Integrative Molecular Pattern Learning for Mental Disorders Via Dual-Effect Matrix-Enabled Multiomics Platform.

Area of Science:

• Biochemistry
• Genomics
• Psychiatry

Background:

• Mental health disorders significantly impact well-being and social functioning, necessitating early and objective screening.
• Current diagnostic methods often lack objectivity and timeliness, hindering effective intervention and leading to severe social consequences.

Purpose of the Study:

• To develop a high-throughput multiomics platform for analyzing serum metabolomic and peptidomic profiles.
• To utilize advanced machine learning algorithms for the objective diagnosis of four major mental disorders in adults and adolescents.
• To identify shared and disorder-specific biomarkers and dysregulated biological pathways.

Main Methods:

• Development of a high-throughput multiomics platform using a dual-effect matrix.
• Acquisition and analysis of serum metabolomic and peptidomic data from patients with major depressive disorder, bipolar disorder, schizophrenia, anxiety disorder, and healthy controls.
• Application of machine learning algorithms for diagnostic classification and identification of biomarkers.
• Multiomics pathway analysis to reveal dysregulated biological pathways.

Main Results:

• Achieved an overall diagnostic area under the curve (AUC) of 0.998 for distinguishing patients with the four mental disorders from healthy controls.
• Attained an average AUC of 0.974 for the specific classification of each individual mental disorder.
• Identified two dysregulated biological pathways through multiomics pathway analysis.
• Discovered age-independent, disease-specific metabolic and peptide features.

Conclusions:

• The developed multiomics platform and machine learning approach show high accuracy in diagnosing major mental disorders.
• This technology represents a significant advancement in objective diagnostic tools for psychiatric disorders.
• The findings contribute to a deeper mechanistic understanding of mental disorders and pave the way for next-generation diagnostic solutions.