In humans, the inheritance of the XX or XY set of sex chromosomes is responsible for most individuals developing into adults expressing male or female sex-specific traits. However, the degree to which sex-biased gene expression occurs in tissues, especially those that do not contribute to characteristic sexually dimorphic traits. is unknown. Oliva et al. examined Genotype-Tissue Expression (GTEx) project data and found that 37% of genes in at least one of the 44 tissues studied exhibit a tissue-specific, sex-biased gene expression. They also identified a sex-specific variation in cellular composition across tissues. Overall, the effects of sex on gene expression were small, but they were genome-wide and mostly mediated through transcription factor binding. With sex-biased gene expression associated with loci identified in genome-wide association studies, this study lays the groundwork for identifying the molecular basis of male- and female-based diseases. Science , this issue p. [eaba3066][1] ### INTRODUCTION Many complex human phenotypes, including diseases, exhibit sex-differentiated characteristics. These sex differences have been variously attributed to hormones, sex chromosomes, genotype × sex effects, differences in behavior, and differences in environmental exposures; however, their mechanisms and underlying biology remain largely unknown. The Genotype-Tissue Expression (GTEx) project provides an opportunity to investigate the prevalence and genetic mechanisms of sex differences in the human transcriptome by surveying many tissues that have not previously been characterized in this manner. ### RATIONALE To characterize sex differences in the human transcriptome and its regulation, and to discover how sex and genetics interact to influence complex traits and disease, we generated a catalog of sex differences in gene expression and its genetic regulation across 44 human tissue sources surveyed by the GTEx project (v8 data release), analyzing 16,245 RNA-sequencing samples and genotypes of 838 adult individuals. We report sex differences in gene expression levels, tissue cell type composition, and cis expression quantitative trait loci (cis-eQTLs). To assess their impact, we integrated these results with gene function, transcription factor binding annotation, and genome-wide association study (GWAS) summary statistics of 87 GWASs. ### RESULTS Sex effects on gene expression are ubiquitous (13,294 sex-biased genes across all tissues). However, these effects are small and largely tissue-specific. Genes with sex-differentiated expression are not primarily driven by tissue-specific gene expression and are involved in a diverse set of biological functions, such as drug and hormone response, embryonic development and tissue morphogenesis, fertilization, sexual reproduction and spermatogenesis, fat metabolism, cancer, and immune response. Whereas X-linked genes with higher expression in females suggest candidates for escape from X-chromosome inactivation, sex-biased expression of autosomal genes suggests hormone-related transcription factor regulation and a role for additional transcription factors, as well as sex-differentiated distribution of epigenetic marks, particularly histone H3 Lys27 trimethylation (H3K27me3). Sex differences in the genetic regulation of gene expression are much less common (369 sex-biased eQTLs across all tissues) and are highly tissue-specific. We identified 58 gene-trait associations driven by genetic regulation of gene expression in a single sex. These include loci where sex-differentiated cell type abundances mediate genotype-phenotype associations, as well as loci where sex may play a more direct role in the underlying molecular mechanism of the association. For example, we identified a female-specific eQTL in liver for the hexokinase HKDC1 that influences glucose metabolism in pregnant females, which is subsequently reflected in the birth weight of the offspring. ### CONCLUSION By integrating sex-aware analyses of GTEx data with gene function and transcription factor binding annotations, we describe tissue-specific and tissue-shared drivers and mechanisms contributing to sex differences in the human transcriptome and eQTLs. We discovered multiple sex-differentiated genetic effects on gene expression that colocalize with complex trait genetic associations, thereby facilitating the mechanistic interpretation of GWAS signals. Because the causative tissue is unknown for many phenotypes, analysis of the diverse GTEx tissue collection can serve as a powerful resource for investigations into the basis of sex-biased traits. This work provides an extensive characterization of sex differences in the human transcriptome and its genetic regulation. ![Figure][2] Sex affects gene expression and its genetic regulation across tissues. Sex effects on gene expression were measured in 44 GTEx human tissue sources and integrated with genotypes of 838 subjects. Sex-biased expression is present in numerous biological pathways and is associated to sex-differentiated transcriptional regulation. Sex-biased expression quantitative trait loci in cis (sex-biased eQTLs) are partially mediated by cellular abundances and reveal gene-trait associations. TT, AT, and AA are genotypes for a single-nucleotide polymorphism; TF, transcription factor. Many complex human phenotypes exhibit sex-differentiated characteristics. However, the molecular mechanisms underlying these differences remain largely unknown. We generated a catalog of sex differences in gene expression and in the genetic regulation of gene expression across 44 human tissue sources surveyed by the Genotype-Tissue Expression project (GTEx, v8 release). We demonstrate that sex influences gene expression levels and cellular composition of tissue samples across the human body. A total of 37% of all genes exhibit sex-biased expression in at least one tissue. We identify cis expression quantitative trait loci (eQTLs) with sex-differentiated effects and characterize their cellular origin. By integrating sex-biased eQTLs with genome-wide association study data, we identify 58 gene-trait associations that are driven by genetic regulation of gene expression in a single sex. These findings provide an extensive characterization of sex differences in the human transcriptome and its genetic regulation. [1]: /lookup/doi/10.1126/science.aba3066 [2]: pending:yes

