The COVID-19 pandemic, with its unprecedented challenges and disruptions, triggered a profound transformation in the retail industry . Health and safety regulations including periodic lockdowns , supply chain disruptions, and economic uncertainty affected the way businesses operate and led to a drastic change in consumer behaviour. This triggered the modification of traditional sales trends, which in turn impacted the accuracy of existing demand forecasting methods, and will affect their future performance. Moreover, the reliance of machine learning algorithms on historical sales data for training made them ill-equipped to adapt to these abrupt sales pattern shifts. Therefore, innovative solutions to address the complexities arising from this new landscape are needed. This paper introduces a framework aimed at enhancing demand forecasting accuracy in the post-pandemic period. Central to this framework is a feature engineering approach involving the creation of a predictor variable that encapsulates the level of restrictions imposed during the pandemic across seven distinct categories. This granular approach not only accounts for lockdowns and store closures but also considers indirect factors influencing retail sales, such as remote work arrangements and school closures. An extensive empirical evaluation of the proposed approach was conducted on a real-world retail dataset obtained from Charles Clinkard, a UK-based footwear retailer, demonstrating consistent improvements in forecasting accuracy across four deep probabilistic models and three levels of product aggregation in a real-life setting. Further validation utilising the Retail Sales Index dataset, which reflects monthly sales across various retail sectors in Great Britain, was also undertaken using six forecasting models, corroborating our initial findings. Overall, we show that leveraging historical sales data spanning the pandemic period – or, in general, any period where the data has inherent bias – is still viable for training machine learning models to forecast the demand, provided that an effective feature engineering approach is implemented.

Studies on understanding the regional seismological differences based on the variations in the characteristics of the ground motion waves recorded during seismic events have provided independent insights into different seismic environments of the world. Contrary to conventional beliefs and practices, this study aims to showcase the differences between seismic environments such as Japanese subduction, Chilean subduction, and Californian crustal. The study is based on developing deep learning-based surrogate generalized ground motion models (GGMMs) and analyzing them to understand the patterns between the earthquake source parameters and the resulting ground motion waveforms’ engineering characteristics. The GGMMs are developed using long short-term memory (LSTM) based recurrent neural networks (RNNs), which are trained using six earthquake source and site parameters as the inputs and a 25 × 1 vector of amplitude-, duration-, and energy-based ground motion intensity measures (IMs). The GGMMs are trained and evaluated using carefully selected large datasets of ground motion records from the Japanese subduction, Chilean subduction, and Californian crustal sources (∼2000 records from each source). The models are developed in two settings: i) three independent GGMMs using the three datasets, ii) one combined GGMM using the combined dataset. While the former provides individual surrogate models of the regional seismic environments and allows relative comparison among the three environments, the latter acts as a global seismic surrogate model and allows comparison in absolute terms. The seismic environments are investigated by analyzing the two types of GGMMs using explainable artificial intelligence (XAI) based Shapley explanations (SHAP). As the direct physical study of the seismic environments is not generally feasible/practical, the proposed GGMMs surrogating the process becomes a source of knowledge. By interpreting them, inferences about the seismic environments are derived. Results indicate the peculiar nature of the earthquakes arising from the three seismic backgrounds, further emphasizing the importance of conducting independent regional seismic hazard and risk analysis. In particular, the role of magnitude and rupture distance is observed to have a significantly different impact on the different IMs of three different environments. The study further provides a novel approach to utilize advanced deep learning and XAI methods in understanding convoluted physics and engineering phenomena.

Data are the most important elements of bioinformatics: Computational analysis of bioinformatics data, in fact, can help researchers infer new knowledge about biology, chemistry, biophysics, and sometimes even medicine, influencing treatments and therapies for patients. Bioinformatics and high-throughput biological data coming from different sources can even be more helpful, because each of these different data chunks can provide alternative, complementary information about a specific biological phenomenon, similar to multiple photos of the same subject taken from different angles. In this context, the integration of bioinformatics and high-throughput biological data gets a pivotal role in running a successful bioinformatics study. In the last decades, data originating from proteomics, metabolomics, metagenomics, phenomics, transcriptomics, and epigenomics have been labelled -omics data, as a unique name to refer to them, and the integration of these omics data has gained importance in all biological areas. Even if this omics data integration is useful and relevant, due to its heterogeneity, it is not uncommon to make mistakes during the integration phases. We therefore decided to present these ten quick tips to perform an omics data integration correctly, avoiding common mistakes we experienced or noticed in published studies in the past. Even if we designed our ten guidelines for beginners, by using a simple language that (we hope) can be understood by anyone, we believe our ten recommendations should be taken into account by all the bioinformaticians performing omics data integration, including experts.

