Search

Imaging genetic studies aim to find associations between genetic variants and imaging quantitative traits. Traditional genome-wide association studies (GWAS) are based on univariate statistical tests, but when multiple traits are analyzed together they suffer from a multiple-testing problem and from not taking into account correlations among the traits. An alternative approach to multi-trait GWAS is to reverse the functional relation between genotypes and traits, by fitting a multivariate regression model to predict genotypes from multiple traits simultaneously. However, current reverse genotype prediction approaches are mostly based on linear models. Here, we evaluated random forest regression (RFR) as a method to predict SNPs from imaging QTs and identify biologically relevant associations. We learned machine learning models to predict 518,484 SNPs using 56 brain imaging QTs. We observed that genotype regression error is a better indicator of permutation p-value significance than genotype classification accuracy. SNPs within the known Alzheimer disease (AD) risk gene APOE had lowest RMSE for lasso and random forest, but not ridge regression. Moreover, random forests identified additional SNPs that were not prioritized by the linear models but are known to be associated with brain-related disorders. Feature selection identified well-known brain regions associated with AD,like the hippocampus and amygdala, as important predictors of the most significant SNPs. In summary, our results indicate that non-linear methods like random forests may offer additional insights into phenotype-genotype associations compared to traditional linear multi-variate GWAS methods.

Multi-trait genome-wide association studies (GWAS) use multi-variate statistical methods to identify associations between genetic variants and multiple correlated traits simultaneously, and have higher statistical power than independent univariate analyses of traits. Reverse regression, where genotypes of genetic variants are regressed on multiple traits simultaneously, has emerged as a promising approach to perform multi-trait GWAS in high-dimensional settings where the number of traits exceeds the number of samples. We analyzed different machine learning methods (ridge regression, naive Bayes/independent univariate, random forests and support vector machines) for reverse regression in multi-trait GWAS, using genotypes, gene expression data and ground-truth transcriptional regulatory networks from the DREAM5 SysGen Challenge and from a cross between two yeast strains to evaluate methods. We found that genotype prediction performance, in terms of root mean squared error (RMSE), allowed to distinguish between genomic regions with high and low transcriptional activity. Moreover, model feature coefficients correlated with the strength of association between variants and individual traits, and were predictive of true trans-eQTL target genes, with complementary findings across methods. Code to reproduce the analysis is available at https://github.com/michoel-lab/Reverse-Pred-GWAS

This paper is concerned with the regulation control of a one-dimensional reaction-diffusion equation in the presence of a state-delay in the reaction term. The objective is to achieve the PI regulation of the right Dirichlet trace with a command selected as the left Dirichlet trace. The control design strategy consists of the design of a PI controller on a finite dimensional truncated model obtained by spectral reduction. By an adequate selection of the number of modes of the original infinite-dimensional system, we show that the proposed control design procedure achieves both the exponential stabilization of the original infinite-dimensional system as well as the setpoint regulation of the right Dirichlet trace., Comment: Accepted for publication in Automatica

Random effect models are popular statistical models for detecting and correcting spurious sample correlations due to hidden confounders in genome-wide gene expression data. In applications where some confounding factors are known, estimating simultaneously the contribution of known and latent variance components in random effect models is a challenge that has so far relied on numerical gradient-based optimizers to maximize the likelihood function. This is unsatisfactory because the resulting solution is poorly characterized and the efficiency of the method may be suboptimal. Here we prove analytically that maximum-likelihood latent variables can always be chosen orthogonal to the known confounding factors, in other words, that maximum-likelihood latent variables explain sample covariances not already explained by known factors. Based on this result we propose a restricted maximum-likelihood method which estimates the latent variables by maximizing the likelihood on the restricted subspace orthogonal to the known confounding factors, and show that this reduces to probabilistic PCA on that subspace. The method then estimates the variance-covariance parameters by maximizing the remaining terms in the likelihood function given the latent variables, using a newly derived analytic solution for this problem. Compared to gradient-based optimizers, our method attains greater or equal likelihood values, can be computed using standard matrix operations, results in latent factors that don't overlap with any known factors, and has a runtime reduced by several orders of magnitude. Hence the restricted maximum-likelihood method facilitates the application of random effect modelling strategies for learning latent variance components to much larger gene expression datasets than possible with current methods., Comment: 15 pages, 4 figures, 3 supplementary figures, 19 pages supplementary methods; minor revision with expanded Discussion section

This paper presents I-nteract, a cyber-physical system that enables real-time interaction with real and virtual objects in a mixed augmented reality environment to design 3D models for additive manufacturing. The system has been developed using mixed reality technologies such as HoloLens, for augmenting visual feedback, and haptic gloves, for augmenting haptic force feedback. The efficacy of the system has been demonstrated by generating 3D model using a novel scanning method to 3D print a customized orthopedic cast for human arm, by estimating spring rates of compression springs, and by simulating interaction with a virtual spring using hand.

I-nteract is a cyber-physical system that enables real-time interaction with both virtual and real artifacts to design 3D models for additive manufacturing by leveraging on mixed reality technologies. This paper presents novel advances in the development of the interaction platform I-nteract to generate 3D models using both constructive solid geometry and artificial intelligence. The system also enables the user to adjust the dimensions of the 3D models with respect to their physical workspace. The effectiveness of the system is demonstrated by generating 3D models of furniture (e.g., chairs and tables) and fitting them into the physical space in a mixed reality environment.

Our objective in this paper is to review the application of feedback ideas in the area of additive manufacturing. Both the application of feedback control to the 3D printing process, and the application of feedback theory to enable users to interact better with machines, are reviewed. Where appropriate, opportunities for future work are highlighted., Comment: Preprint

Non-PR, IFPRI1; BioSight; CRP2; A Ensuring Sustainable food production, EPTD; PIM, CGIAR Research Program on Policies, Institutions, and Markets (PIM), Agent-based models (ABM) have become an important tool for natural resource management in recent decades, and for the study of agricultural change in particular (e.g., Becu, Perez, Walker, Barreteau, & Page, 2003; Bell, 2011; Bert et al., 2010). Where household-level decisions, made in interaction with other households and the natural environment, shape outcomes at the landscape scale, ABM can provide insights that coarser equation-based models (EBM) or statistical models may not (Bankes, 2002; Paranuk et al. 1998). ABM provide as well a unique point of entry for non-expert stakeholders into the analytic process because it offers a 1:1 mapping of real-world actors to computational agents, which provides a level of conceptual understanding and familiarity that is not available when EBM or statistical models are used. Furthermore, the actor behaviours that are formalized within the computational code that defines an agent’s behavior can be represented in a variety of ways (e.g., heuristic decision trees, utility functions) that are again easier for non-expert stakeholders to than the equations and constraints of other modeling approaches.

Non-PR, IFPRI1; PSSP, DSGD, The form and function of many cities are increasingly marred by congestion, sprawl and socioeconomic segregation, preventing them from experiencing expected productivity gains associated with urbanization. We operationalize these insights by creating a stylized agent-based model of a theoretical city, inspired by social complexity theory and the new urban literature.