Biomarker combination identification method and system based on biomedical big data

Abstract

The invention relates to a biomarker combination identification method and system based on biomedical big data. The method includes steps of 1, acquiring a large amount of clinical data of proteins or metabolic small molecules in serum of patients and healthy people; 2, according to the acquired clinical data, adopting a latest central classifying framework to establish an optimal model of biomarker combination identification; 3, analyzing single features one by one to acquire prediction capacity of the single features, and ranking all the features according to the prediction capacity of the single features; 4, focusing on the features with the prediction capacity, arranging the clinic data into determined formats and inputting the clinic data to the optimal model of biomarker combination identification so as to estimate prediction capacities of multiple biomarker combinations, and determining an optimal biomarker combination according to errors of minimizing classification. The method focuses on identifying the biomarker combinations, and can be applied in biomedical big data of gene expression, protein combination and the like.

Description

technical field [0001] The invention belongs to the interdisciplinary field of biotechnology and information technology, and in particular relates to a biomarker combination identification method and system based on biomedical big data. Background technique [0002] Health management based on big data is the frontier trend of personalized medicine and future medicine. Among them, the health diagnosis of biomarkers based on clinical data is an important research hotspot and has broad application prospects. Biomarkers refer to biomolecules that can distinguish the physiological and pathological states of the body. For example, tumor markers are chemical substances that reflect the presence of tumors. They either do not exist in normal adult tissues but are only found in embryonic tissues, or their content in tumor tissues greatly exceeds that in normal tissues. Their existence or quantitative changes can indicate the nature of tumors, so as to understand the histogenesis and...

AI Technical Summary

Problems solved by technology

[0009] The current popular biomarker identification methods are mainly aimed at a single marker, and the prediction accuracy and stability of a single marker are still unsatisfactory

In addition, simply combining some single predictive markers together tends to select too many markers when the clinical data is high-dimensional data, and cannot remove highly correlated and redundant biomarkers, and cannot be found Nonlinear combination effects between markers

In addition, existing methods separate classification and feature selection, failing to achieve simultaneous optimization

From a practical perspective, existing technologies also fail to combine the detection, modeling, and validation of biomarker combinations into a practical computational system

Images