Omics-CNN: A comprehensive pipeline for predictive analytics in quantitative omics using one-dimensional convolutional neural networks.

Background and objective: The development of machine learning-based models that can be used for the prediction of severe diseases has been one of the main concerns of the scientific community. The current study seeks to expand a highly sophisticated tool, the Convolutional Neural Networks, making it applicable in multidimensional omics data classification problems and testing the newly introduced method on publicly available transcriptomics and proteomics data. Methods: In this study, we introduce Omics-CNN, a Convolutional Neural Network-based pipeline, which couples Convolutional Neural Networks with dimensionality reduction, preprocessing, clustering, and explainability techniques to make them suitable to build highly accurate and interpretable classification models from high-throughput omics data. The developed tool has the potential to classify patients depending on the expression of genetic and clinical factors and identify features that can act as diagnostic biomarkers. Regarding dimensionality reduction, univariate and multivariate techniques were explored and compared. Gradient Weighted Class Activation Mapping analysis was performed to determine the most important features in the classification of the samples after training the model. Results: The newly introduced pipeline was applied to one transcriptomics and one proteomics dataset for the identification of diagnostic models and biosignatures for Ischemic Stroke (IS) and COVID-19 infection, reporting highly accurate biosignatures with accuracies of 96 % and 95.41 %, respectively. Meanwhile, classification models based solely on a small part of attributes provided lower predictive accuracy, but identified compact transcript biosignature (KRT15, VPRBP, TNFRSF4, GORASP2) for Ischemic Stroke and protein biosignature (ADGRB3, VNN2, AGER, CIAPIN1) for Covid-19 infection diagnosis, respectively. Conclusions: Omics-CNN, overcame the inherent problems of applying Convolutional Neural Networks for the training diagnostic models with quantitative omics data, outperforming previous models of machine learning developed using the same datasets for Ischemic Stroke and Covid-19 infection diagnosis, determining the most contributing biomarkers for both diseases.

MEvA-X: a hybrid multiobjective evolutionary tool using an XGBoost classifier for biomarkers discovery on biomedical datasets.

MOTIVATION: Biomarker discovery is one of the most frequent pursuits in bioinformatics and is crucial for precision medicine, disease prognosis, and drug discovery. A common challenge of biomarker discovery applications is the low ratio of samples over features for the selection of a reliable not-redundant subset of features, but despite the development of efficient tree-based classification methods, such as the extreme gradient boosting (XGBoost), this limitation is still relevant. Moreover, existing approaches for optimizing XGBoost do not deal effectively with the class imbalance nature of the biomarker discovery problems, and the presence of multiple conflicting objectives, since they focus on the training of a single-objective model. In the current work, we introduce MEvA-X, a novel hybrid ensemble for feature selection (FS) and classification, combining a niche-based multiobjective evolutionary algorithm (EA) with the XGBoost classifier. MEvA-X deploys a multiobjective EA to optimize the hyperparameters of the classifier and perform FS, identifying a set of Pareto-optimal solutions and optimizing multiple objectives, including classification and model simplicity metrics. RESULTS: The performance of the MEvA-X tool was benchmarked using one omics dataset coming from a microarray gene expression experiment, and one clinical questionnaire-based dataset combined with demographic information. MEvA-X tool outperformed the state-of-the-art methods in the balanced categorization of classes, creating multiple low-complexity models and identifying important nonredundant biomarkers. The best-performing run of MEvA-X for the prediction of weight loss using gene expression data yields a small set of blood circulatory markers which are sufficient for this precision nutrition application but need further validation. AVAILABILITY AND IMPLEMENTATION: https://github.com/PanKonstantinos/MEvA-X.

Toward a general and interpretable umami taste predictor using a multi-objective machine learning approach.

The umami taste is one of the five basic taste modalities normally linked to the protein content in food. The implementation of fast and cost-effective tools for the prediction of the umami taste of a molecule remains extremely interesting to understand the molecular basis of this taste and to effectively rationalise the production and consumption of specific foods and ingredients. However, the only examples of umami predictors available in the literature rely on the amino acid sequence of the analysed peptides, limiting the applicability of the models. In the present study, we developed a novel ML-based algorithm, named VirtuousUmami, able to predict the umami taste of a query compound starting from its SMILES representation, thus opening up the possibility of potentially using such a model on any database through a standard and more general molecular description. Herein, we have tested our model on five databases related to foods or natural compounds. The proposed tool will pave the way toward the rationalisation of the molecular features underlying the umami taste and toward the design of specific peptide-inspired compounds with specific taste properties.

