Spaces:
Sleeping
Sleeping
| from pyuul_kmeans import VolumeMaker | |
| from pyuul_kmeans import utils | |
| import os | |
| import zipfile | |
| import pathlib | |
| from sklearn.cluster import KMeans | |
| from collections import OrderedDict | |
| import numpy as np | |
| import pandas as pd | |
| import random | |
| import torch | |
| import os | |
| import shutil | |
| import gradio as gr | |
| # 设置随机数种子 | |
| def setup_seed(seed): | |
| torch.manual_seed(seed) | |
| torch.cuda.manual_seed_all(seed) | |
| np.random.seed(seed) | |
| random.seed(seed) | |
| torch.backends.cudnn.deterministic = True | |
| setup_seed(100) | |
| device = "cpu" | |
| def add_file_to_folder(new_file_path, folder): | |
| ls = os.listdir(new_file_path) | |
| for line in ls: | |
| filePath = os.path.join(new_file_path, line) | |
| if os.path.isfile(filePath): | |
| shutil.copy(filePath, folder) | |
| def copy(files,folder): | |
| file = os.listdir(folder) | |
| for i in file: | |
| if i not in files: | |
| file_path = os.path.join(folder, i) | |
| os.remove(file_path) | |
| def pyuul(folder,n_clusters): | |
| PDBFile = str(folder) | |
| coords, atname, pdbname, pdb_num = utils.parsePDB(PDBFile) | |
| atoms_channel = utils.atomlistToChannels(atname) | |
| radius = utils.atomlistToRadius(atname) | |
| PointCloudSurfaceObject = VolumeMaker.PointCloudVolume(device=device) | |
| coords = coords.to(device) | |
| radius = radius.to(device) | |
| atoms_channel = atoms_channel.to(device) | |
| SurfacePoitCloud = PointCloudSurfaceObject(coords, radius) | |
| feature = SurfacePoitCloud.view(pdb_num,-1).cpu() | |
| kmean = KMeans(n_clusters=n_clusters,n_init=10,init="k-means++",random_state=100) | |
| y = kmean.fit_predict(feature) | |
| pairs = zip(pdbname, y) | |
| result_dict = {key: value for key, value in pairs} | |
| ligend_class = result_dict['ligend.pdb'] | |
| sheet = [] | |
| for key, value in result_dict.items(): | |
| if value == ligend_class: | |
| sheet.append(key) | |
| return sheet | |
| def kmeans(ligend,n_clusters,n_num): | |
| azip = zipfile.ZipFile("peptides.zip") | |
| azip.extractall() | |
| peptide_folder_path = pathlib.Path(__file__).parent.joinpath("peptides" ) | |
| pdb_folder = pathlib.Path(__file__).parent.joinpath("temp") | |
| ligend_path = ligend.name | |
| shutil.copy(ligend_path,pdb_folder) | |
| n_num = int(n_num) | |
| n_clusters = int(n_clusters) | |
| for i in range(1,n_num+1): | |
| if i == 1: | |
| add_file_to_folder(peptide_folder_path,pdb_folder) | |
| output = pyuul(pdb_folder, n_clusters) | |
| copy(output,pdb_folder) | |
| else: | |
| if pdb_folder != None: | |
| output = pyuul(pdb_folder, n_clusters) | |
| copy(output,pdb_folder) | |
| data = OrderedDict() | |
| data['Name'] = output | |
| data = pd.DataFrame(data) | |
| data.to_csv('outputs.csv', index=False) | |
| shutil.rmtree(pdb_folder) | |
| os.mkdir(pdb_folder) | |
| return 'outputs.csv' | |
| with open(metadata_root.joinpath("pyuul_kmeans.md"), "r") as f: | |
| description = f.read() | |
| iface = gr.Interface(fn=kmeans, | |
| title="Pyuul_Kmeans", | |
| inputs=["file", | |
| gr.Textbox(label="n_clusters", placeholder="2", lines=1), | |
| gr.Textbox(label="Times", placeholder="2", lines=1) | |
| ], | |
| outputs= "file", | |
| description=description | |
| ) | |
| iface.launch() | |