Newer
Older
"execution_count": 2,
"id": "f76b47d6",
"metadata": {},
"outputs": [],
"source": [
"import mdtraj as md\n",
"import os\n",
"import numpy as np\n",
"from ipywidgets import widgets\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"import pandas as pd\n",
"import itertools\n",
"from tqdm import tqdm \n",
"import ot\n",
"import MDAnalysis"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1219123d-f44f-4e08-9e71-4dc45cd81ced",
"metadata": {},
"outputs": [],
"source": [
"def multiframe_pdb_to_xtc(pdb_file, save_path, prot_name):\n",
" \n",
" u = MDAnalysis.core.universe.Universe(pdb_file)\n",
" at = u.atoms\n",
" \n",
" os.chdir(save_path)\n",
" \n",
" # Write the trajectory in .xtc format\n",
" at.write(\".\".join([prot_name,'xtc']), frames='all')\n",
" # Write a frame of the trajectory in .pdb format for topology information\n",
" at.write(\".\".join([prot_name,'pdb']))"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "6f669fe3",
"metadata": {},
"outputs": [],
"source": [
"def get_cluster_files(ensemble_path, ensemble_name, labels_umap):\n",
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
" \n",
" # Initial parameters\n",
" var_dict = {'multiframe' : 'n', 'check_folder' : True, 'do_xtc' : False, 'do_pdb' : False,\n",
" 'ensemble_name' : ensemble_name, 'ensemble_path' : ensemble_path}\n",
" \n",
" var_dict['xtc_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".xtc\")] \n",
" var_dict['pdb_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".pdb\") or file.endswith(\".prmtop\") or file.endswith(\".parm7\") or file.endswith(\".gro\")]\n",
" var_dict['folders'] = [file for file in os.listdir(ensemble_path) if (os.path.isdir(\"/\".join([ensemble_path,file])) and not file.startswith('.') and not file.startswith(\"results\"))]\n",
" \n",
" # File processing\n",
" \n",
" if len(var_dict[\"xtc_files\"]) + len(var_dict[\"folders\"]) + len(var_dict[\"pdb_files\"]) == 0:\n",
" sys.exit(\"\".join(['Folder for ', var_dict[\"ensemble_name\"], ' ensemble is empty...']))\n",
" \n",
" # .xtc file with a .pdb topology file\n",
" \n",
" if len(var_dict[\"xtc_files\"]) >= len(var_dict[\"pdb_files\"]) and len(var_dict[\"pdb_files\"]) == 1:\n",
"\n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([str(var_dict[\"xtc_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],',']))\n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : topology file of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"xtc_files\"]) > 1:\n",
" print(\"\\nMore than one .xtc file were found. Taking the first as the trajectory file.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = var_dict[\"ensemble_path\"]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # multiframe .pdb files\n",
" \n",
" if var_dict['multiframe'] == 'y' or (len(var_dict[\"pdb_files\"]) >= 1 and len(var_dict[\"xtc_files\"]) == 0):\n",
" \n",
" print('\\nTaking as input:\\n') \n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"pdb_files\"]) > 1:\n",
" print(\"\\nMore than one multiframe .pdb file were found. Taking the first as the trajectory file.\\n\")\n",
" print(\"\\nTaking the previously converted files.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = \"/\".join([var_dict[\"ensemble_path\"],'converted_files'])\n",
" var_dict[\"xtc_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".xtc\")]\n",
" var_dict[\"pdb_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".pdb\")]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # folder with .pdb files\n",
" \n",
" if len(var_dict[\"folders\"]) >= 1 and var_dict['check_folder'] == True:\n",
" \n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([var_dict[\"folders\"][0],' folder contains: trajectory of ',var_dict[\"ensemble_name\"],\".\"]))\n",
" if len(var_dict[\"folders\"]) > 1:\n",
