Detection methods for microarray mismarked samples

Abstract

The invention relates to detection methods for microarray data mismarked samples, belonging to the field of computational biology. The invention uses the influence of data perturbation on the regression model to identify suspected mismarked samples in the microarray; if the method of data perturbation is used in the pretreatment of disease gene expression data, the influence and loss caused by mismarks can be reduced. In the invention, a cofinal model between a description sample classmark and a sample gene expression vector is established, and then the classmarks of all the samples are perturbed in sequence to establish a perturbation regression matrix so as to capture the influence of the perturbation on the regression model. The invention defines three perturbation influence indexes: perturbation influence value, overall perturbation influence value and comprehensive perturbation influence value. Based on the defined three perturbation influence indexes, three detection methods for mismarked sample in response to microarray data are given: overall perturbation influence value identification method, comprehensive perturbation influence value discriminance method and gradual rectification method.

Description

technical field [0001] The patent of the present invention relates to a set of calculation methods for detecting mislabeled samples of microarray data, belonging to the field of computational biology. Background technique [0002] During the collection of gene expression data, due to the objective reasons of experimental methods and the subjective negligence of experimental operators, a lot of noise data is often introduced, and mislabeling of samples is one of the more common ones. The so-called mislabeling of samples means that the samples that originally belonged to a certain category are wrongly labeled as other categories, so that the sample becomes a wrong sample. This kind of situation is often seen in experiments on diseases, and the reasons are mostly the influence of subjective factors, such as the misoperation of the experimenter, the wrong judgment of the doctor, and so on. Since classification methods are widely used in medical cancer diagnosis and other fields...

AI Technical Summary

Problems solved by technology

However, both algorithms are only applied in a single microarray dataset and have not been extensively validated on other datasets

Malossini (2006) proposed two classification perturbation methods to detect mislabeled samples. The stability method can achieve good recognition results, but still has the defect of low recall rate.

Images