The Genotype-Tissue Expression (GTEx) project was established to characterize genetic effects on the transcriptome across human tissues and to link these regulatory mechanisms to trait and disease associations. Here, we present analyses of the version 8 data, examining 15,201 RNA-sequencing samples from 49 tissues of 838 postmortem donors. We comprehensively characterize genetic associations for gene expression and splicing in cis and trans, showing that regulatory associations are found for almost all genes, and describe the underlying molecular mechanisms and their contribution to allelic heterogeneity and pleiotropy of complex traits. Leveraging the large diversity of tissues, we provide insights into the tissue specificity of genetic effects and show that cell type composition is a key factor in understanding gene regulatory mechanisms in human tissues.

Before anything, make sure to understand to core components of neural networks as well as their mechanisms. There is a ton of online documentation about feedforward neural networks in their most basic form (here, here and here), make sure to check it out. To demonstrate classification, I will model constructiveness in Amazon reviews (4000 reviews) with Libra's neural network. I have worked on a similar task in a previous article and in my master's thesis (in which I describe the dataset in more details), in case you are interested. You can perform classification in Libra with the classification_query_ann() method from the client object.

A new function, K-Means Clustering, allows data points to be grouped together based on similarity and is highly useful for customer segmentation, fraud detection and many other use cases. In addition, Insight Advisor will now auto-generate cluster and correlation charts in search-based visual analysis; Qlik plans to introduce new additional advanced calculations in the future.

Multi-objective gradient methods are becoming the standard for solving multi-objective problems. Among others, they show promising results in developing multi-objective recommender systems with both correlated and uncorrelated objectives. Classic multi-gradient descent usually relies on the combination of the gradients, not including the computation of first and second moments of the gradients. This leads to a brittle behavior and misses important areas in the solution space. In this work, we create a multi-objective Adamize method that leverage the benefits of the Adam optimizer in single-objective problems. This corrects and stabilizes the gradients of every objective before calculating a common gradient descent vector that optimizes all the objectives simultaneously. We evaluate the benefits of Multi-objective Adamize on two multi-objective recommender systems and for three different objective combinations, both correlated or uncorrelated. We report significant improvements, measured with three different Pareto front metrics: hypervolume, coverage, and spacing. Finally, we show that the Adamized Pareto front strictly dominates the previous one on multiple objective pairs.