" print(\"\\nMore than one .pdb folder were found. Taking the first as the trajectory folder.\\n\")\n",
" var_dict[\"do_pdb\"] = True\n",
" \n",
" if not var_dict[\"do_pdb\"] and not var_dict[\"do_xtc\"]:\n",
" sys.exit(\"\".join(['\\n Sorry, I did not understood the input. Please follow the guidelines described in the function documentation to create ',ensemble_name,' folder.\\n'])) \n",
" \n",
" print(\"\\n----------------------------------------------------------------------------------\\n\")\n",
" print(\"\\nCreating cluster-specific files...\\n\")\n",
" \n",
" results_path = \"/\".join([os.path.abspath(ensemble_path),\"_\".join(['results',ensemble_name])])\n",
" save_files = \"/\".join([results_path, \"cluster_files\"])\n",
" if not os.path.exists(save_files):\n",
" os.mkdir(save_files)\n",
" \n",
" if var_dict[\"do_xtc\"]:\n",
" \n",
" traj_file = md.load_xtc(\"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"xtc_files\"][0]]), top = \"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"pdb_files\"][0]]))\n",
" \n",
" # Save .xtc cluster files\n",
" for k in tqdm(range(len(np.unique(labels_umap[labels_umap >= 0])))):\n",
" traj_file[np.where(labels_umap == k)].save_xtc(\"/\".join([save_files, \"\".join([ensemble_name,'_',str(k),'.xtc'])]))\n",
"\n",
" if var_dict[\"do_pdb\"]:\n",
" \n",
" conf_list = os.listdir(\"/\".join([var_dict[\"ensemble_path\"],var_dict[\"folders\"][0]]))\n",
"\n",
" for k in tqdm(range(len(np.unique(labels_umap[labels_umap >= 0])))):\n",
" clus_k_path = \"/\".join([save_files, \"_\".join(['clus',str(k)])])\n",
" if not os.path.exists(clus_k_path):\n",
" os.mkdir(clus_k_path)\n",
" \n",
" clus_k = np.where(labels_umap == k)[0]\n",
" for j in range(len(clus_k)):\n",
" traj = md.load_pdb(\"/\".join([\"/\".join([var_dict[\"ensemble_path\"],var_dict[\"folders\"][0]]),conf_list[clus_k[j]]]))\n",
" traj.save_pdb(\"/\".join([clus_k_path, \"\".join([ensemble_name,'_',str(clus_k[j]),'.pdb'])]))\n",
"\n",
" print(\"\\nFiles saved.\\n\") "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "ff9c4941",
"metadata": {},
"outputs": [],
"source": [
"def plot_2umap(embedding_2d, labels_umap, ensemble_name, results_path):\n",
" classified = np.where(labels_umap >= 0)[0]\n",
" \n",
" output1 = widgets.Output()\n",
" with output1:\n",
" fig, ax = plt.subplots()\n",
" ax.scatter(embedding_2d[~classified, 0],\n",
" embedding_2d[~classified, 1],\n",
" color=(0.5, 0.5, 0.5),\n",
" s=0.5,\n",
" alpha=0.5)\n",
" scatter = ax.scatter(embedding_2d[classified, 0],\n",
" embedding_2d[classified, 1],\n",
" s=0.5,\n",
" alpha = 1,\n",
" cmap='Spectral')\n",
" plt.xlabel('UMAP coordinate 1')\n",
" plt.ylabel('UMAP coordinate 2')\n",
" plt.title(\"\".join(['UMAP 2-dimensional projection after contact clustering for ',ensemble_name,' ensemble']), fontsize = 8)\n",
" plt.savefig(\"/\".join([results_path, \"\".join([\"clusters_2d\", ensemble_name, '.png'])]), dpi = 199)\n",
" plt.show()\n",
"\n",
" output2 = widgets.Output()\n",
" with output2:\n",
" repartition = pd.Series(labels_umap).value_counts()\n",
" repartition.index = [\"Unclassified\" if i == -1 else i for i in repartition.index]\n",
" display(pd.DataFrame({\"Cluster\" : np.array(repartition.index), \"Occupancy (%)\" : 100*np.array(repartition.values)/len(labels_umap)}))\n",
" two_columns = widgets.HBox([output1, output2])\n",
" display(two_columns)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "00dfbe24",
"metadata": {},
"outputs": [],
"source": [
"def get_wmaps(wcont_data, labels_umap, ensemble_name, results_path, subsequence = None):\n",
" \n",
" maps_path = \"/\".join([results_path,\"wcont_maps\"]) # Path to save files\n",
" if not os.path.exists(maps_path): # Create if doesn't exist\n",
" os.mkdir(maps_path)\n",
" \n",
" L = int(0.5*(1+np.sqrt(1+8*wcont_data.shape[1]))) # Sequence length\n",