MOTIVATION: Gene regulation is responsible for controlling numerous physiological functions and dynamically responding to environmental fluctuations. Reconstructing the human network of gene regulatory interactions is thus paramount to understanding the cell functional organization across cell types, as well as to elucidating pathogenic processes and identifying molecular drug targets. Although significant effort has been devoted towards this direction, existing computational methods mainly rely on gene expression levels, possibly ignoring the information conveyed by mechanistic biochemical knowledge. Moreover, except for a few recent attempts, most of the existing approaches only consider the information of the organism under analysis, without exploiting the information of related model organisms. RESULTS: We propose a novel method for the reconstruction of the human gene regulatory network, based on a transfer learning strategy that synergically exploits information from human and mouse, conveyed by gene-related metabolic features generated in silico from gene expression data. Specifically, we learn a predictive model from metabolic activity inferred via tissue-specific metabolic modelling of artificial gene knockouts. Our experiments show that the combination of our transfer learning approach with the constructed metabolic features provides a significant advantage in terms of reconstruction accuracy, as well as additional clues on the contribution of each constructed metabolic feature. AVAILABILITY AND IMPLEMENTATION: The method, the datasets and all the results obtained in this study are available at: https://doi.org/10.6084/m9.figshare.c.5237687. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Text-based communication is highly favoured as a communication mean, especially in business environments. As a result, it is often abused by sending malicious messages, e.g., spam emails, to deceive users into relaying personal information, including online accounts credentials or banking details. For this reason, many machine learning methods for text classification have been proposed and incorporated into the services of most providers. However, optimising text classification algorithms and finding the right tradeoff on their aggressiveness is still a major research problem. We present an updated survey of 12 machine learning text classifiers applied to a public spam corpus. A new pipeline is proposed to optimise hyperparameter selection and improve the models’ performance by applying specific methods (based on natural language processing) in the preprocessing stage. Our study aims to provide a new methodology to investigate and optimise the effect of different feature sizes and hyperparameters in machine learning classifiers that are widely used in text classification problems. The classifiers are tested and evaluated on different metrics including F-score (accuracy), precision, recall, and run time. B analysing all these aspects, we show how the proposed pipeline can be used to achieve a good accuracy towards spam filtering on the Enron dataset, a widely used public corpus. Statistical tests and explainability techniques (SHAP) are applied to provide a robust analysis of the proposed pipeline and interpret the classification outcomes of the 12 machine learning models, also identifying words that drive the classification results. Our analysis shows that it is possible to identify an effective machine learning model to classify the Enron dataset with an F-score of 94%. All data, models, and code used in this work are available on GitHub at https://github.com/Angione-Lab/12-machine-learning-models-for-text-classification.

