An Ensemble Approach to Predict Schizophrenia Using Protein Data in the N-methyl-D-Aspartate Receptor (NMDAR) and Tryptophan Catabolic Pathways

Abstract

In the wake of recent advances in artificial intelligence research, precision psychiatry using machine learning techniques represents a new paradigm. The D-amino acid oxidase (DAO) protein and its interaction partner, the D-amino acid oxidase activator (DAOA, also known as G72) protein, have been implicated as two key proteins in the N-methyl-D-aspartate receptor (NMDAR) pathway for schizophrenia. Another potential biomarker in regard to the etiology of schizophrenia is melatonin in the tryptophan catabolic pathway. To develop an ensemble boosting framework with random undersampling for determining disease status of schizophrenia, we established a prediction approach resulting from the analysis of genomic and demographic variables such as DAO levels, G72 levels, melatonin levels, age, and gender of 355 schizophrenia patients and 86 unrelated healthy individuals in the Taiwanese population. We compared our ensemble boosting framework with other state-of-the-art algorithms such as support vector machine, multilayer feedforward neural networks, logistic regression, random forests, naive Bayes, and C4.5 decision tree. The analysis revealed that the ensemble boosting model with random undersampling [area under the receiver operating characteristic curve (AUC) = 0.9242 ± 0.0652; sensitivity = 0.8580 ± 0.0770; specificity = 0.8594 ± 0.0760] performed maximally among predictive models to infer the complicated relationship between schizophrenia disease status and biomarkers. In addition, we identified a causal link between DAO and G72 protein levels in influencing schizophrenia disease status. The study indicates that the ensemble boosting framework with random undersampling may provide a suitable method to establish a tool for distinguishing schizophrenia patients from healthy controls using molecules in the NMDAR and tryptophan catabolic pathways.

Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework

“…The LogitBoost algorithm is a boosting ensemble model, which incorporates the performance of many weak predictive models (also referred to as base predictive models) to accomplish a robust predictive model with higher accuracy [ 26 ]. Moreover, the LogitBoost algorithm employs a binomial log-likelihood algorithm that adjusts the predictive error linearly, thereby tending to be robust in handling outliers and noisy data [ 26 ]. The base predictive model we utilized is an MFNN, which consists of one input layer, one hidden layer, and one output layer.…”

“…Here, for the LogitBoost algorithm, we used the default parameters of WEKA, such as 1.0 for the shrinkage parameter, 100 for the batch size, 3.0 for the Z max threshold, and 10 for the number of iterations. In addition, for the MFNN model, WEKA’s parameters were chosen as follows: the momentum = 0.01, the learning rate = 0.001 or 0.002, and the batch size = 100 [ 4 , 26 ]. The momentum, learning rate, and batch size were set at the given values using a grid search approach [ 27 ].…”

“…The naïve Bayes model measures the probability that a given instance belongs to a certain class (for example, “non-responder” or “responder” in this study) by using the Bayes’ theorem [ 26 ]. Here, we used the default parameters of WEKA for the naïve Bayes model, such as 100 for the batch size.…”

Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design

“…Moreover, a common pitfall is that the aforementioned GAN-based frameworks may not employ the cross-validation strategy to avoid the risk of overfitting during the training step. For instance, the repeated 10-fold cross-validation method and leave-one-out cross-validation method could be good procedures for examining the generalization of GAN-based frameworks [109,110]. In brief, the repeated 10-fold cross-validation method randomly separates the whole dataset into ten subsets, and then the GAN-based frameworks can be trained by nine-tenths of the data and tested by the remaining tenth of data [111].…”

Plasma d-glutamate levels for detecting mild cognitive impairment and Alzheimer’s disease: Machine learning approaches

“…A pilot study used machine learning models to predict schizophrenia with two NNMDR-related proteins: DAO and G72. The prediction and sensitivities were 0.9242 and 0.8580, respectively (Lin et al, 2020a). However, machine learning with NMDAR-related biomarkers in MCI and AD remains unknown.…”