MOTIVATION: Genome-wide association studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice. RESULTS: We develop, apply, and comparatively evaluate an automated machine learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures. AVAILABILITY AND IMPLEMENTATION: Code for this study is available at: https://github.com/mensxmachina/autoML-GWAS. JADBio offers a free version at: https://jadbio.com/sign-up/. SNP data can be downloaded from the EGA repository (https://ega-archive.org/). PRS data are found at: https://www.aicrowd.com/challenges/opensnp-height-prediction. Simulation data to study population structure can be found at: https://easygwas.ethz.ch/data/public/dataset/view/1/.

Feature selection for predictive analytics is the problem of identifying a minimal-size subset of features that is maximally predictive of an outcome of interest. To apply to molecular data, feature selection algorithms need to be scalable to tens of thousands of features. In this paper, we propose γ-OMP, a generalisation of the highly-scalable Orthogonal Matching Pursuit feature selection algorithm. γ-OMP can handle (a)various types of outcomes, such as continuous, binary, nominal, time-to-event, (b)discrete (categorical)features, (c)different statistical-based stopping criteria, (d)several predictive models (e.g., linear or logistic regression), (e)various types of residuals, and (f)different types of association. We compare γ-OMP against LASSO, a prototypical, widely used algorithm for high-dimensional data. On both simulated data and several real gene expression datasets, γ-OMP is on par, or outperforms LASSO in binary classification (case-control data), regression (quantified outcomes), and time-to-event data (censored survival times). γ-OMP is based on simple statistical ideas, it is easy to implement and to extend, and our extensive evaluation shows that it is also effective in bioinformatics analysis settings.

High-throughput technologies such as microarrays and RNA-sequencing (RNA-seq) allow to precisely quantify transcriptomic profiles, generating datasets that are inevitably high-dimensional. In this work, we investigate whether the whole human transcriptome can be represented in a compressed, low dimensional latent space without loosing relevant information. We thus constructed low-dimensional latent feature spaces of the human genome, by utilizing three dimensionality reduction approaches and a diverse set of curated datasets. We applied standard Principal Component Analysis (PCA), kernel PCA and Autoencoder Neural Networks on 1360 datasets from four different measurement technologies. The latent feature spaces are tested for their ability to (a) reconstruct the original data and (b) improve predictive performance on validation datasets not used during the creation of the feature space. While linear techniques show better reconstruction performance, nonlinear approaches, particularly, neural-based models seem to be able to capture non-additive interaction effects, and thus enjoy stronger predictive capabilities. Despite the limited sample size of each dataset and the biological / technological heterogeneity across studies, our results show that low dimensional representations of the human transcriptome can be achieved by integrating hundreds of datasets. The created space is two to three orders of magnitude smaller compared to the raw data, offering the ability of capturing a large portion of the original data variability and eventually reducing computational time for downstream analyses.

We present ePGA (electronic Pharmacogenomics Assistant), a web-based system that offers two main services to the engaged pharmacogenomic biomedical communities namely, explore — a service to search and browse through established pharmacogenomic gene-drug associations, and translate — a service to infer metabolizing phenotypes from individual genotype profiles. Furthermore, we present our work on utilizing a machine-learning methodology (decision-tree induction) in order to induce generalized pharmacogenomic translation models from known haplotype-tables that are able to infer the metabolizer status of individuals from their genotype profiles. Preliminary results are highly predictive, and highlight the potential of the whole approach. The whole work falls into the rising field of Pharmacogenomic Informatics.

The overwhelmed amount of medical information available online, makes the use of automated recommendation methods essential for identifying relevant information according to user profile needs. This paper presents a method to address the problem of medical document classification into documents for medical professionals (experts) and non-professionals (consumers). Documents are represented by terms extracted from AMTEx, a medical document indexing method, specifically designed for the automatic indexing of documents in large medical collections, such as MEDLINE, and then mapped to the UMLS Semantic Network (SN) categories. Multiple Criteria Decision Analysis (MCDA) tools are applied to calculate the membership of each SN category to the document classification. Several factors such as the classification nature of the problem and the incorporation of common readability formulas are also examined.

UTARec, a Recommender System that incorporates Multiple Criteria Analysis methodologies is presented. The system's performance and capability of addressing certain shortfalls of existing Recommender Systems is demonstrated in the case of movie recommendations. UTARec's accuracy is measured in terms of Kendall's tau and ROC curve analysis and is also compared to a Multiple Rating Collaborative Filtering (MRCF) approach. The results indicate that the proposed Multiple Criteria Analysis methodology can certainly improve the recommendation process by producing highly accurate results, from a user oriented perspective.

Designing optimal product lines is essential for any firm to stay competitive. Whereas a large number of optimization algorithms have been applied for solving the problem, most of them adopt the first choice rule to simulate the consumer's choice process. Researchers avoid using probabilistic choice models, such as the logit, since they tend to produce duplicate products in the line, due to the IIA problem. Furthermore preference heterogeneity among consumers is a factor usually neglected, although its representation form has a substantial impact in the design of the product line. We propose a probabilistic choice model that can be used with algorithms that solve the optimal product line design problem, using the share of choices criterion. Our model deals with the IIA problem, by incorporating the similarity among products through the use of a corrective method. In addition, preference heterogeneity among consumers is effectively represented, while the model's predictive accuracy is optimized through the use of Stochastic Logarithmic Search and Genetic Algorithms.