Machine learning classification of ADHD and HC by multimodal serotonergic data
TRANSLATIONAL PSYCHIATRY
Authors: Kautzky, A.; Vanicek, T.; Philippe, C.; Kranz, G. S.; Wadsak, W.; Mitterhauser, M.; Hartmann, A.; Hahn, A.; Hacker, M.; Rujescu, D.; Kasper, S.; Lanzenberger, R.
Abstract
Serotonin neurotransmission may impact the etiology and pathology of attention-deficit and hyperactivity disorder (ADHD), partly mediated through single nucleotide polymorphisms (SNPs). We propose a multivariate, genetic and positron emission tomography (PET) imaging classification model for ADHD and healthy controls (HC). Sixteen patients with ADHD and 22 HC were scanned by PET to measure serotonin transporter (SERT') binding potential with [C-11]DASB. All subjects were genotyped for thirty SNPs within the HTR1A, HTR1B, HTR2A and TPH2 genes. Cortical and subcortical regions of interest (ROI) were defined and random forest (RF) machine learning was used for feature selection and classification in a five-fold cross-validation model with ten repeats. Variable selection highlighted the ROI posterior cingulate gyrus, cuneus, precuneus, pre-, para- and postcentral gyri as well as the SNPs HTR2A rs1328684 and rs6311 and HTR1B rs130058 as most discriminative between ADHD and HC status. The mean accuracy for the validation sets across repeats was 0.82 (+/- 0.09) with balanced sensitivity and specificity of 0.75 and 0.86, respectively. With a prediction accuracy above 0.8, the findings underlying the proposed model advocate the relevance of the SERT as well as the HTR1B and HTR2A genes in ADHD and hint towards disease-specific effects. Regarding the high rates of comorbidities and difficult differential diagnosis especially for ADHD, a reliable computer-aided diagnostic tool for disorders anchored in the serotonergic system will support clinical decisions.
Cerebral 5-HT2A receptor binding, but not mGluR2, is increased in tryptophan hydroxylase 2 decrease-of-function mice
NEUROSCIENCE LETTERS
Authors: Jorgensen, Christinna V.; Jacobsen, Jacob P.; Caron, Marc G.; Klein, Anders B.; Knudsen, Gitte M.; Mikkelsen, Jens D.
Abstract
Transgenic mice with a knock-in (KI) of a tryptophan hydroxylase 2 (Tph2) R439H mutation, analogous to the Tph2 R441H single-nucleotide polymorphism originally identified in a late life depression cohort, have markedly reduced levels of 5-hydroxytryptamine (5-HT). These Tph2KI mice are therefore interesting as a putative translational model of low endogenous 5-HT function that allows for assessment of adaptive changes in different anatomical regions. Here, we determined 5-HT2A receptor binding in several brain regions using in vitro receptor autoradiography and two different radioligands. When using the 5-HT2A receptor selective antagonist radioligand H-3-MDL100907, we found higher binding in the prefrontal cortex (10%, P = 0.009), the striatum (26%, P = 0.005), and the substantia nigra (21%, P = 0.027). The increase was confirmed in the same regions with the 5-HT2A/c receptor agonist, H-3-CIMBI-36 (2-(4-Bromo-2,5-dimethoxyphenyl)-N-(2-methoxybenzyl)ethanamine). 5-HT2A receptors establish heteromeric receptor complexes with metabotropic glutamate 2 receptors (mGluR2), but binding levels of the mGluR2/3 ligand H-3-LY341495 were unaltered in brain areas with increased 5-HT2A receptor levels. These data show that in distinct anatomical regions, 5-HT2A receptor binding sites are up-regulated in 5-HT deficient mice, and this increase is not associated with changes in mGluR2 binding. (C) 2013 Elsevier Ireland Ltd. All rights reserved.