A survey on computational taste predictors.

Taste is a sensory modality crucial for nutrition and survival, since it allows the discrimination between healthy foods and toxic substances thanks to five tastes, i.e., sweet, bitter, umami, salty, and sour, associated with distinct nutritional or physiological needs. Today, taste prediction plays a key role in several fields, e.g., medical, industrial, or pharmaceutical, but the complexity of the taste perception process, its multidisciplinary nature, and the high number of potentially relevant players and features at the basis of the taste sensation make taste prediction a very complex task. In this context, the emerging capabilities of machine learning have provided fruitful insights in this field of research, allowing to consider and integrate a very large number of variables and identifying hidden correlations underlying the perception of a particular taste. This review aims at summarizing the latest advances in taste prediction, analyzing available food-related databases and taste prediction tools developed in recent years. Supplementary Information: The online version contains supplementary material available at 10.1007/s00217-022-04044-5.

Revisiting miRNA Association with Melanoma Recurrence and Metastasis from a Machine Learning Point of View.

The diagnostic and prognostic value of miRNAs in cutaneous melanoma (CM) has been broadly studied and supported by advanced bioinformatics tools. From early studies using miRNA arrays with several limitations, to the recent NGS-derived miRNA expression profiles, an accurate diagnostic panel of a comprehensive pre-specified set of miRNAs that could aid timely identification of specific cancer stages is still elusive, mainly because of the heterogeneity of the approaches and the samples. Herein, we summarize the existing studies that report several miRNAs as important diagnostic and prognostic biomarkers in CM. Using publicly available NGS data, we analyzed the correlation of specific miRNA expression profiles with the expression signatures of known gene targets. Combining network analytics with machine learning, we developed specific non-linear classification models that could successfully predict CM recurrence and metastasis, based on two newly identified miRNA signatures. Subsequent unbiased analyses and independent test sets (i.e., a dataset not used for training, as a validation cohort) using our prediction models resulted in 73.85% and 82.09% accuracy in predicting CM recurrence and metastasis, respectively. Overall, our approach combines detailed analysis of miRNA profiles with heuristic optimization and machine learning, which facilitates dimensionality reduction and optimization of the prediction models. Our approach provides an improved prediction strategy that could serve as an auxiliary tool towards precision treatment.

Pharmacoepigenomics circuits induced by a novel retinoid-polyamine conjugate in human immortalized keratinocytes.

Retinoids are widely used in diseases spanning from dermatological lesions to cancer, but exhibit severe adverse effects. A novel all-trans-Retinoic Acid (atRA)-spermine conjugate (termed RASP) has shown previously optimal in vitro and in vivo anti-inflammatory and anticancer efficacy, with undetectable teratogenic and toxic side-effects. To get insights, we treated HaCaT cells which resemble human epidermis with IC50 concentration of RASP and analyzed their miRNA expression profile. Gene ontology analysis of their predicted targets indicated dynamic networks involved in cell proliferation, signal transduction and apoptosis. Furthermore, DNA microarrays analysis verified that RASP affects the expression of the same categories of genes. A protein-protein interaction map produced using the most significant common genes, revealed hub genes of nodal functions. We conclude that RASP is a synthetic retinoid derivative with improved properties, which possess the beneficial effects of retinoids without exhibiting side-effects and with potential beneficial effects against skin diseases including skin cancer.

Reducing Opioid Prescriptions by Identifying Responders on Topical Analgesic Treatment Using an Individualized Medicine and Predictive Analytics Approach.

