A miRNA marker for risk assessment of lung cancer
A technology of markers and risk scoring, applied in the field of biomedicine, can solve problems such as insufficient sensitivity and accuracy of lung cancer risk, no reference standard for lung cancer risk determination, and little knowledge of effective molecules
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0081] Example 1 Screening miRNAs associated with lung cancer
[0082] 1. Sample
[0083] The samples in GSE106817, GSE112264, GSE113486, GSE122497, GSE124158, GSE137140, and GSE139031 were selected from the GEO database as the research objects. A total of 10475 normal individuals and 1801 lung cancer patients had serum circulating miRNA expression profile data.
[0084] Randomly select 300 cases of data from 10475 normal people as the test set, and the remaining data as the training set; randomly select 300 cases of data from 1801 lung cancer patients as the test set, and the remaining data as the training set;
[0085] 2. Data normalization processing
[0086] Normalize the test set data and training set data; a) normalize the data to the (0,1) interval or (1,1) interval; b) change the dimensioned expression into a dimensionless expression;
[0087] 3) Screen differentially expressed molecules
[0088] The edgeR package was used to screen out differentially expressed miRN...
Embodiment 2
[0091] Example 2 Construction of risk scoring model
[0092] A risk scoring model was constructed using a 1D convolutional neural network model.
[0093] The input tensor dimension of the 1-dimensional convolutional neural network model is (length, 1), where length represents the number of selected feature miRNAs. The main body of the model includes an initial convolutional layer (init_conv), eight residual convolutional modules (res_block), a global pooling layer (GlobalAveragePooling), a fully connected layer (Dense) and an activation output layer (Sigmoid). Among them, conv is a one-dimensional convolution operation, k represents the size of the convolution kernel, and filters represent the number of convolution kernels. BatchNorm is a batch normalization layer, which normalizes the output tensor of the previous layer to a standard normal distribution with a mean of 0 and a variance of 1, so as to alleviate the gradient dispersion and gradient explosion in network training...
Embodiment 3
[0095] Example 3 Diagnostic efficacy testing of risk scoring model
[0096] In the training set, the results of using the risk scoring model of the present invention to diagnose the risk of lung cancer in subjects showed that a single miRNA or a combination of several miRNAs can be used as an independent prognostic factor for the diagnosis of lung cancer risk, and 3 or 4 miRNAs combined The area under the curve (AUC) formed is the highest, as shown in Table 1 and Figure 1-15 shown.
[0097] Table 1 Area under the curve formed by different miRNA markers
[0098] miRNA AUC hsa-miR-125a-3p 0.77 hsa-miR-3615 0.80 hsa-miR-4730 0.54 hsa-miR-575 0.90 hsa-miR-125a-3p+hsa-miR-3615 0.96 hsa-miR-125a-3p+hsa-miR-4730 0.98 hsa-miR-125a-3p+hsa-miR-575 0.97 hsa-miR-3615+hsa-miR-4730 0.98 hsa-miR-3615+hsa-miR-575 0.97 hsa-miR-4730+hsa-miR-575 0.98 hsa-miR-125a-3p+hsa-miR-3615+hsa-miR-4730 0.99 hsa-miR-125a-3p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More