Using Data-Driven Algorithms with Large-Scale Plasma Proteomic Data to Discover Novel Biomarkers for Diagnosing Depression

Given recent technological advances in proteomics, it is now possible to quantify plasma proteomes in large cohorts of patients to screen for biomarkers and to guide the early diagnosis and treatment of depression. Here we used CatBoost machine learning to model and discover biomarkers of depression...

Full description

Saved in:
Bibliographic Details
Published in:Journal of proteome research Vol. 23; no. 9; p. 4043
Main Authors: Ma, Simeng, Li, Ruiling, Gong, Qian, Lv, Honggang, Deng, Zipeng, Wang, Beibei, Yao, Lihua, Kang, Lijun, Xiang, Dan, Yang, Jun, Liu, Zhongchun
Format: Journal Article
Language:English
Published: United States 06.09.2024
Subjects:
Algorithms
Area Under Curve
Biomarkers - blood
Blood Proteins - analysis
Blood Proteins - metabolism
Depression - blood
Depression - diagnosis
Female
Humans
Machine Learning
Male
Proteome - analysis
Proteome - metabolism
Proteomics - methods
ROC Curve
Biomarkers
Depression
CatBoost
Proteomic
ISSN:1535-3907, 1535-3907
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Given recent technological advances in proteomics, it is now possible to quantify plasma proteomes in large cohorts of patients to screen for biomarkers and to guide the early diagnosis and treatment of depression. Here we used CatBoost machine learning to model and discover biomarkers of depression in UK Biobank data sets (depression = 4,479, healthy control = 19,821). CatBoost was employed for model construction, with Shapley Additive Explanations (SHAP) being utilized to interpret the resulting model. Model performance was corroborated through 5-fold cross-validation, and its diagnostic efficacy was evaluated based on the area under the receiver operating characteristic (AUC) curve. A total of 45 depression-related proteins were screened based on the top 20 important features output by the CatBoost model in six data sets. Of the nine diagnostic models for depression, the performance of the traditional risk factor model was improved after the addition of proteomic data, with the best model having an average AUC of 0.764 in the test sets. KEGG pathway analysis of 45 screened proteins showed that the most significant pathway involved was the cytokine-cytokine receptor interaction. It is feasible to explore diagnostic biomarkers of depression using data-driven machine learning methods and large-scale data sets, although the results require validation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1535-3907
1535-3907
DOI:10.1021/acs.jproteome.4c00389