown(["EvoDiff-MSA"], type="value", label = "Model") | |
| ], | |
| outputs=[ | |
| "text", | |
| gr.HTML() | |
| ], | |
| # examples=[["https://github.com/microsoft/evodiff/raw/main/examples/example_files/bfd_uniclust_hits.a3m"]], | |
| title = "Conditional sequence generation", | |
| description="Evolutionary guided sequence generation with the `EvoDiff-MSA` model." | |
| ) | |
| with gr.Blocks() as edapp: | |
| with gr.Row(): | |
| gr.Markdown( | |
| """ | |
| # EvoDiff | |
| ## Generation of protein sequences and evolutionary alignments via discrete diffusion models | |
| Created By: Microsoft Research [Sarah Alamdari, Nitya Thakkar, Rianne van den Berg, Alex X. Lu, Nicolo Fusi, ProfileAva P. Amini, and Kevin K. Yang] | |
| Spaces App By: [Colby T. Ford](httos://github.com/colbyford) | |
| """ | |
| ) | |
| with gr.Row(): | |
| gr.TabbedInterface([usg_app, csg_app], ["Unconditional sequence generation", "Conditional generation"]) | |
| if __name__ == "__main__": | |
| edapp.launch() |