Comparing feature selection and machine learning approaches for predicting CYP2D6 methylation from genetic variation.

Introduction: Pharmacogenetics currently supports clinical decision-making on the basis of a limited number of variants in a few genes and may benefit paediatric prescribing where there is a need for more precise dosing. Integrating genomic information such as methylation into pharmacogenetic models holds the potential to improve their accuracy and consequently prescribing decisions. Cytochrome P450 2D6 (CYP2D6) is a highly polymorphic gene conventionally associated with the metabolism of commonly used drugs and endogenous substrates. We thus sought to predict epigenetic loci from single nucleotide polymorphisms (SNPs) related to CYP2D6 in children from the GUSTO cohort. Methods: Buffy coat DNA methylation was quantified using the Illumina Infinium Methylation EPIC beadchip. CpG sites associated with CYP2D6 were used as outcome variables in Linear Regression, Elastic Net and XGBoost models. We compared feature selection of SNPs from GWAS mQTLs, GTEx eQTLs and SNPs within 2 MB of the CYP2D6 gene and the impact of adding demographic data. The samples were split into training (75%) sets and test (25%) sets for validation. In Elastic Net model and XGBoost models, optimal hyperparameter search was done using 10-fold cross validation. Root Mean Square Error and R-squared values were obtained to investigate each models' performance. When GWAS was performed to determine SNPs associated with CpG sites, a total of 15 SNPs were identified where several SNPs appeared to influence multiple CpG sites. Results: Overall, Elastic Net models of genetic features appeared to perform marginally better than heritability estimates and substantially better than Linear Regression and XGBoost models. The addition of nongenetic features appeared to improve performance for some but not all feature sets and probes. The best feature set and Machine Learning (ML) approach differed substantially between CpG sites and a number of top variables were identified for each model. Discussion: The development of SNP-based prediction models for CYP2D6 CpG methylation in Singaporean children of varying ethnicities in this study has clinical application. With further validation, they may add to the set of tools available to improve precision medicine and pharmacogenetics-based dosing.

Differential acetylcholinesterase inhibition of chlorpyrifos, diazinon and parathion in larval zebrafish.

Zebrafish are increasingly used for developmental neurotoxicity testing because early embryonic events are easy to visualize, exposures are done without affecting the mother and the rapid development of zebrafish allows for high throughput testing. We used zebrafish to examine how exposures to three different organophosphorus pesticides (chlorpyrifos, diazinon and parathion) over the first five days of embryonic and larval development of zebrafish affected their survival, acetylcholinesterase (AChE) activity and behavior. We show that at non-lethal, equimolar concentrations, chlorpyrifos (CPF) is more effective at equimolar concentrations than diazinon (DZN) and parathion (PA) in producing AChE inhibition. As concentrations of DZN and PA are raised, lethality occurs before they can produce the degree of AChE inhibition observed with CPF at 300 nM. Because of its availability outside the mother at the time of fertilization, zebrafish provides a complementary model for studying the neurotoxicity of very early developmental exposures.

Critical duration of exposure for developmental chlorpyrifos-induced neurobehavioral toxicity.

Developmental exposure of rats to the pesticide chlorpyrifos (CPF) causes persistent neurobehavioral impairment. In a parallel series of studies with zebrafish, we have also found persisting behavioral dysfunction after developmental CPF exposure. We have developed a battery of measures of zebrafish behavior, which are reliable and sensitive to toxicant-induced damage. This study determined the critical duration of developmental CPF exposure for causing persisting neurobehavioral effects. Tests of sensorimotor response (tap startle response and habituation), stress response (novel tank diving test) and learning (3-chamber tank spatial discrimination) were conducted with adult zebrafish after early developmental CPF exposure. The CPF exposure level was 100 ng/ml with durations of 0-1, 0-2, 0-3, 0-4 and 0-5 days after fertilization. Developmental CPF exposure had persisting behavioral effects in zebrafish tested as adults. In the tactile startle test, CPF exposed fish showed decreased habituation to startle and a trend toward increased overall startle response. In the novel tank exploration test, exposed fish showed decreased escape diving response and increased swimming activity. In the 3-chamber learning test, the 0-5 day CPF exposure group had a significantly lower learning rate. There was evidence for persisting declines in brain dopamine and norepinepherine levels after developmental CPF exposure. In all of the measures the clearest persistent effects were seen in fish exposed for the full duration of five days after fertilization. In a follow-up experiment there were some indications for persisting behavioral effects after exposure during only the later phase of this developmental window. This study demonstrated the selective long-term neurobehavioral alterations caused by exposure to CPF in zebrafish. The zebrafish model can facilitate the determination of the molecular mechanisms underlying long-term neurobehavioral impairment after developmental toxicant exposure.

