[数据科学] 通过基因表达监测进行肿瘤预测

简介

通过基因表达监测（DNA微阵列）对新的癌症病例进行分类，从而为鉴定新的癌症类别和将肿瘤分配到已知类别提供了一般方法。这些数据用于对患有急性髓性白血病（AML）和急性淋巴细胞白血病（ALL）的患者进行分类。

代码实例

导入依赖库

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inlineimport numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline      

载入数据

labels_df = pd.read_csv('actual.csv', index_col = 'patient')
test_df = pd.read_csv('data_set_ALL_AML_independent.csv')
data_df = pd.read_csv('data_set_ALL_AML_train.csv')
print('train_data: ',  data_df.shape, '\n test_data: ',  test_df.shape, '\n labels: ', labels_df.shape)
# labels_df.shape
data_df.head()   #查看前5行（默认前5行）      

清理数据

test_cols_to_drop = [c for c in test_df.columns if 'call' in c]
test_df = test_df.drop(test_cols_to_drop, axis=1)
test_df = test_df.drop(['Gene Description', 'Gene Accession Number'], axis=1 )
 
data_cols_to_drop = [c for c in data_df.columns if 'call' in c]
data_df = data_df.drop(data_cols_to_drop, axis=1)
data_df = data_df.drop(['Gene Description', 'Gene Accession Number'], axis=1 )
print('train_data ', data_df.shape, '\n test_data: ',  test_df.shape,  '\n labels: ', labels_df.shape)
data_df.head()      

定义'特征'和'样本'

使用基因表达值来预测癌症类型。 因此，特征是患者的基因和样本。 使用X作为输入数据，其中行是样本（患者），列是特征（基因）。

将'ALLL'替换为0，将'AML'替换为1。

labels_df = labels_df.replace({'ALL':0, 'AML':1})
train_labels = labels_df[labels_df.index <= 38]
test_labels = labels_df[labels_df.index > 38]
print(train_labels.shape, test_labels.shape)
# labels_df.index
test_df = test_df.T
train_df = data_df.T      

检查空值

print('Columns containing null values in train and test data are ', data_df.isnull().values.sum(),  test_df.isnull().values.sum())      

联合训练集和测试集

full_df = train_df.append(test_df, ignore_index=True)
print(full_df.shape)
full_df.head()      

标准化和处理高维度

标准化

所有变量具有非常相似的范围的方式重新调整我们的变量（预测变量）。

高维度

只有72个样本和7000多个变量。 意味着如果采取正确的方法，模型很可能会受到HD的影响。 一个非常常见的技巧是将数据投影到较低维度空间，然后将其用作新变量。 最常见的尺寸减小方法是PCA。

# Standardization
from sklearn import preprocessing
X_std = preprocessing.StandardScaler().fit_transform(full_df)
# Check how the standardized data look like
gene_index = 1
print('mean is : ',  np.mean(X_std[:, gene_index] ) )
print('std is :', np.std(X_std[:, gene_index]))
 
fig= plt.figure(figsize=(10,10))
plt.hist(X_std[:, gene_index], bins=10)
plt.xlim((-4, 4))
plt.xlabel('rescaled expression', size=30)
plt.ylabel('frequency', size=30)      

PCA(聚类分析)

# PCA
 
from sklearn.decomposition import PCA
pca = PCA(n_components=50, random_state=42)
X_pca = pca.fit_transform(X_std)
print(X_pca.shape)      

cum_sum = pca.explained_variance_ratio_.cumsum()
cum_sum = cum_sum*100
 
fig = plt.figure(figsize=(10,10))
plt.bar(range(50), cum_sum)
plt.xlabel('PCA', size=30)
plt.ylabel('Cumulative Explained Varaince', size=30)
plt.title("Around 90% of variance is explained by the First 50 columns ", size=30)      

labels = labels_df['cancer'].values
 
colors = np.where(labels==0, 'red', 'blue')
 
 
from mpl_toolkits.mplot3d import Axes3D
plt.clf()
fig = plt.figure(1, figsize=(15,15 ))
ax = Axes3D(fig, elev=-150, azim=110,)
ax.scatter(X_pca[:, 0], X_pca[:, 1], X_pca[:, 2], c=colors, cmap=plt.cm.Paired,linewidths=10)
ax.set_title("First three PCA directions")
ax.set_xlabel("PCA1")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("PCA2")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("PCA3")
ax.w_zaxis.set_ticklabels([])
plt.show()      

RF分类

X = X_pca
y = labels
print(X.shape, y.shape)      

划分训练集和测试集

from sklearn.model_selection import train_test_split
 
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
print(X_train.shape, y_train.shape)      

import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
rfc = RandomForestClassifier(random_state=42)
rfc.fit(X_train, y_train)
y_pred = rfc.predict(X_test)
print(accuracy_score(y_test, y_pred))      

0.7083333333333334      

重要特征

labs = ['PCA'+str(i+1) for i in range(X_train.shape[1])]
importance_df = pd.DataFrame({
    'feature':labs,
    'importance': rfc.feature_importances_
})
 
importance_df_sorted = importance_df.sort_values('importance', ascending=False)
importance_df_sorted.head()
 
fig = plt.figure(figsize=(25,10))
sns.barplot(data=importance_df_sorted, x='feature', y='importance')
plt.xlabel('PCAs', size=30)
plt.ylabel('Feature Importance', size=30)
plt.title('RF Feature Importance', size=30)
plt.savefig('RF Feature Importance.png', dpi=300)
plt.show      

Confusion Matrix（混淆矩阵）

Gradient Boost Classifier（梯度增强分类器）

from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
### Normalize cm, np.newaxis makes to devide each row by the sum
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
 
 
print(np.newaxis)
cmap=plt.cm.Blues
 
plt.imshow(cm, interpolation='nearest', cmap=cmap)
print(cm)      

from sklearn.ensemble import GradientBoostingClassifier
gbc = GradientBoostingClassifier(random_state=42)
gbc.fit(X_train, y_train)
y_gbc_pred = gbc.predict(X_test)
print(accuracy_score(y_test, y_gbc_pred))      

0.7083333333333334