" list_pos = np.asarray(list(itertools.combinations(range(1,L+1), 2))) # List of position pairs\n",
" \n",
" repartition = pd.Series(labels_umap).value_counts() # Clustering partition\n",
" repartition.index = [\"Unclassified\" if i == -1 else i for i in repartition.index]\n",
" repartition = repartition.drop(\"Unclassified\")\n",
" cont_data = np.zeros([len(repartition),len(list_pos)+1])\n",
" \n",
" for cluster in tqdm(repartition.index): \n",
" \n",
" # Cluster-specific w-contact matrix\n",
" prop_cluster = pd.Series(labels_umap).value_counts().sort_index()[cluster]/np.shape(wcont_data)[0]\n",
" cont_matrix = pd.DataFrame(np.concatenate([list_pos,np.asarray([wcont_data.loc[labels_umap == cluster,].mean()]).T], axis = 1), columns=['pos1','pos2','cp'])\n",
" cont_matrix.pos1 = cont_matrix.pos1.astype(int)\n",
" cont_matrix.pos2 = cont_matrix.pos2.astype(int)\n",
" cont_data[np.where(repartition.index == cluster)[0][0],:] = np.append(cont_matrix.cp.to_numpy(), prop_cluster)\n",
" cont_matrix = cont_matrix.pivot(index='pos1',columns='pos2',values='cp')\n",
"\n",
" if subsequence is not None:\n",
"\n",
" list_pos = list_pos - 1\n",
" cont_matrix.index = np.unique(subsequence[list_pos[:,0]]).astype(int)\n",
" cont_matrix.columns = np.unique(subsequence[list_pos[:,1]]).astype(int)\n",
" \n",
" fig = plt.figure()\n",
" res = sns.heatmap(cont_matrix.T, cmap='Reds',square=True, cbar_kws={\"shrink\": .5,'label':\"Contact weight average\"})\n",
" plt.suptitle(\" \".join([ensemble_name,'contact-based clustering']), fontsize=10)\n",
" plt.title(\"\".join(['Cluster #',str(cluster),' with ',str(round(100*prop_cluster,2)),'% of occupation']), fontsize = 8)\n",
"\n",
" plt.xlabel('Sequence position')\n",
" plt.ylabel('Sequence position')\n",
" plt.xticks(rotation=0)\n",
" res.set_xticklabels(res.get_xmajorticklabels(), fontsize = 6)\n",
" res.set_yticklabels(res.get_ymajorticklabels(), fontsize = 6)\n",
" plt.savefig(\"/\".join([maps_path,\"\".join([ensemble_name,'_',str(cluster),'.png'])]), dpi=199) # Save figure in \n",
"\n",
" np.save(\"/\".join([results_path,\"\".join([ensemble_name,'_contdata'])]),cont_data)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "a4c98c97",
"metadata": {},
"outputs": [],
"source": [
"def representative_ensemble(size, ensemble_path, ensemble_name, labels_umap):\n",
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
" \n",
" # Initial parameters\n",
" var_dict = {'multiframe' : 'n', 'check_folder' : True, 'do_xtc' : False, 'do_pdb' : False,\n",
" 'ensemble_name' : ensemble_name, 'ensemble_path' : ensemble_path}\n",
" \n",
" var_dict['xtc_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".xtc\")] \n",
" var_dict['pdb_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".pdb\") or file.endswith(\".prmtop\") or file.endswith(\".parm7\") or file.endswith(\".gro\")]\n",
" var_dict['folders'] = [file for file in os.listdir(ensemble_path) if (os.path.isdir(\"/\".join([ensemble_path,file])) and not file.startswith('.') and not file.startswith(\"results\"))]\n",
" \n",
" # File processing\n",
" \n",
" if len(var_dict[\"xtc_files\"]) + len(var_dict[\"folders\"]) + len(var_dict[\"pdb_files\"]) == 0:\n",
" sys.exit(\"\".join(['Folder for ', var_dict[\"ensemble_name\"], ' ensemble is empty...']))\n",
" \n",
" # .xtc file with a .pdb topology file\n",
" \n",
" if len(var_dict[\"xtc_files\"]) >= len(var_dict[\"pdb_files\"]) and len(var_dict[\"pdb_files\"]) == 1:\n",
"\n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([str(var_dict[\"xtc_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],',']))\n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : topology file of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"xtc_files\"]) > 1:\n",
