1.3.Helps
0) 编程工具介绍
#导入必需的库
import gc, argparse, sys, os, errno
%pylab inline
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import NearestNeighbors
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_curve, auc
from tqdm import tqdm_notebook as tqdm
from scipy.stats import pearsonr
import warnings
warnings.filterwarnings('ignore')
#绘图设置
styles = ["white","dark",'whitegrid',"darkgrid"]
contexts = ['paper','talk','poster','notebook']
sns.set_context(contexts[1])
sns.set_style(styles[2])
tableau20 = np.array([(31, 119, 180), (174, 199, 232), (255, 127, 14), (255, 187, 120),
(44, 160, 44), (152, 223, 138), (214, 39, 40), (255, 152, 150),
(148, 103, 189), (197, 176, 213), (140, 86, 75), (196, 156, 148),
(227, 119, 194), (247, 182, 210), (127, 127, 127), (199, 199, 199),
(188, 189, 34), (219, 219, 141), (23, 190, 207), (158, 218, 229)])/255.1) Reads Processing and Mapping 指南

1a) Data Structure
1b) Running Steps
1b.1) 获取数据
1b.2) QC-Trim-QC
1b.3) Clean rRNA reads
1b.4) Sequential Mapping
1b.5) length & ratio
2) Construct Expression Matrix 指南
2a) Data Structure
2b) Running Scripts
2b.1) Software/Tools
2b.2) FeatureCounts
2c) Merge不同RNA类型的Raw Counts
2d) 检查结果正确性
2e) 使用Domain Feature(选做)

3) 数据分析和质量控制指南
3a) 基本信息统计







3b) 代码示例
3c) sample QC

4) 矩阵处理指南
4a) 相关教程
4b) Data Normalization

4c) remove batch effect

4d) 通过clustering score量化PCA和t-SNE可视化结果

4e) 矩阵处理部分代码示例
5) 特征选择指南
5a) 对feature做scale

6) 模型评估与特征解释指南
6a) 特征选择结果可视化

6b) 用选出的feature进行分类并绘制ROC曲线
6c) 用AUC评估挑选不同数量feature的效果

6d) 比较不同的模型和参数挑出的feature的差异

6e) 查看feature的robustness(鲁棒性)

6f) 利用Venn图分析feature的重合

Last updated
Was this helpful?



