基于主成分分析和聚类探索化学空间
PCA :Principal Component Analysis
分析化合物数据库,发现它们之间的共享描述符(物理化学特性)。
1. 导入库
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import gridspec
from rdkit import Chem, DataStructs
from rdkit.Chem import Descriptors,Crippen
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
import matplotlib.cm as cm
from sklearn.metrics import silhouette_samples, silhouette_score
from sklearn.cluster import