PURPOSE: Chronic pain is a life changing condition, and non-opioid treatments have been lately introduced to overcome the addictive nature of opioid therapies and their side effects. In the present study, we explore the potential of machine learning methods to discriminate chronic pain patients into ones who will benefit from such a treatment and ones who will not, aiming to personalize their treatment. PATIENTS AND METHODS: In the current study, data from the OPERA study were used, with 631 chronic pain patients answering the Brief Pain Inventory (BPI) validated questionnaire along with supplemental questions before and after a follow-up period. A novel machine learning approach combining multi-objective optimization and support vector regression was used to build prediction models which can predict, using responses in the baseline, the four different outcomes of the study: total drugs change, total interference change, total severity change, and total complaints change. Data were split to training (504 patients) and testing (127 patients) sets and all results are measured on the independent test set. RESULTS: The machine learning models extracted in the present study significantly overcame other state of the art machine learning methods which were deployed for comparative purposes. The experimental results indicated that the machine learning models can predict the outcomes of this study with considerably high accuracy (AUC 73.8-87.2%) and this allowed their incorporation in a decision support system for the selection of the treatment of chronic pain patients. CONCLUSION: Results of this study revealed the potential of machine learning for an individualized medicine application for chronic pain therapies. Topical analgesics treatment were proven to be, in general, beneficial but carefully selecting with the suggested individualized medicine decision support system was able to decrease by approximately 10% the patients which would have been subscribed with topical analgesics without having benefits from it.

Discovery of stroke-related blood biomarkers from gene expression network models.

BACKGROUND: Identifying molecular biomarkers characteristic of ischemic stroke has the potential to aid in distinguishing stroke cases from stroke mimicking symptoms, as well as advancing the understanding of the physiological changes that underlie the body's response to stroke. This study uses machine learning-based analysis of gene co-expression to identify transcription patterns characteristic of patients with acute ischemic stroke. METHODS: Mutual information values for the expression levels among 13,243 quantified transcripts were computed for blood samples from 82 stroke patients and 68 controls to construct a co-expression network of genes (separately) for stroke and control samples. Page rank centrality scores were computed for every gene; a gene's significance in the network was assessed according to the differences in their network's pagerank centrality between stroke and control expression patterns. A hybrid genetic algorithm - support vector machine learning tool was used to classify samples based on gene centrality in order to identify an optimal set of predictor genes for stroke while minimizing the number of genes in the model. RESULTS: A predictive model with 89.6% accuracy was identified using 6 network-central and differentially expressed genes (ID3, MBTPS1, NOG, SFXN2, BMX, SLC22A1), characterized by large differences in association network connectivity between stroke and control samples. In contrast, classification models based solely on individual genes identified by significant fold-changes in expression level provided lower predictive accuracies: < 71% for any single gene, and even models with larger (10-25) numbers of gene transcript biomarkers gave lower predictive accuracies (≤ 82%) than the 6 network-based gene signature classification. miRNA:mRNA target prediction computational analysis revealed 8 differentially expressed micro-RNAs (miRNAs) that are significantly associated with at least 2 of the 6 network-central genes. CONCLUSIONS: Network-based models have the potential to identify a more statistically robust pattern of gene expression typical of acute ischemic stroke and to generate hypotheses about possible interactions among functionally relevant genes, leading to the identification of more informative biomarkers.

Where we stand, where we are moving: Surveying computational techniques for identifying miRNA genes and uncovering their regulatory role.

Traditional biology was forced to restate some of its principles when the microRNA (miRNA) genes and their regulatory role were firstly discovered. Typically, miRNAs are small non-coding RNA molecules which have the ability to bind to the 3'untraslated region (UTR) of their mRNA target genes for cleavage or translational repression. Existing experimental techniques for their identification and the prediction of the target genes share some important limitations such as low coverage, time consuming experiments and high cost reagents. Hence, many computational methods have been proposed for these tasks to overcome these limitations. Recently, many researchers emphasized on the development of computational approaches to predict the participation of miRNA genes in regulatory networks and to analyze their transcription mechanisms. All these approaches have certain advantages and disadvantages which are going to be described in the present survey. Our work is differentiated from existing review papers by updating the methodologies list and emphasizing on the computational issues that arise from the miRNA data analysis. Furthermore, in the present survey, the various miRNA data analysis steps are treated as an integrated procedure whose aims and scope is to uncover the regulatory role and mechanisms of the miRNA genes. This integrated view of the miRNA data analysis steps may be extremely useful for all researchers even if they work on just a single step.