In the WWW (World Wide Web), dynamic development and spread of data has resulted a tremendous amount of information available on the Internet, yet user is unable to find relevant information in a short span of time. Consequently, a system called recommendation system developed to help users find their infromation with ease through their browsing activities. In other words, recommender systems are tools for interacting with large amount of information that provide personalized view for prioritizing items likely to be of keen for users. They have developed over the years in artificial intelligence techniques that include machine learning and data mining amongst many to mention. Furthermore, the recommendation systems have personalized on an e-commerce, on-line applications such as Amazon.com, Netflix, and Booking.com. As a result, this has inspired many researchers to extend the reach of recommendation systems into new sets of challenges and problem areas that are yet to be truly solved, primarily a problem with the case of making a recommendation to a new user that is called cold-state (i.e. cold-start) user problem where the new user might likely not yield much of information searched. Therfore, the purpose of this paper is to tackle the said cold-start problem with a few effecient methods and challenges, as well as identify and overview the current state of recommendation system as a whole

The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has focused on the problem of optimizing the learning process itself. In this paper we study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior, or default behavior that constrains the space of solutions and serves as a bias for exploration; as well as a representation for the value function, both of which are easily learned from a number of training tasks in a multi-task scenario. Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.

We introduce deep switching auto-regressive factorization (DSARF), a deep generative model for spatio-temporal data with the capability to unravel recurring patterns in the data and perform robust short- and long-term predictions. Similar to other factor analysis methods, DSARF approximates high dimensional data by a product between time dependent weights and spatially dependent factors. These weights and factors are in turn represented in terms of lower dimensional latent variables that are inferred using stochastic variational inference. DSARF is different from the state-of-the-art techniques in that it parameterizes the weights in terms of a deep switching vector auto-regressive likelihood governed with a Markovian prior, which is able to capture the non-linear inter-dependencies among weights to characterize multimodal temporal dynamics. This results in a flexible hierarchical deep generative factor analysis model that can be extended to (i) provide a collection of potentially interpretable states abstracted from the process dynamics, and (ii) perform short- and long-term vector time series prediction in a complex multi-relational setting. Our extensive experiments, which include simulated data and real data from a wide range of applications such as climate change, weather forecasting, traffic, infectious disease spread and nonlinear physical systems attest the superior performance of DSARF in terms of long- and short-term prediction error, when compared with the state-of-the-art methods.

Recent studies on the weight space of deep neural networks [1, 2] have highlighted the existence of rare subdominant clusters of configurations which yield a high test accuracy. Although these clusters constitute a deviation from typicality, they are efficiently encountered by stochastic gradient descent (SGD) algorithms and correspond to wide valleys of suitable loss functions, such as cross entropy [3]. An analogous circumstance occurs in the context of constraint satisfaction problems, where the chase after clusters of solutions is improved when the loss function gets supplemented by a term that encourages a local high density of solutions [4]. In order to find the number of solutions contained in a vicinity of a specific weight configuration, one can define a local solution-counting functional, namely, a local entropy. Classification tasks performed by means of quantized neural networks (where the weights are discrete) can be interpreted as constraint satisfaction problems. There are however two reasons to generalize the concept of local entropy: First, classification problems are typically required to reach a high but not necessarily perfect accuracy; second, they are often approached with machines that have continuous weights.

Graph neural networks (GNNs) have been shown with superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs. Some recent work started to study the pre-training of GNNs. However, none of them provide theoretical insights into the design of their frameworks, or clear requirements and guarantees towards the transferability of GNNs. In this work, we establish a theoretically grounded and practically useful framework for the transfer learning of GNNs. Firstly, we propose a novel view towards the essential graph information and advocate the capturing of it as the goal of transferable GNN training, which motivates the design of Ours, a novel GNN framework based on ego-graph information maximization to analytically achieve this goal. Secondly, we specify the requirement of structure-respecting node features as the GNN input, and derive a rigorous bound of GNN transferability based on the difference between the local graph Laplacians of the source and target graphs. Finally, we conduct controlled synthetic experiments to directly justify our theoretical conclusions. Extensive experiments on real-world networks towards role identification show consistent results in the rigorously analyzed setting of direct-transfering, while those towards large-scale relation prediction show promising results in the more generalized and practical setting of transfering with fine-tuning.