MOTIVATION: High-throughput biological data, thanks to technological advances, have become cheaper to collect, leading to the availability of vast amounts of omic data of different types. In parallel, the in silico reconstruction and modeling of metabolic systems is now acknowledged as a key tool to complement experimental data on a large scale. The integration of these model- and data-driven information is therefore emerging as a new challenge in systems biology, with no clear guidance on how to better take advantage of the inherent multisource and multiomic nature of these data types while preserving mechanistic interpretation. RESULTS: Here, we investigate different regularization techniques for high-dimensional data derived from the integration of gene expression profiles with metabolic flux data, extracted from strain-specific metabolic models, to improve cellular growth rate predictions. To this end, we propose ad-hoc extensions of previous regularization frameworks including group, view-specific and principal component regularization and experimentally compare them using data from 1143 Saccharomyces cerevisiae strains. We observe a divergence between methods in terms of regression accuracy and integration effectiveness based on the type of regularization employed. In multiomic regression tasks, when learning from experimental and model-generated omic data, our results demonstrate the competitiveness and ease of interpretation of multimodal regularized linear models compared to data-hungry methods based on neural networks. AVAILABILITY AND IMPLEMENTATION: All data, models and code produced in this work are available on GitHub at https://github.com/Angione-Lab/HybridGroupIPFLasso_pc2Lasso. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Computational modelling of metabolic processes has proven to be a useful approach to formulate our knowledge and improve our understanding of core biochemical systems that are crucial to maintaining cellular functions. Towards understanding the broader role of metabolism on cellular decision-making in health and disease conditions, it is important to integrate the study of metabolism with other core regulatory systems and omics within the cell, including gene expression patterns. After quantitatively integrating gene expression profiles with a genome-scale reconstruction of human metabolism, we propose a set of combinatorial methods to reverse engineer gene expression profiles and to find pairs and higher-order combinations of genetic modifications that simultaneously optimize multi-objective cellular goals. This enables us to suggest classes of transcriptomic profiles that are most suitable to achieve given metabolic phenotypes. We demonstrate how our techniques are able to compute beneficial, neutral or "toxic" combinations of gene expression levels. We test our methods on nine tissue-specific cancer models, comparing our outcomes with the corresponding normal cells, identifying genes as targets for potential therapies. Our methods open the way to a broad class of applications that require an understanding of the interplay among genotype, metabolism, and cellular behaviour, at scale.

The use of data mining and modeling methods in service industry is a promising avenue for optimizing current processes in a targeted manner, ultimately reducing costs and improving customer experience. However, the introduction of such tools in already established pipelines often must adapt to the way data is sampled and to its content. In this study, we tackle the challenge of characterizing and predicting customer experience having available only process log data with time-stamp information, without any ground truth feedback from the customers. As a case study, we consider the context of a contact center managed by TeleWare and analyze phone call logs relative to a two months span. We develop an approach to interpret the phone call process events registered in the logs and infer concrete points of improvement in the service management. Our approach is based on latent tree modeling and multi-class Naïve Bayes classification, which jointly allow us to infer a spectrum of customer experiences and test their predictability based on the current data sampling strategy. Moreover, such approach can overcome limitations in customer feedback collection and sharing across organizations, thus having wide applicability and being complementary to tools relying on more heavily constrained data.

Gut microbiota and human relationships are strictly connected to each other. What we eat reflects our body-mind connection and synchronizes with people around us. However, how this impacts on gut microbiota and, conversely, how gut bacteria influence our dietary behaviors has not been explored yet. To quantify the complex dynamics of this interplay between gut and human behaviors we explore the "gut-human behavior axis" and its evolutionary dynamics in a real-world scenario represented by the social multiplex network. We consider a dual type of similarity, homophily and gut similarity, other than psychological and unconscious biases. We analyze the dynamics of social and gut microbial communities, quantifying the impact of human behaviors on diets and gut microbial composition and, backwards, through a control mechanism. Meal timing mechanisms and "chrono-nutrition" play a crucial role in feeding behaviors, along with the quality and quantity of food intake. Considering a population of shift workers, we explore the dynamic interplay between their eating behaviors and gut microbiota, modeling the social dynamics of chrono-nutrition in a multiplex network. Our findings allow us to quantify the relation between human behaviors and gut microbiota through the methodological introduction of gut metabolic modeling and statistical estimators, able to capture their dynamic interplay. Moreover, we find that the timing of gut microbial communities is slower than social interactions and shift-working, and the impact of shift-working on the dynamics of chrono-nutrition is a fluctuation of strategies with a major propensity for defection (e.g. high-fat meals). A deeper understanding of the relation between gut microbiota and the dietary behavioral patterns, by embedding also the related social aspects, allows improving the overall knowledge about metabolic models and their implications for human health, opening the possibility to design promising social therapeutic dietary interventions.

Omic data analysis is steadily growing as a driver of basic and applied molecular biology research. Core to the interpretation of complex and heterogeneous biological phenotypes are computational approaches in the fields of statistics and machine learning. In parallel, constraint-based metabolic modeling has established itself as the main tool to investigate large-scale relationships between genotype, phenotype, and environment. The development and application of these methodological frameworks have occurred independently for the most part, whereas the potential of their integration for biological, biomedical, and biotechnological research is less known. Here, we describe how machine learning and constraint-based modeling can be combined, reviewing recent works at the intersection of both domains and discussing the mathematical and practical aspects involved. We overlap systematic classifications from both frameworks, making them accessible to nonexperts. Finally, we delineate potential future scenarios, propose new joint theoretical frameworks, and suggest concrete points of investigation for this joint subfield. A multiview approach merging experimental and knowledge-driven omic data through machine learning methods can incorporate key mechanistic information in an otherwise biologically-agnostic learning process.

Metabolic modelling has entered a mature phase with dozens of methods and software implementations available to the practitioner and the theoretician. It is not easy for a modeller to be able to see the wood (or the forest) for the trees. Driven by this analogy, we here present a 'forest' of principal methods used for constraint-based modelling in systems biology. This provides a tree-based view of methods available to prospective modellers, also available in interactive version at http://modellingmetabolism.net, where it will be kept updated with new methods after the publication of the present manuscript. Our updated classification of existing methods and tools highlights the most promising in the different branches, with the aim to develop a vision of how existing methods could hybridize and become more complex. We then provide the first hands-on tutorial for multi-objective optimization of metabolic models in R. We finally discuss the implementation of multi-view machine learning approaches in poly-omic integration. Throughout this work, we demonstrate the optimization of trade-offs between multiple metabolic objectives, with a focus on omic data integration through machine learning. We anticipate that the combination of a survey, a perspective on multi-view machine learning and a step-by-step R tutorial should be of interest for both the beginner and the advanced user.

Motivation: Despite being often perceived as the main contributors to cell fate and physiology, genes alone cannot predict cellular phenotype. During the process of gene expression, 95% of human genes can code for multiple proteins due to alternative splicing. While most splice variants of a gene carry the same function, variants within some key genes can have remarkably different roles. To bridge the gap between genotype and phenotype, condition- and tissue-specific models of metabolism have been constructed. However, current metabolic models only include information at the gene level. Consequently, as recently acknowledged by the scientific community, common situations where changes in splice-isoform expression levels alter the metabolic outcome cannot be modeled. Results: We here propose GEMsplice, the first method for the incorporation of splice-isoform expression data into genome-scale metabolic models. Using GEMsplice, we make full use of RNA-Seq quantitative expression profiles to predict, for the first time, the effects of splice isoform-level changes in the metabolism of 1455 patients with 31 different breast cancer types. We validate GEMsplice by generating cancer-versus-normal predictions on metabolic pathways, and by comparing with gene-level approaches and available literature on pathways affected by breast cancer. GEMsplice is freely available for academic use at https://github.com/GEMsplice/GEMsplice_code. Compared to state-of-the-art methods, we anticipate that GEMsplice will enable for the first time computational analyses at transcript level with splice-isoform resolution. Availability and implementation: https://github.com/GEMsplice/GEMsplice_code. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Ageing can be classified in two different ways, chronological ageing and biological ageing. While chronological age is a measure of the time that has passed since birth, biological (also known as transcriptomic) ageing is defined by how time and the environment affect an individual in comparison to other individuals of the same chronological age. Recent research studies have shown that transcriptomic age is associated with certain genes, and that each of those genes has an effect size. Using these effect sizes we can calculate the transcriptomic age of an individual from their age-associated gene expression levels. The limitation of this approach is that it does not consider how these changes in gene expression affect the metabolism of individuals and hence their observable cellular phenotype. RESULTS: We propose a method based on poly-omic constraint-based models and machine learning in order to further the understanding of transcriptomic ageing. We use normalised CD4 T-cell gene expression data from peripheral blood mononuclear cells in 499 healthy individuals to create individual metabolic models. These models are then combined with a transcriptomic age predictor and chronological age to provide new insights into the differences between transcriptomic and chronological ageing. As a result, we propose a novel metabolic age predictor. CONCLUSIONS: We show that our poly-omic predictors provide a more detailed analysis of transcriptomic ageing compared to gene-based approaches, and represent a basis for furthering our knowledge of the ageing mechanisms in human cells.

BACKGROUND: Genomic, transcriptomic, and metabolic variations shape the complex adaptation landscape of bacteria to varying environmental conditions. Elucidating the genotype-phenotype relation paves the way for the prediction of such effects, but methods for characterizing the relationship between multiple environmental factors are still lacking. Here, we tackle the problem of extracting network-level information from collections of environmental conditions, by integrating the multiple omic levels at which the bacterial response is measured. RESULTS: To this end, we model a large compendium of growth conditions as a multiplex network consisting of transcriptomic and fluxomic layers, and we propose a multi-omic network approach to infer similarity of growth conditions by integrating layers of the multiplex network. Each node of the network represents a single condition, while edges are similarities between conditions, as measured by phenotypic and transcriptomic properties on different layers of the network. We then fuse these layers into one network, therefore capturing a global network of conditions and the associated similarities across two omic levels. We apply this multi-omic fusion to an updated genome-scale reconstruction of Escherichia coli that includes underground metabolism and new gene-protein-reaction associations. CONCLUSIONS: Our method can be readily used to evaluate and cross-compare different collections of conditions among different species. Acquiring multi-omic information on the topology of the space of experimental conditions makes it possible to infer the position and to build condition-specific models of untested or incomplete profiles for which experimental data is not available. Our weighted network fusion method for genome-scale models is freely available at https://github.com/maxconway/SNFtool .

We propose a framework to design metabolic pathways in which many objectives are optimized simultaneously. This allows to characterize the energy signature in models of algal and mitochondrial metabolism. The optimal design and assessment of the model is achieved through a multi-objective optimization technique driven by epsilon-dominance and identifiability analysis. A faster convergence process with robust candidate solutions is permitted by a relaxed Pareto dominance, regulating the granularity of the approximation of the Pareto front. Our framework is also suitable for black-box analysis, enabling to investigate and optimize any biological pathway modeled with ODEs, DAEs, FBA and GPR.

In low and high eukaryotes, energy is collected or transformed in compartments, the organelles. The rich variety of size, characteristics, and density of the organelles makes it difficult to build a general picture. In this paper, we make use of the Pareto-front analysis to investigate the optimization of energy metabolism in mitochondria and chloroplasts. Using the Pareto optimality principle, we compare models of organelle metabolism on the basis of single- and multiobjective optimization, approximation techniques (the Bayesian Automatic Relevance Determination), robustness, and pathway sensitivity analysis. Finally, we report the first analysis of the metabolic model for the hydrogenosome of Trichomonas vaginalis, which is found in several protozoan parasites. Our analysis has shown the importance of the Pareto optimality for such comparison and for insights into the evolution of the metabolism from cytoplasmic to organelle bound, involving a model order reduction. We report that Pareto fronts represent an asymptotic analysis useful to describe the metabolism of an organism aimed at maximizing concurrently two or more metabolite concentrations.

MOTIVATION: Metabolic engineering algorithms provide means to optimize a biological process leading to the improvement of a biotechnological interesting molecule. Therefore, it is important to understand how to act in a metabolic pathway in order to have the best results in terms of productions. In this work, we present a computational framework that searches for optimal and robust microbial strains that are able to produce target molecules. Our framework performs three tasks: it evaluates the parameter sensitivity of the microbial model, searches for the optimal genetic or fluxes design and finally calculates the robustness of the microbial strains. We are capable to combine the exploration of species, reactions, pathways and knockout parameter spaces with the Pareto-optimality principle. RESULTS: Our framework provides also theoretical and practical guidelines for design automation. The statistical cross comparison of our new optimization procedures, performed with respect to currently widely used algorithms for bacteria (e.g. Escherichia coli) over different multiple functions, reveals good performances over a variety of biotechnological products. AVAILABILITY: http://www.dmi.unict.it/nicosia/pathDesign.html. CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.