Lasso Regression for Gene Selection and Patient Status Output

This code demonstrates how to use Lasso Regression to identify important genes in a dataset of patient data. The selected genes are then output along with their expression levels and patient status to an Excel file.

Steps:

Import Necessary Libraries: Import the pandas library for data manipulation and the Lasso class from the sklearn.linear_model module for Lasso Regression.
Load Data: Load the patient data from an Excel file. The file path is specified as 'C:\Users\lenovo\Desktop\HIV\PAH三个数据集\193lasso.xlsx'. The header=0 argument specifies that the first row of the file contains column headers.
Prepare Data: The code assumes that the first column of the data contains the patient status. Extract the features (X) and labels (y) from the DataFrame.
Perform Lasso Regression: Initialize a Lasso object with an alpha value of 0.01, which controls the strength of the regularization. Fit the model to the features (X) and labels (y).
Identify Important Genes: Get the coefficients from the fitted Lasso model. These coefficients represent the weights assigned to each gene. Non-zero coefficients indicate genes that are deemed important by the model. Sort these genes by their coefficients in descending order to identify the most influential genes.
Output Selected Genes: Create a new DataFrame containing only the selected genes. Insert a column for the patient status at the beginning of the DataFrame. Finally, save this DataFrame to an Excel file named 'selected_genes.xlsx'.

Code:

import pandas as pd
from sklearn.linear_model import Lasso

# Load Excel file
df = pd.read_excel('C:\Users\lenovo\Desktop\HIV\PAH三个数据集\193lasso.xlsx', header=0)

# Extract features and labels
X = df.iloc[:, 1:]
y = df.iloc[:, 0]

# Lasso regression
lasso = Lasso(alpha=0.01)
lasso.fit(X, y)

# Identify important genes
coef = pd.Series(lasso.coef_, index=X.columns)
important_genes = coef[coef != 0].sort_values(ascending=False)
print('Important Genes:')
print(important_genes)

# Output selected genes and patient status
selected_genes_df = df.loc[:, important_genes.index.tolist()]
selected_genes_df.insert(0, 'Patient Status', df['Patient Status'])
selected_genes_df.to_excel('C:\Users\lenovo\Desktop\HIV\PAH三个数据集\selected_genes.xlsx', index=False)

Output:

The code will output a list of important genes to the console and will save an Excel file containing the selected genes, their expression levels, and the corresponding patient status.

Note: This code provides a basic example of using Lasso Regression for gene selection. You may need to adjust the alpha value or modify the code to suit your specific needs and data.

Lasso Regression for Gene Selection and Patient Status Output