Predictors of early-onset cognitive impairment

Reduced neurobehavioral functioning in agricultural workers and rural inhabitants exposed to pesticides in northern Chile and its association with blood biomarkers inhibition

BACKGROUND

Previous biomonitoring studies have shown that people in the rural population of Coquimbo, the major agricultural area in northern Chile are being occupationally and environmentally exposed to organophosphate/carbamate (OP/CB) pesticides. Given their harmful effects, this study had two aims; first, to evaluate the effect of cumulative or chronic exposure to OP/CB pesticides on the neurobehavioral performance of agricultural workers and rural inhabitants; second, to determine if changes in the neurobehavioral performance are associated to changes in blood biomarkers of OP/CB pesticides during the spray season, when exposure is higher.

METHODS

For the first aim, a cross sectional study of neurobehavioral performance in adult volunteers (men and women, 18-50 years-old, right-handed) was carried out in the pre-spray season. Sampling was done by convenience and a questionnaire was used to categorize participants depending on their level of chronic exposure, as either: occupationally exposed (OE, n = 87), environmentally exposed (EE, n = 81), or non-exposed controls or reference group (RG, n = 100). A neurobehavioral test battery consisting of 21 tests to measure cognitive, motor and emotional state was applied. For the second aim, neurobehavioral measures were taken a second time from EE and OE groups during the spray season, and their exposure corroborated by blood-based biomarker inhibition.

RESULTS

Lower neurobehavioral performance was observed in the pre-spray evaluation of EE and OE groups compared to the non-exposed, OE being the worst performing group. Seasonal exposure impaired performance in both exposure groups on all tests except those on attention and mood. Data modeling of the basal (pre-spray) measurements showed that the level of exposure was the best predictor of performance. During spraying, inhibition of BChE activity in the EE group was the best predictor of low performance in tests measuring logical, auditory and visual memory, inhibitory control of cognitive interference, constructional and planning abilities, executive functions, and motor speed and coordination.

CONCLUSION

Long-term occupational or environmental exposure to pesticides caused impairment in neurobehavioral functioning, which worsened during the spraying season, mainly in EE. BChE inhibition was the best predictor for seasonal neurobehavioral changes in EE.

Integration of Machine Learning Methods to Dissect Genetically Imputed Transcriptomic Profiles in Alzheimer's Disease

The genetic component of many common traits is associated with the gene expression and several variants act as expression quantitative loci, regulating the gene expression in a tissue specific manner. In this work, we applied tissue-specific cis-eQTL gene expression prediction models on the genotype of 808 samples including controls, subjects with mild cognitive impairment, and patients with Alzheimer's Disease. We then dissected the imputed transcriptomic profiles by means of different unsupervised and supervised machine learning approaches to identify potential biological associations. Our analysis suggests that unsupervised and supervised methods can provide complementary information, which can be integrated for a better characterization of the underlying biological system. In particular, a variational autoencoder representation of the transcriptomic profiles, followed by a support vector machine classification, has been used for tissue-specific gene prioritizations. Interestingly, the achieved gene prioritizations can be efficiently integrated as a feature selection step for improving the accuracy of deep learning classifier networks. The identified gene-tissue information suggests a potential role for inflammatory and regulatory processes in gut-brain axis related tissues. In line with the expected low heritability that can be apportioned to eQTL variants, we were able to achieve only relatively low prediction capability with deep learning classification models. However, our analysis revealed that the classification power strongly depends on the network structure, with recurrent neural networks being the best performing network class. Interestingly, cross-tissue analysis suggests a potentially greater role of models trained in brain tissues also by considering dementia-related endophenotypes. Overall, the present analysis suggests that the combination of supervised and unsupervised machine learning techniques can be used for the evaluation of high dimensional omics data.

What are the earlier life contributions to reserve and resilience?

The brain's structures and functions arise from a combination of developmental processes and interaction with environmental experiences, beginning in utero and continuing throughout the lifespan. Broadly, the process that we think of as "successful aging" likely has its foundation in early life and is continuously shaped as life experiences are programmed into the brain in response to a changing environment. Thus, individual lifestyle choices and interventions aimed at increasing cognitive reserve and resilience could change the course of cognitive aging. To determine the relative efficacy of these approaches, we will need to understand how the timing of these interventions (e.g., age, duration, frequency) influences cognitive capacity through the lifespan. Although analysis of age-related changes in cognitive function reveals a general decline at the population level, it has become clear that there is great individual variance in the extent to which cognitive function changes with advanced age. The factors responsible for the individual differences in cognitive decline are unclear, but uncovering them with new analytical tools, epigenetic approaches, and subpopulation studies will provide a roadmap toward enhancing reserve and resilience in the population at large and preserving cognitive function in a greater number of aging individuals.