Machine learning methods applied to genotyping data capture interactions between single nucleotide variants in late onset Alzheimer's disease.

Introduction: Genome-wide association studies (GWAS) in late onset Alzheimer's disease (LOAD) provide lists of individual genetic determinants. However, GWAS do not capture the synergistic effects among multiple genetic variants and lack good specificity. Methods: We applied tree-based machine learning algorithms (MLs) to discriminate LOAD (>700 individuals) and age-matched unaffected subjects in UK Biobank with single nucleotide variants (SNVs) from Alzheimer's disease (AD) studies, obtaining specific genomic profiles with the prioritized SNVs. Results: MLs prioritized a set of SNVs located in genes PVRL2, TOMM40, APOE, and APOC1, also influencing gene expression and splicing. The genomic profiles in this region showed interaction patterns involving rs405509 and rs1160985, also present in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. rs405509 located in APOE promoter interacts with rs429358 among others, seemingly neutralizing their predisposing effect. Discussion: Our approach efficiently discriminates LOAD from controls, capturing genomic profiles defined by interactions among SNVs in a hot-spot region.

Detection of newly emerging psychoactive substances using Raman spectroscopy and chemometrics.

A novel approach for the identification of New Psychoactive Substances (NPS) by means of Raman spectroscopy coupled with Principal Components Analysis (PCA) employing the largest dataset of NPS reference materials to date is reported here. Fifty three NPS were selected as a structurally diverse subset from an original dataset of 478 NPS compounds. The Raman spectral profiles were experimentally acquired for all 53 substances, evaluated using a number of pre-processing techniques, and used to generate a PCA model. The optimum model system used a relatively narrow spectral range (1300-1750 cm-1) and accounted for 37% of the variance in the dataset using the first three principal components, despite the large structural diversity inherent in the NPS subset. Nonetheless, structurally similar NPS (i.e., the synthetic cannabinoids FDU-PB-22 & NM-2201) grouped together in the PCA model based on their Raman spectral profiles, while NPS with different chemical scaffolds (i.e., the benzodiazepine flubromazolam and the cathinone α-PBT) were well delineated, occupying markedly different areas of the three-dimensional scores plot. Classification of NPS based on their Raman spectra (i.e., chemical scaffolds) using the PCA model was further investigated. NPS that were present in the initial dataset of 478 NPS but were not part of the selected 53 training set (validation set) were observed to be closely aligned to structurally similar NPS within the generated model system in all cases. Furthermore, NPS that were not present in the original dataset of 478 NPS (test set) were also shown to group as expected in the model (i.e., methamphetamine and N-ethylamphetamine). This indicates that, for the first time, a model system can be applied to potential 'unknown' psychoactive substances, which are new to the market and absent from existing chemical libraries, to identify key structural features to make a preliminary classification. Consequently, it is anticipated that this study will be of interest to the broad scientific audience working with large structurally diverse chemical datasets and particularly to law enforcement agencies and associated scientific analytical bodies worldwide investigating the development of novel identification methodologies for psychoactive substances.

The effect of formulations and experimental conditions on in vitro human skin permeation-Data from updated EDETOX database.

In vitro methods are commonly used in order to estimate the extent of systemic absorption of chemicals through skin. Due to the wide variability of experimental procedures, types of skin and data analytical methods, the resulting permeation measures varies significantly between laboratories and individuals. Inter-laboratory and inter-individual variations with the in vitro measures of skin permeation lead to unreliable extrapolations to in vivo situations. This investigation aimed at a comprehensive assessment of the available data and development of validated models for in vitro skin flux of chemicals under various experimental and vehicle conditions. Following an exhaustive literature review, the human skin flux data were collated and combined with those from EDETOX database resulting in a dataset of a total of 536 flux reports. Quantitative structure-activity relationship techniques combined with data mining tools were used to develop models incorporating the effects of permeant molecular structure, properties of the vehicle, and the experimental conditions including the membrane thickness, finite/infinite exposure, skin pre-hydration and occlusion. The work resulted in statistically valid models for estimation of the skin flux from varying experimental conditions, including relevant real-world mixture exposure scenarios. The models indicated that the most prominent factors influencing flux values were the donor concentration, lipophilicity, size and polarity of the penetrant, and the melting and boiling points of the vehicle, with skin occlusion playing significant role in a non-linear way. The models will aid assessment of the utility of dermal absorption data collected under different conditions with broad implications on transdermal delivery research.

Validated models for predicting skin penetration from different vehicles.

The permeability of a penetrant though skin is controlled by the properties of the penetrants and the mixture components, which in turn relates to the molecular structures. Despite the well-investigated models for compound permeation through skin, the effect of vehicles and mixture components has not received much attention. The aim of this Quantitative Structure Activity Relationship (QSAR) study was to develop a statistically validated model for the prediction of skin permeability coefficients of compounds dissolved in different vehicles. Furthermore, the model can help with the elucidation of the mechanisms involved in the permeation process. With this goal in mind, the skin permeability of four different penetrants each blended in 24 different solvent mixtures were determined from diffusion cell studies using porcine skin. The resulting 96 kp values were combined with a previous dataset of 288 kp data for QSAR analysis. Stepwise regression analysis was used for the selection of the most significant molecular descriptors and development of several regression models. The selected QSAR employed two penetrant descriptors of Wiener topological index and total lipole moment, boiling point of the solvent and the difference between the melting point of the penetrant and the melting point of the solvent. The QSAR was validated internally, using a leave-many-out procedure, giving a mean absolute error of 0.454 for the logkp value of the test set.