RESUMO
Introduction: Stigma contributes to a significant part of the burden of schizophrenia (SCZ), therefore reducing false positives from the diagnosis would be liberating for the individuals with SCZ and desirable for the clinicians. The stigmatization associated with schizophrenia advocates the need for high-precision diagnosis. In this study, we present an ensemble learning-based approach for high-precision diagnosis of SCZ using peripheral blood gene expression profiles. Methodology: The machine learning (ML) models, support vector machines (SVM), and prediction analysis for microarrays (PAM) were developed using differentially expressed genes (DEGs) as features. The SCZ samples were classified based on a voting ensemble classifier of SVM and PAM. Further, microarray-based learning was used to classify RNA sequencing (RNA-Seq) samples from our case-control study (Pune-SCZ) to assess cross-platform compatibility. Results: Ensemble learning using ML models resulted in a significantly higher precision of 80.41% (SD: 0.04) when compared to the individual models (SVM-radial: 71.69%, SD: 0.04 and PAM 77.20%, SD: 0.02). The RNA sequencing samples from our case-control study (Pune-SCZ) resulted in a moderate precision (59.92%, SD: 0.05). The feature genes used for model building were enriched for biological processes such as response to stress, regulation of the immune system, and metabolism of organic nitrogen compounds. The network analysis identified RBX1, CUL4B, DDB1, PRPF19, and COPS4 as hub genes. Conclusion: In summary, this study developed robust models for higher diagnostic precision in psychiatric disorders. Future efforts will be directed towards multi-omic integration and developing "explainable" diagnostic models.
RESUMO
Schizophrenia is a disorder that is characterized by delusions, hallucinations, disorganized speech or behavior, and socio-occupational impairment. The duration of observation and variability in symptoms can make the accurate diagnosis difficult. Identification of biomarkers for schizophrenia (SCZ) can help in early diagnosis, ascertaining the diagnosis, and development of effective treatment strategies. Here we review peripheral blood-based gene expression studies for identification of gene expression biomarkers for SCZ. A literature search was carried out in PubMed and Web of Science databases for blood-based gene expression studies in SCZ. A list of differentially expressed genes (DEGs) was compiled and analyzed for overlap with genetic markers, differences based on drug status of the participants, functional enrichment, and for effect of antipsychotics. This literature survey identified 61 gene expression studies. Seventeen out of these studies were based on expression microarrays. A comparative analysis of the DEGs (n = 227) from microarray studies revealed differences between drug-naive and drug-treated SCZ participants. We found that of the 227 DEGs, 11 genes (ACOT7, AGO2, DISC1, LDB1, RUNX3, SIGIRR, SLC18A1, NRG1, CHRNB2, PRKAB2, and ZNF74) also showed genetic and epigenetic changes associated with SCZ. Functional enrichment analysis of the DEGs revealed dysregulation of proline and 4-hydroxyproline metabolism. Also, arginine and proline metabolism was the most functionally enriched pathway for SCZ in our analysis. Follow-up studies identified effect of antipsychotic treatment on peripheral blood gene expression. Of the 27 genes compiled from the follow-up studies AKT1, DISC1, HP, and EIF2D had no effect on their expression status as a result of antipsychotic treatment. Despite the differences in the nature of the study, ethnicity of the population, and the gene expression analysis method used, we identified several coherent observations. An overlap, though limited, of genetic, epigenetic and gene expression changes supports interplay of genetic and environmental factors in SCZ. The studies validate the use of blood as a surrogate tissue for biomarker analysis. We conclude that well-designed cohort studies across diverse populations, use of high-throughput sequencing technology, and use of artificial intelligence (AI) based computational analysis will significantly improve our understanding and diagnostic capabilities for this complex disorder.