Dynamic zebrafish interactome reveals transcriptional mechanisms of dioxin toxicity.

BACKGROUND: In order to generate hypotheses regarding the mechanisms by which 2,3,7,8-tetrachlorodibenzo-p-dioxin (dioxin) causes toxicity, we analyzed global gene expression changes in developing zebrafish embryos exposed to this potent toxicant in the context of a dynamic gene network. For this purpose, we also computationally inferred a zebrafish (Danio rerio) interactome based on orthologs and interaction data from other eukaryotes. METHODOLOGY/PRINCIPAL FINDINGS: Using novel computational tools to analyze this interactome, we distinguished between dioxin-dependent and dioxin-independent interactions between proteins, and tracked the temporal propagation of dioxin-dependent transcriptional changes from a few genes that were altered initially, to large groups of biologically coherent genes at later times. The most notable processes altered at later developmental stages were calcium and iron metabolism, embryonic morphogenesis including neuronal and retinal development, a variety of mitochondria-related functions, and generalized stress response (not including induction of antioxidant genes). Within the interactome, many of these responses were connected to cytochrome P4501A (cyp1a) as well as other genes that were dioxin-regulated one day after exposure. This suggests that cyp1a may play a key role initiating the toxic dysregulation of those processes, rather than serving simply as a passive marker of dioxin exposure, as suggested by earlier research. CONCLUSIONS/SIGNIFICANCE: Thus, a powerful microarray experiment coupled with a flexible interactome and multi-pronged interactome tools (which are now made publicly available for microarray analysis and related work) suggest the hypothesis that dioxin, best known in fish as a potent cardioteratogen, has many other targets. Many of these types of toxicity have been observed in mammalian species and are potentially caused by alterations to cyp1a.

Silver exposure in developing zebrafish (Danio rerio): persistent effects on larval behavior and survival.

The increased use of silver nanoparticles in consumer and medical products has led to elevated human and environmental exposures. Silver nanoparticles act as antibacterial/antifungal agents by releasing Ag(+) and recent studies show that Ag(+) impairs neural cell replication and differentiation in culture, suggesting that in vivo exposures could compromise neurodevelopment. To determine whether Ag(+) impairs development in vivo, we examined the effects of exposure on survival, morphological, and behavioral parameters in zebrafish embryos and larvae. We exposed zebrafish from 0 to 5days post-fertilization to concentrations of Ag(+) ranging from 10nM to 100microM in order to assess effects on survival and early embryonic development. We then tested whether concentrations below the threshold for dysmorphology altered larval behavior and subsequent survival. Ag(+) concentrations >or=3microM significantly reduced embryonic survival, whereas 1microM delayed hatching with no effect on survival. Reducing the concentration to as low as 0.1microM delayed the inflation of the swim bladder without causing gross dysmorphology or affecting hatching. At this concentration, swimming activity was impaired, an effect that persisted past the point where swim bladder inflation became normal; in contrast, general motor function was unaffected. The early behavioral impairment was then predictive of subsequent decreases in survival. Ag(+) is a developmental toxicant at concentrations only slightly above allowable levels. At low concentrations, Ag(+) acts as a neurobehavioral toxicant even in the absence of dysmorphology.