JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Proteome analysis of the prefrontal cortex and the application of machine learning models for the identification of potential biomarkers related to suicide

  • 0Programa de Doctorado en Ciencias Biomédicas, Universidad Nacional Autónoma de México (UNAM), Mexico City, Mexico.
Frontiers in Psychiatry +

|

March 7, 2025

|

March 7, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Suicide prevention is crucial. This study identified altered protein expression in the dorsolateral prefrontal cortex (DLPFC) of individuals who died by suicide, revealing potential biomarkers and pathways involved in suicide risk.

Area Of Science

  • Neuroscience
  • Proteomics
  • Biochemistry

Background

  • Suicide is a major public health concern, particularly in low- and middle-income countries.
  • Biological and social factors contribute to suicide.
  • Previous research has examined the proteome of the dorsolateral prefrontal cortex (DLPFC) in individuals who died by suicide.

Purpose Of The Study

  • To analyze protein expression profiles in the DLPFC of individuals who died by suicide compared to controls.
  • To identify potential biomarkers for suicide risk.
  • To develop a machine learning model for suicide prediction.

Main Methods

  • Proteomic analysis of DLPFC tissue (Brodmann area 9) from suicide cases (n=9) and age-matched controls (n=7) using 2D-polyacrylamide gel electrophoresis and mass spectrometry.
  • Bioinformatics tools to determine the biological relevance of differentially expressed proteins.
  • Machine learning algorithms applied to protein expression data for predictive modeling.

Main Results

  • Twelve differentially expressed proteins were identified.
  • Decreased expression of peroxiredoxin 2 and alpha-internexin was validated in suicide cases via Western blotting.
  • Machine learning models successfully differentiated between control and suicide groups using protein densitometry data.

Conclusions

  • Oxidative stress responses and neurodevelopmental pathways are implicated in the DLPFC of individuals who died by suicide.
  • Identified proteins in the DLPFC may serve as potential biomarkers for suicide risk.
  • Machine learning models, particularly KNeighborsClassifier, show promise in predicting suicide outcomes.

Keywords: