Enhancing genome-wide populus trait prediction through deep convolutional neural networks.

As a promising model, genome-based plant breeding has greatly promoted the improvement of agronomic traits. Traditional methods typically adopt linear regression models with clear assumptions, neither obtaining the linkage between phenotype and genotype nor providing good ideas for modification. Nonlinear models are well characterized in capturing complex nonadditive effects, filling this gap under traditional methods. Taking populus as the research object, this paper constructs a deep learning method, DCNGP, which can effectively predict the traits including 65 phenotypes. The method was trained on three datasets, and compared with other four classic models-Bayesian ridge regression (BRR), Elastic Net, support vector regression, and dualCNN. The results show that DCNGP has five typical advantages in performance: strong prediction ability on multiple experimental datasets; the incorporation of batch normalization layers and Early-Stopping technology enhancing the generalization capabilities and prediction stability on test data; learning potent features from the data and thus circumventing the tedious steps of manual production; the introduction of a Gaussian Noise layer enhancing predictive capabilities in the case of inherent uncertainties or perturbations; fewer hyperparameters aiding to reduce tuning time across datasets and improve auto-search efficiency. In this way, DCNGP shows powerful predictive ability from genotype to phenotype, which provide an important theoretical reference for building more robust populus breeding programs.

White Matter Plasticity Underpins Cognitive Gains After Multidomain Adaptive Computerized Cognitive Training.

BACKGROUND: This study aims to evaluate the effectiveness of computerized cognitive training (CCT) on white matter (WM) neuroplasticity and neuropsychological performance. METHODS: A total of 128 community older adults (64.36 ±â€…6.14 years) were recruited and randomly assigned to the intervention or control group. Participants in the intervention group received a home-based, multidomain, and adaptive CCT for 30 minutes, 2 days per week for 1 year. Neuropsychological assessments, diffusion magnetic resonance imaging (MRI), and T1-weighted structural MRI were performed at the pre- and post-intervention visits. RESULTS: Eighty-one of 128 participants (41 in the intervention group and 40 in the control group) completed the 1-year intervention, and 61 of them (27 in the intervention group and 34 in the control group) underwent MRI scans twice. After excluding attrition bias, a significant time-by-group interaction on the Stroop Color-Word Test (SCWT; F = 51.85, p < .001) was found, showing improvement in the intervention group and a decline in the control group. At the brain level, the intervention group exhibited increased axial diffusivity in the left posterior thalamic radiation, and this increase was significantly correlated with reduced SCWT reaction time (r = ‒0.42, p = .029). No significant time-by-group interactions were found for gray matter volume. CONCLUSIONS: Our findings suggest that conducting multidomain adaptive CCT is an effective and feasible method to counteract cognitive decline in older adults, with WM neuroplasticity underpinning cognitive improvements. This study contributes to the understanding of the neural basis for the beneficial effect of CCT for older adults.

Cognitive Training Effect and Imaging Evidence.

Cognitive intervention is a specific form of non-pharmacological intervention used to combat cognitive dysfunction. In this chapter, behavioral and neuroimaging studies about cognitive interventions are introduced. Regarding intervention studies, the form of intervention and the effects of the interventions have been systematically sorted out. In addition, we compared the effects of different intervention approaches, which help people with different cognitive states to choose appropriate intervention programs. With the development of imaging technology, many studies have discussed the neural mechanism of cognitive intervention training and the effects of cognitive intervention from the perspective of neuroplasticity. Behavioral studies and neural mechanism studies are used to improve the understanding of cognitive interventions for the treatment of cognitive impairment.

Lifestyle Adjustment: Influential Risk Factors in Cognitive Aging.

Cognitive aging is inevitable. However, researchers have demonstrated that lifestyle adjustments can reduce the risk of cognitive impairment. A healthy diet style, the Mediterranean diet, has been proven to benefit the elderly. Oil, salt, sugar, and fat are, on the contrary, risk factors for cognitive dysfunction because of the resultant high caloric intake. Physical and mental exercises, especially cognitive training, are also beneficial for aging. At the same time, several risk factors need to be noted, such as smoking, alcohol consumption, insomnia, and excessive daytime sleeping, which are highly relative to cognitive impairment, cardiovascular diseases, and dementia.

APOE influences working memory in non-demented elderly through an interaction with SPON1 rs2618516.

Exploring how risk genes cumulatively impair brain function in preclinical phase (i.e., in cognitively normal elderly) could provide critical insights into the pathophysiology of Alzheimer's disease (AD). Working memory impairment has always been a considerable cognitive deficit in AD, which is likely under complex genetic control. Though, the APOE ɛ4 allele could damage the working memory performance in normal elderly, dissociable results have been reported. This allele may exert specific effects in contexts with other genetic variants. The rs2618516 in the spondin 1 gene (SPON1) has been associated with AD risk and brain structure in the elderly. SPON1 may interact with APOE through processing the amyloid precursor protein and suppressing amyloid-ß levels. Using neuropsychological tasks from 710 individuals, we found significant SPON1 × APOE genotype interactions in working memory and executive function performances. Moreover, such interaction was also found in regional brain activations based on functional magnetic resonance imaging data with the n-back working memory task performed in a sub-cohort of 64 subjects. The effects of ɛ4 allele on activation of right inferior frontal gyrus, triangular part (IFGtriang.R) were modulated by rs2618516 in a working memory task. Furthermore, lower IFGtriang.R activation was associated with better cognitive functions. Moreover, the IFGtriang.R activation could mediate the impacts of SPON1 × APOE interactions on working memory performance. These findings suggested the importance of weighing APOE effects on brain activation under the working memory task within the context of the SPON1 genotype.

The Interactive Effects of Age and PICALM rs541458 Polymorphism on Cognitive Performance, Brain Structure, and Function in Non-demented Elderly.

The PICALM rs541458 T allele has been recognized as a risk factor for late-onset Alzheimer's disease, and age might modulate the effects that genetic factors have on cognitive functions and brain. Thus, the current study intended to examine whether the effects of rs541458 on cognitive functions, brain structure, and function were modulated by age in non-demented Chinese elderly. We enrolled 638 subjects aged 50 to 82 years and evaluated their cognitive functions through a series of neuropsychological tests. Seventy-eight of these participants also received T1-weighted structural and resting state functional magnetic resonance imaging. Dividing subjects into groups <65 and ≥65 years old, results of neuropsychological tests showed that interactive effects of rs541458 × age existed with regard to executive function and processing speed after controlling for gender, years of education and APOE ε4 status. In addition, the effects of rs541458 on resting state functional connectivity of left superior parietal gyrus within left frontal-parietal network and on gray matter volume of left middle temporal gyrus were modulated by age. Furthermore, reduction of functional connectivity of left superior parietal gyrus was closely related with better executive function in the T allele carriers <65 years old. Further, greater volume of left middle temporal gyrus was significantly related to better executive function in both CC genotype <65 years old and CC genotype ≥65 years old groups, separately. Pending further confirmation from additional studies, our results support the hypothesis that the modulation of age, with respect to the rs541458, has interactional effects on cognitive performance, brain function, and structural measurements.