Abstract
Combination antidepressant pharmacotherapies are frequently used to treat major depressive disorder (MDD). However, there is no evidence that machine learning approaches combining multi-omics measures (e.g., genomics and plasma metabolomics) can achieve clinically meaningful predictions of outcomes to combination pharmacotherapy. This study examined data from 264 MDD outpatients treated with citalopram or escitalopram in the Mayo Clinic Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS) and 111 MDD outpatients treated with combination pharmacotherapies in the Combined Medications to Enhance Outcomes of Antidepressant Therapy (CO-MED) study to predict response to combination antidepressant therapies. To assess whether metabolomics with functionally validated single-nucleotide polymorphisms (SNPs) improves predictability over metabolomics alone, models were trained/tested with and without SNPs. Models trained with PGRN-AMPS’ and CO-MED’s escitalopram/citalopram patients predicted response in CO-MED’s combination pharmacotherapy patients with accuracies of 76.6% (p < 0.01; AUC: 0.85) without and 77.5% (p < 0.01; AUC: 0.86) with SNPs. Then, models trained solely with PGRN-AMPS’ escitalopram/citalopram patients predicted response in CO-MED’s combination pharmacotherapy patients with accuracies of 75.3% (p < 0.05; AUC: 0.84) without and 77.5% (p < 0.01; AUC: 0.86) with SNPs, demonstrating cross-trial replication of predictions. Plasma hydroxylated sphingomyelins were prominent predictors of treatment outcomes. To explore the relationship between SNPs and hydroxylated sphingomyelins, we conducted multi-omics integration network analysis. Sphingomyelins clustered with SNPs and metabolites related to monoamine neurotransmission, suggesting a potential functional relationship. These results suggest that integrating specific metabolites and SNPs achieves accurate predictions of treatment response across classes of antidepressants. Finally, these results motivate functional investigation into how sphingomyelins might influence MDD pathophysiology, antidepressant response, or both.
Highlights
Major depressive disorder (MDD) is a significant public health challenge and an economic burden [1]
Including six functionally validated genomic biomarkers (i.e., single-nucleotide polymorphisms (SNPs) with mechanisms related to major depressive disorder (MDD) severity, or citalopram or escitalopram
Can machine learning strategies combining plasma metabolomic and genomic measures from MDD patients receiving antidepressant monotherapy achieve statistically significant predictions of response to combination pharmacotherapy? If combining these multi-omics measures improves predictability of response to multiple classes of antidepressants, can multi-omics integration networks elucidate biologically meaningful relationships between metabolomic predictors of antidepressant response and functionally validated genomic biomarkers? This present study hypothesized that augmenting clinical measures with multiple biological measures might improve the predictability of response to combination antidepressant therapies
Summary
Major depressive disorder (MDD) is a significant public health challenge and an economic burden [1]. Machine learning strategies using clinical and sociodemographic factors predicted response to escitalopram/citalopram with accuracies of 59.6% but could not achieve statistically significant predictions across groups of patients receiving combination antidepressant therapies [12]. Response) in the Pharmacogenomic Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS [16]) improved predictive accuracies of treatment response to >69% in patients treated with either citalopram or escitalopram [7] These prior studies using either plasma metabolomics or genomics were limited, because they did not demonstrate cross-trial replication of predictions in patients receiving combination pharmacotherapy. Can machine learning strategies combining plasma metabolomic and genomic measures from MDD patients receiving antidepressant monotherapy (citalopram or escitalopram) achieve statistically significant predictions of response to combination pharmacotherapy? Can machine learning strategies combining plasma metabolomic and genomic measures from MDD patients receiving antidepressant monotherapy (citalopram or escitalopram) achieve statistically significant predictions of response to combination pharmacotherapy? If combining these multi-omics measures improves predictability of response to multiple classes of antidepressants, can multi-omics integration networks elucidate biologically meaningful relationships between metabolomic predictors of antidepressant response and functionally validated genomic biomarkers? This present study hypothesized that augmenting clinical measures (e.g., symptom severity scores) with multiple biological measures (e.g., metabolomics and genomics) might improve the predictability of response to combination antidepressant therapies
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