" print(\"\\nMore than one .xtc file were found. Taking the first as the trajectory file.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = var_dict[\"ensemble_path\"]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # multiframe .pdb files\n",
" \n",
" if var_dict['multiframe'] == 'y' or (len(var_dict[\"pdb_files\"]) >= 1 and len(var_dict[\"xtc_files\"]) == 0):\n",
" \n",
" print('\\nTaking as input:\\n') \n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"pdb_files\"]) > 1:\n",
" print(\"\\nMore than one multiframe .pdb file were found. Taking the first as the trajectory file.\\n\")\n",
" print(\"\\nTaking the previously converted files.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = \"/\".join([var_dict[\"ensemble_path\"],'converted_files'])\n",
" var_dict[\"xtc_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".xtc\")]\n",
" var_dict[\"pdb_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".pdb\")]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # folder with .pdb files\n",
" \n",
" if len(var_dict[\"folders\"]) >= 1 and var_dict['check_folder'] == True:\n",
" \n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([var_dict[\"folders\"][0],' folder contains: trajectory of ',var_dict[\"ensemble_name\"],\".\"]))\n",
" if len(var_dict[\"folders\"]) > 1:\n",
" print(\"\\nMore than one .pdb folder were found. Taking the first as the trajectory folder.\\n\")\n",
" var_dict[\"do_pdb\"] = True\n",
" \n",
" if not var_dict[\"do_pdb\"] and not var_dict[\"do_xtc\"]:\n",
" sys.exit(\"\".join(['\\n Sorry, I did not understood the input. Please follow the guidelines described in the function documentation to create ',ensemble_name,' folder.\\n'])) \n",
" \n",
" print(\"\\n----------------------------------------------------------------------------------\\n\")\n",
" print(\"\\nSampling representative family...\\n\")\n",
" \n",
" repartition = pd.Series(labels_umap).value_counts() # Clustering partition\n",
" repartition.index = [\"Unclassified\" if i == -1 else i for i in repartition.index]\n",
" repartition = repartition.drop(\"Unclassified\")\n",
" probas = repartition.values/np.sum(repartition.values)\n",
"\n",
" selected_conf = np.zeros(size)\n",
" for i in range(size):\n",
"\n",
" choose_cluster = np.random.choice(repartition.index, size = 1, p = probas)[0]\n",
" selected_conf[i] = np.random.choice(np.where(labels_umap == choose_cluster)[0], size = 1)[0]\n",
" \n",
" selected_conf = np.ndarray.astype(selected_conf, int)\n",
" results_path = \"/\".join([os.path.abspath(ensemble_path),\"_\".join(['results',ensemble_name])])\n",
" save_files = \"/\".join([results_path, \"representative_family\"])\n",
" if not os.path.exists(save_files):\n",
" os.mkdir(save_files)\n",
" \n",
" if var_dict[\"do_xtc\"]:\n",
" \n",
" traj_file = md.load_xtc(\"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"xtc_files\"][0]]), top = \"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"pdb_files\"][0]]))\n",
" \n",
" # Save .xtc file\n",
" traj_file[selected_conf].save_xtc(\"/\".join([save_files, \"\".join([ensemble_name,'_repfam.xtc'])]))\n",
"\n",
" if var_dict[\"do_pdb\"]:\n",
" \n",
" conf_list = os.listdir(\"/\".join([var_dict[\"ensemble_path\"],var_dict[\"folders\"][0]]))\n",
" # Save pdb folder\n",
" for j in selected_conf:\n",
" traj = md.load_pdb(\"/\".join([\"/\".join([var_dict[\"ensemble_path\"],var_dict[\"folders\"][0]]),conf_list[j]]))\n",
" traj.save_pdb(\"/\".join([save_files, \"\".join([ensemble_name,'_',conf_list[j],'.pdb'])]))\n",
"\n",
" print(\"\\nFiles saved.\\n\") "
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "7069e00f",
"metadata": {},
"outputs": [],
"source": [
"def cluster_descriptors(ensemble_path, ensemble_name, labels_umap):\n",
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
" \n",
" # Initial parameters\n",
" var_dict = {'multiframe' : 'n', 'check_folder' : True, 'do_xtc' : False, 'do_pdb' : False,\n",
