Discrimination of missing data types in metabolomics data based on particle swarm optimization algorithm and XGBoost model.

ABSTRACT: In the field of data analysis, it is often faced with a large number of missing values, especially in metabolomics data, this problem is more prominent. Data imputation is a common method to deal with missing metabolomics data, while traditional data imputation methods usually ignore the differences in missing types, and thus the results of data imputation are not satisfactory. In order to discriminate the missing types of metabolomics data, a missing data classification model (PX-MDC) based on particle swarm algorithm and XGBoost is proposed in this paper. First, the missing values in a given missing data set are obtained by panning the missing values to obtain the largest subset of complete data, and then the particle swarm algorithm is used to search for the concentration threshold of m

SUBMITTER: Yuan Y 

PROVIDER: S-EPMC10762217 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature