Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
CSP_Rank/UMAP_TSNE_STATS_medoid.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
153 lines (124 sloc)
5.2 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# UMAP_TSNE_STATS.py | |
from util import * | |
import sys | |
import pymol | |
from pymol import cmd | |
def process_pdb(pdb_file, object_name): | |
# Initialize PyMOL | |
pymol.finish_launching() | |
# Load the PDB file | |
cmd.load(pdb_file, object_name) | |
# Color by chain | |
cmd.color('green', object_name + ' and chain A') | |
cmd.color('cyan', object_name + ' and chain B') | |
# Show chain B as sticks | |
cmd.show('sticks', f'{object_name} and chain B') | |
# Hide ribbon for chain B | |
cmd.hide('cartoon', f'{object_name} and chain B') | |
cmd.orient() | |
cmd.viewport(800, 800) | |
#import matplotlib.pyplot as plt | |
def plot_boxplots(data_dict): | |
""" | |
Plot boxplots for each key:query pair in the dictionary. | |
Parameters: | |
data_dict (dict): Dictionary with integer keys and lists of floats as values. | |
""" | |
# Extract keys and values | |
keys = list(data_dict.keys()) | |
values = list(data_dict.values()) | |
# Create the boxplot | |
plt.figure(figsize=(10, 6)) | |
plt.boxplot(values, labels=keys) | |
# Set plot labels and title | |
plt.xlabel('Keys') | |
plt.ylabel('Values') | |
plt.title('Boxplots for Each Key:Query Pair') | |
# Show plot | |
plt.show() | |
if __name__ == "__main__": | |
if len(sys.argv) != 2: | |
print("Usage: python UMAP_TSNE_STATS.py <bound>") | |
sys.exit(1) | |
bound = sys.argv[1] | |
data_source_file = './CSP_'+bound+'_CSpred.csv' | |
parsed_data = parse_csv(data_source_file) | |
holo_model_files = [data['holo_model_path'][data['holo_model_path'].rfind('/')+1:] for data in parsed_data] | |
holo_model_files_raw = [data['holo_model_path'] for data in parsed_data] | |
consensus_scores = [float(data['consensus']) for data in parsed_data] | |
UMAP_file = './data/'+bound+'_aligned_CSPREDB_UMAP_chain_B_data.csv' | |
UMAP_data = parse_csv(UMAP_file) | |
UMAP_files = [ data['pdb_file'] for data in UMAP_data ] | |
UMAP_clusters = [ int(data['Cluster']) for data in UMAP_data ] | |
TSNE_file = './data/'+bound+'_aligned_CSPREDB_TSNE_chain_B_data.csv' | |
TSNE_data = parse_csv(TSNE_file) | |
TSNE_files = [ data['pdb_file'] for data in TSNE_data ] | |
TSNE_clusters = [ int(data['Cluster']) for data in TSNE_data ] | |
print("getting TSNE cluster scores") | |
TSNE_cluster_scores = {} | |
TSNE_cluster_files = {} | |
for i, pdb_file in enumerate(TSNE_files): | |
cluster_number = TSNE_clusters[i] | |
if cluster_number not in list(TSNE_cluster_scores): | |
TSNE_cluster_scores[cluster_number] = [] | |
TSNE_cluster_files[cluster_number] = [] | |
try: | |
index = holo_model_files.index(pdb_file) | |
except: | |
continue | |
TSNE_cluster_files[cluster_number].append(holo_model_files_raw[index]) | |
TSNE_cluster_scores[cluster_number].append(consensus_scores[index]) | |
#plot_boxplots(TSNE_cluster_scores) | |
print("getting UMAP cluster scores") | |
UMAP_cluster_scores = {} | |
UMAP_cluster_files = {} | |
for i, pdb_file in enumerate(UMAP_files): | |
cluster_number = UMAP_clusters[i] | |
if cluster_number not in list(UMAP_cluster_scores): | |
UMAP_cluster_scores[cluster_number] = [] | |
UMAP_cluster_files[cluster_number] = [] | |
try: | |
index = holo_model_files.index(pdb_file) | |
except: | |
continue | |
UMAP_cluster_files[cluster_number].append(holo_model_files_raw[index]) | |
UMAP_cluster_scores[cluster_number].append(consensus_scores[index]) | |
#plot_boxplots(UMAP_cluster_scores) | |
print("getting TSNE cluster score averages") | |
TSNE_cluster_score_averages = {} | |
for i in list(TSNE_cluster_scores): | |
sum_scores = 0 | |
for j in TSNE_cluster_scores[i]: | |
sum_scores += j | |
sum_scores /= len(TSNE_cluster_scores[i]) | |
TSNE_cluster_score_averages[i] = sum_scores | |
print("getting UMAP cluster score averages") | |
UMAP_cluster_score_averages = {} | |
for i in list(UMAP_cluster_scores): | |
sum_scores = 0 | |
for j in UMAP_cluster_scores[i]: | |
sum_scores += j | |
sum_scores /= len(UMAP_cluster_scores[i]) | |
UMAP_cluster_score_averages[i] = sum_scores | |
def print_sorted_dicts(*dicts): | |
for d in dicts: | |
sorted_dict = {k: round(v, 3) for k, v in sorted(d.items())} | |
for k, v in sorted_dict.items(): | |
print(f"{k}: {v}") | |
print() # Print a newline for better separation between dictionaries | |
print_sorted_dicts(TSNE_cluster_score_averages, UMAP_cluster_score_averages) | |
tSNE_medoid_files = [] | |
print("getting TSNE cluster medoid structures") | |
for itr, i in enumerate(list(TSNE_cluster_files)): | |
medoid_file = find_medoid_structure(TSNE_cluster_files[i]) | |
print("Medoid file for TSNE CLUSTER " + str(i) + " = " + medoid_file) | |
tSNE_medoid_files.append(medoid_file) | |
process_pdb(medoid_file, 'tSNE_' + str(i)) | |
UMAP_medoid_files = [] | |
print("getting UMAP cluster medoid structures") | |
for itr,i in enumerate(list(UMAP_cluster_files)): | |
medoid_file = find_medoid_structure(UMAP_cluster_files[i]) | |
print("Medoid file for UMAP CLUSTER " + str(i) + " = " + medoid_file) | |
UMAP_medoid_files.append(medoid_file) | |
process_pdb(medoid_file, 'UMAP_' + str(i)) | |
cmd.hide('everything', 'hydro') |