Cancer type prediction system and method based on tissue and organ differentiation hierarchical relationship

Abstract

The invention provides a cancer type prediction system and method based on a tissue and organ differentiation hierarchical relationship. The method comprises the following steps of: acquiring transcriptome gene expression quantity data of each cancer in a plurality of cancer types as a training set; dividing different cancer types into a first grade and a second grade according to a tissue and organ differentiation relationship; performing feature selection based on the tissue and organ differentiation hierarchical relationship, that is, for each tissue and organ type or cancer type of each grade, the cancer type is selected to differentially express genes compared with all other cancer types in the training set, and the genes are high-expression genes; carrying out normalization processing on the gene expression data; inputting the normalized gene expression data into a machine learning algorithm to construct a double-layer machine learning classification model; and inputting a processed to-be-detected sample data into the double-layer machine learning classification model for prediction.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a cancer type prediction system and method based on the hierarchical relationship of tissue and organ differentiation. Background technique [0002] Metastatic cancer with unknown primary tumor refers to metastatic cancer that can be confirmed by histological or cytological examination, but the medical history and clinical manifestations cannot provide evidence of the primary tumor. Adenocarcinoma accounts for 40% of metastatic cancers with unknown primary tumors, and the primary tumors may be: tumors of the lung, pancreas, gastrointestinal tract, gallbladder, liver, kidney, breast, prostate, thyroid, adrenal gland, and germ cells; Undifferentiated carcinoma accounts for 40%, and can occur in almost any location; squamous cell carcinoma accounts for 13%, mainly from tumors of the lung, head and neck, esophagus, cervix, bladder, etc.; other types of tumors account for 7%. [0003] Mult...

AI Technical Summary

Problems solved by technology

Therefore, the method of the present invention solves the problem that metastatic cancer with unknown primary tumor or multiple primary malignant tumors is difficult to determine the type of cancer

Images