" 'ensemble_name' : ensemble_name, 'ensemble_path' : ensemble_path}\n",
" \n",
" var_dict['xtc_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".xtc\")] \n",
" var_dict['pdb_files'] = [file for file in os.listdir(ensemble_path) if file.endswith(\".pdb\") or file.endswith(\".prmtop\") or file.endswith(\".parm7\") or file.endswith(\".gro\")]\n",
" var_dict['folders'] = [file for file in os.listdir(ensemble_path) if (os.path.isdir(\"/\".join([ensemble_path,file])) and not file.startswith('.') and not file.startswith(\"results\"))]\n",
" \n",
" # File processing\n",
" \n",
" if len(var_dict[\"xtc_files\"]) + len(var_dict[\"folders\"]) + len(var_dict[\"pdb_files\"]) == 0:\n",
" sys.exit(\"\".join(['Folder for ', var_dict[\"ensemble_name\"], ' ensemble is empty...']))\n",
" \n",
" # .xtc file with a .pdb topology file\n",
" \n",
" if len(var_dict[\"xtc_files\"]) >= len(var_dict[\"pdb_files\"]) and len(var_dict[\"pdb_files\"]) == 1:\n",
"\n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([str(var_dict[\"xtc_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],',']))\n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : topology file of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"xtc_files\"]) > 1:\n",
" print(\"\\nMore than one .xtc file were found. Taking the first as the trajectory file.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = var_dict[\"ensemble_path\"]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # multiframe .pdb files\n",
" \n",
" if var_dict['multiframe'] == 'y' or (len(var_dict[\"pdb_files\"]) >= 1 and len(var_dict[\"xtc_files\"]) == 0):\n",
" \n",
" print('\\nTaking as input:\\n') \n",
" print(\"\".join([str(var_dict[\"pdb_files\"][0]),' : trajectory of ',var_dict[\"ensemble_name\"],'.']))\n",
" if len(var_dict[\"pdb_files\"]) > 1:\n",
" print(\"\\nMore than one multiframe .pdb file were found. Taking the first as the trajectory file.\\n\")\n",
" print(\"\\nTaking the previously converted files.\\n\")\n",
" var_dict[\"do_xtc\"] = True\n",
" var_dict[\"xtc_root_path\"] = \"/\".join([var_dict[\"ensemble_path\"],'converted_files'])\n",
" var_dict[\"xtc_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".xtc\")]\n",
" var_dict[\"pdb_files\"] = [file for file in os.listdir(var_dict[\"xtc_root_path\"]) if file.endswith(\".pdb\")]\n",
" var_dict['check_folder'] = False\n",
" \n",
" # folder with .pdb files\n",
" \n",
" if len(var_dict[\"folders\"]) >= 1 and var_dict['check_folder'] == True:\n",
" \n",
" print('\\nTaking as input:\\n')\n",
" print(\"\".join([var_dict[\"folders\"][0],' folder contains: trajectory of ',var_dict[\"ensemble_name\"],\".\"]))\n",
" if len(var_dict[\"folders\"]) > 1:\n",
" print(\"\\nMore than one .pdb folder were found. Taking the first as the trajectory folder.\\n\")\n",
" var_dict[\"do_pdb\"] = True\n",
" \n",
" if not var_dict[\"do_pdb\"] and not var_dict[\"do_xtc\"]:\n",
" sys.exit(\"\".join(['\\n Sorry, I did not understood the input. Please follow the guidelines described in the function documentation to create ',ensemble_name,' folder.\\n'])) \n",
" \n",
" print(\"\\n----------------------------------------------------------------------------------\\n\")\n",
" print(\"\\nComputing cluster-specific descriptors...\\n\")\n",
" \n",
" results_path = \"/\".join([os.path.abspath(ensemble_path),\"_\".join(['results',ensemble_name])])\n",
" save_files = \"/\".join([results_path, \"cluster_descriptors\"])\n",
" if not os.path.exists(save_files):\n",
" os.mkdir(save_files)\n",
" \n",
" if var_dict[\"do_xtc\"]:\n",
" \n",
" traj_file = md.load_xtc(\"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"xtc_files\"][0]]), top = \"/\".join([var_dict[\"xtc_root_path\"],var_dict[\"pdb_files\"][0]]))\n",
" L = traj_file.n_residues\n",
