Profile Characterization of Biogenic Amines in Glioblastoma Patients Undergoing Standard-of-Care Treatment

Abstract

Introduction: Biogenic amines play important roles throughout cellular metabolism. This study explores a role of biogenic amines in glioblastoma pathogenesis. Here, we characterize the plasma levels of biogenic amines in glioblastoma patients undergoing standard-of-care treatment.

Methods: We examined 138 plasma samples from 36 patients with isocitrate dehydrogenase (IDH) wild-type glioblastoma at multiple stages of treatment. Untargeted gas chromatography-time of flight mass spectrometry (GC-TOF MS) was used to measure metabolite levels. Machine learning approaches were then used to develop a predictive tool based on these datasets.

Results: Surgery was associated with increased levels of 12 metabolites and decreased levels of 11 metabolites. Chemoradiation was associated with increased levels of three metabolites and decreased levels of three other metabolites. Ensemble learning models, specifically random forest (RF) and AdaBoost (AB), accurately classified treatment phases with high accuracy (RF: 0.81 ± 0.04, AB: 0.78 ± 0.05). The metabolites sorbitol and N-methylisoleucine were identified as important predictive features and confirmed via SHAP.

Conclusion: To our knowledge, this is the first study to describe plasma biogenic amine signatures throughout the treatment of patients with glioblastoma. A larger study is needed to confirm these results with hopes of developing a diagnostic algorithm.

Keywords: biogenic amines; concurrent chemoradiation; glioblastoma; metabolomic profiling.

Figure 1

Comparison of biogenic amine profile of post-surgery samples vs. pre-surgery. (A) Partial least squares–discriminant analysis (PLS-DA) showed two-group clustering with evidence of separation between plasma at pre-surgery (purple) and post-surgery (green). (B) VIP score with the highest 25 metabolites. (C) Heat map of the top 40 altered metabolites pre-surgery and post-surgery. Blue indicates decreased peak value and maroon indicates increased peak value of each compound listed. (D) Volcano plot of upregulated biogenic amine (right side) and downregulated biogenic amine (left side) plasma specimens post-surgery compared to pre-surgery using p-value of <0.05 and fold change cutoffs of 2.0; colors correlate with metabolite’s super class.

Figure 2

Comparison of biogenic amines profile of post-radiation samples vs. pre-radiation. (A) Partial least squares–discriminant analysis (PLS-DA) showed two-group clustering with evidence of separation between plasma at pre-radiation (purple) and post-radiation (green). (B) VIP score with the highest 25 metabolites. (C) Heat map of the top 40 altered metabolites pre-radiation and post-radiation. Blue indicates decreased peak value and maroon indicates increased peak value of each compound listed. (D) Volcano plot of upregulated biogenic amines (right side) and downregulated biogenic amines (left side) in plasma specimens post-radiation compared to pre-radiation using p-value of <0.05 and fold change cutoffs of 2.0; colors correlate with metabolite’s super class.

Figure 3

Comparison of biogenic amine profiles of post-treatment samples vs. pre-radiation samples. (A) Partial least squares–discriminant analysis (PLS-DA) showed two-group clustering with evidence of separation between plasma pre-radiation (purple) and post-treatment (green). (B) VIP score with the highest 25 metabolites. (C) Heat map of the top 40 altered metabolites pre-radiation and post-radiation. Blue indicates decreased peak value and maroon indicates increased peak value of each compound listed. (D) Volcano plot of upregulated biogenic amines (right side) and downregulated biogenic amines (left side) in plasma specimens post-treatment compared to pre-radiation using p-value of <0.05 and fold change cutoffs of 2.0; colors correlate with metabolite’s super class.

Figure 4

Comparison between random forest (RF), AdaBoost (AB), Support Vector Machine (SVM), Logistic Regression (LR), and Multiplayer Perceptron (MLP) classifiers on 5-fold cross-validation results. Five independent grid searches were performed for robustness, and the hyperparameter set with the best mean validation accuracy was shown for each classifier (i.e., n = 25 for each boxplot). The box indicates the interquartile range, the horizontal middle line indicates the median, the diamond indicates an outlier, and the whisker line indicates the range between minimum and maximum, excluding outliers. The p-values were computed with two-tailed t-tests.

Figure 5

Performance evaluation on the testing set for the best model. Random forest with the best hyperparameter trained with the entire training set was shown. (A) Micro- and macro-averaging of evaluation metrics. Macro-averaging is the average of a metric across different classes, while micro-averaging is the weighted average based on the size of each class. The boxplot consists of 20 points, where each point is a corresponding metric computed from an independent run with different random initialization. (B) Confusion matrix for the best model. The standard deviation was computed from the 20 independent runs. (C,D) Precision–recall (PR) and receiver operating characteristic (ROC) curves. Each curve was plotted by concatenating predictions from the 20 independent runs.

Figure 6

Comparison of different feature importance methods. (A) Metabolite feature ranks of Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), random forest (RF), and sequential feature selection (SFS). The table only shows the biogenic amines ranked top 10 by at least two methods. Dark green represents tope 3 ranked metabolites, and light green represents top 10 ranked metabolites (B) SHAP values of random forest with features selected via SFS. The interpretation of a SHAP value for a tree-based model is that a feature satisfying a split criterion expects to change the output probability by the amount of SHAP value.