GAN-based chromosome structure anomaly detection method and system and storage medium

Abstract

The invention discloses a GAN-based chromosome structure anomaly detection method and system and a storage medium, and the method comprises the steps: carrying out cleaning and filtering of a chromosome data set, and obtaining a to-be-trained data set; performing data enhancement processing on the to-be-trained data set to obtain massive to-be-trained data; constructing a GAN-based anomaly detection model according to the to-be-trained data; optimizing the anomaly detection model; and predicting a chromosome detection result according to the optimized anomaly detection model. The GAN-based anomaly detection model is constructed, only normal chromosomes need to be trained and feature information of the normal chromosomes needs to be learned, and chromosome structure anomaly detection is performed by fully utilizing the difference between the feature information of the normal chromosomes and the feature information of abnormal chromosomes; besides, the invention can be used for carryingout chromosome classification and anomaly detection on chromosomes, is high in practicability, and can be widely applied to the technical field of machine learning.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a GAN-based chromosome structure abnormality detection method, system and storage medium. Background technique [0002] Explanation of terms: [0003] Chromosomes: Chromosomes are genetic material. There are 23 pairs of chromosomes in human somatic cells, including 22 pairs of autosomes and a pair of sex chromosomes (XX or XY). In the present invention, the chromosome categories are divided into 24 categories, corresponding to 22 pairs of autosomes, X sex chromosomes and Y sex chromosomes respectively. [0004] Chromosomal abnormalities: Chromosomal abnormalities include abnormalities in the number of chromosomes and abnormalities in the structure of chromosomes. Abnormal numbers represent deletions and increases in chromosome number, and structural abnormalities are characterized by partial deletions, translocations, inversions, and duplications on chromosomes. [000...

AI Technical Summary

Problems solved by technology

From the perspective of research methods, in this research field, most of the deep learning models currently used are simple basic models such as CNN and RNN for feature extraction, and the effect is relatively general.

Images