Plasma protein biomarkers for depression and schizophrenia by multi analyte profiling of case-control collections

Abstract

Despite significant research efforts aimed at understanding the neurobiological underpinnings of psychiatric disorders, the diagnosis and the evaluation of treatment of these disorders are still based solely on relatively subjective assessment of symptoms. Therefore, biological markers which could improve the current classification of psychiatry disorders, and in perspective stratify patients on a biological basis into more homogeneous clinically distinct subgroups, are highly needed. In order to identify novel candidate biological markers for major depression and schizophrenia, we have applied a focused proteomic approach using plasma samples from a large case-control collection. Patients were diagnosed according to DSM criteria using structured interviews and a number of additional clinical variables and demographic information were assessed. Plasma samples from 245 depressed patients, 229 schizophrenic patients and 254 controls were submitted to multi analyte profiling allowing the evaluation of up to 79 proteins, including a series of cytokines, chemokines and neurotrophins previously suggested to be involved in the pathophysiology of depression and schizophrenia. Univariate data analysis showed more significant p-values than would be expected by chance and highlighted several proteins belonging to pathways or mechanisms previously suspected to be involved in the pathophysiology of major depression or schizophrenia, such as insulin and MMP-9 for depression, and BDNF, EGF and a number of chemokines for schizophrenia. Multivariate analysis was carried out to improve the differentiation of cases from controls and identify the most informative panel of markers. The results illustrate the potential of plasma biomarker profiling for psychiatric disorders, when conducted in large collections. The study highlighted a set of analytes as candidate biomarker signatures for depression and schizophrenia, warranting further investigation in independent collections.

Figure 1. Relative change of protein markers in MDD or schizophrenia against their p-values.

Plot of relative changes for measured analytes in depression (a) and schizophrenia (b) against their p-values. The Y axis reports the relative increase (or decrease) as the ratio (and the confidence interval) based on analysis of log-transformed data from cases/controls. Reference vertical line corresponds to p-value threshold at a 5% significance level, after correction for multiple testing. Male and females are computed and reported separately.

Figure 2. Plasma protein markers with highest significance in MDD and schizophrenia.

Box plots of individual analytes with high univariate significance. Where data below detection limit were present (see bar charts on bottom row for EGF and MMP-9) they are replaced by the lowest observed value to generate the box plots. The bracketed values in the titles refer to the data transformation, if applied, and the sequence number in the original dataset. The white line corresponds to the median, whilst the full box represents the central 50%.

Figure 3. PCA plot showing the separation of schizophrenia samples from controls and MDD.

PCA plot obtained by using SIMCA, where the 1st and 3rd components of the model (t and t, respectively) are shown. The graph is obtained by replacing values below detection limit with the lowest value measured for each protein (conservative approach).

Figure 4. Contribution from each individual marker to case-control separation from PLS discrimination analysis.

Variable Importance of Information (VIP) plot ranking markers for their contribution to case-control separation from PLS discrimination analysis. A: MDD; B: schizophrenia. Larger values on the left indicate more important contributions.

Figure 5. Comparing marker contributions to case-control separation for MDD versus schizophrenia.

The Variable Importance of Contribution (VIP) from PLS-DA for each analyte is plotted on X axis for MDD and on the Y axis for schizophrenia. The overlap between the two groups of markers highlights findings that are in common between the two disease groups.

Figure 6. Receiver-operating characteristic (ROC) plot derived from linear discriminative analysis (LDA) based on the top findings from the PLS approach.

ROC plot of sensitivity (True Positive Rate, Y-axis) versus 1 – specificity (False Positive Rate, X-axis) based on a Linear discrimination model (LDA) built upon the 10 markers with the highest contribution as determined by PLS-DA.

Figure 7. PCA plot showing the lack of separation of untreated from treated schizophrenics by plasma profiling.

PCA plot obtained by SIMCA coded according with the different medications for schizophrenia cases (“C” indicates treatment with clozapine, “A” treatment with other atypical antipsychotics, “T” indicates treatment with typical antipsychotics, “-“ indicates untreated subjects). The dark blue (untreated, diamond) schizophrenics samples do not separate out from the whole schizophrenic group. t and t represent the 1st and 3rd component of the PCA model.