" Nconf = traj_file.n_frames\n",
" \n",
" dssp_types = ['H','B','E','G','I','T','S',' ']\n",
" prop_dssp = np.zeros([len(dssp_types),L,len(labels_umap)-1])\n",
" rg = np.zeros([len(labels_umap)-1])\n",
" for k in range(len(np.unique(labels_umap[labels_umap >= 0]))):\n",
" \n",
" prop_dssp_k = np.zeros([len(dssp_types),L])\n",
" dssp_k = md.compute_dssp(traj_file[np.where(labels_umap == k)], simplified = False)\n",
" rg[k] = np.mean(md.compute_rg(traj_file[np.where(labels_umap == k)]))\n",
" prop_dssp_k[dt,:] = (dssp_k == dssp_types[dt]).sum(axis = 0)/len(np.where(labels_umap == k)[0])\n",
" prop_dssp[:,:,k] = prop_dssp_k\n",
"\n",
" if var_dict[\"do_pdb\"]:\n",
" \n",
" conf_list = os.listdir(var_dict[\"folders\"][0])\n",
" md_file = md.load_pdb(\"/\".join([var_dict[\"folders\"][0],conf_list[0]]))\n",
" L = md_file.topology.n_residues\n",
" Nconf = len(conf_list)\n",
" \n",
" dssp_types = ['H','B','E','G','I','T','S',' ']\n",
" prop_dssp = np.zeros([len(dssp_types),L,len(labels_umap)-1])\n",
" rg = np.zeros([len(labels_umap)-1])\n",
" for k in range(len(np.unique(labels_umap[labels_umap >= 0]))):\n",
" \n",
" prop_dssp_k = np.zeros([len(dssp_types),L])\n",
" clus_k = np.where(labels_umap == k)[0]\n",
" dssp_k = np.zeros([len(clus_k),L]).astype(str)\n",
" rg_k = np.zeros([len(clus_k)])\n",
"\n",
" for l in range(len(clus_k)):\n",
" dssp_k[l,:] = md.compute_dssp(md.load_pdb(\"/\".join([pdb_folder,conf_list[clus_k[l]]])), simplified = False)[0].astype(str)\n",
" rg_k[l] = md.compute_rg(md.load_pdb(\"/\".join([pdb_folder,conf_list[clus_k[l]]])))\n",
" rg[k] = np.mean(rg_k)\n",
" for dt in range(len(dssp_types)):\n",
" prop_dssp_k[dt,:] = (dssp_k == dssp_types[dt]).sum(axis = 0)/len(np.where(labels_umap == k)[0])\n",
" for cluster in tqdm(range(len(np.unique(labels_umap[labels_umap >= 0])))):\n",
" prop_cluster = round(100*len(np.where(labels_umap == cluster)[0])/Nconf,2)\n",
" fig = plt.figure(figsize=(10, 1.7))\n",
" res = sns.heatmap(prop_dssp[:,:,cluster], cmap='Blues', square = True, cbar_kws={\"shrink\": .7,'label':\"Class prop.\"})\n",
" xlabels = [item.get_text() for item in res.get_xmajorticklabels()]\n",
" plt.xlabel('Sequence position')\n",
" plt.ylabel('DSSP class')\n",
" plt.title(\"\".join([ensemble_name, ' - cluster #',str(cluster),' (',str(prop_cluster),'% oc.). Average RG = ', str(round(10*rg[cluster],2)),r'$\\AA$.']), fontsize = 8)\n",
" plt.yticks(rotation=0) \n",
" res.set_xticklabels(np.asarray(xlabels).astype(int) + 1, fontsize = 7)\n",
" res.set_yticklabels(['L' if x==' ' else x for x in dssp_types], fontsize = 7)\n",
" plt.savefig(\"/\".join([save_files,\"\".join([ensemble_name,'_',str(cluster),'_DSSP.png'])]), dpi=199, bbox_inches='tight')\n",
"\n",
" \n",
" print(\"\\nPlots saved.\\n\") "
]
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
},
{
"cell_type": "code",
"execution_count": null,
"id": "cc23916d-784e-4204-ab55-2ee8179cc317",
"metadata": {},
"outputs": [],
"source": [
"def compare_families(path_a, path_b, ensemble_name_a, ensemble_name_b):\n",
" \n",
" contmatrix_a = np.load('/'.join([path_a, \"_\".join([ensemble_name_a,'contdata.npy'])]))\n",
" contmatrix_b = np.load('/'.join([path_b, \"_\".join([ensemble_name_b,'contdata.npy'])]))\n",
"\n",
" a = np.delete(contmatrix_a, -1, axis = 1)\n",
" ma = contmatrix_a[:,-1]/np.sum(contmatrix_a[:,-1])\n",
" b = np.delete(contmatrix_b, -1, axis = 1)\n",
" mb = contmatrix_b[:,-1]/np.sum(contmatrix_b[:,-1])\n",
" \n",
" if np.shape(a)[1] != np.shape(b)[1]:\n",
" quit('Both sequences must have the same number of residues.')\n",
"\n",
" M = ot.dist(a, b, metric = 'sqeuclidean') # Cost matrix\n",
" clean = ot.utils.clean_zeros(ma, mb, M)\n",
" w = np.sqrt(ot.emd2(clean[0], clean[1], clean[2])) # 2-Wasserstein distance\n",
" return w"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}