The selection of biomarker panels in omics data, challenged by numerous molecular features and limited samples, often requires the use of machine learning methods paired with wrapper feature selection techniques, like genetic algorithms. They test various feature sets-potential biomarker solutions-to fine-tune a machine learning model's performance for supervised tasks, such as classifying cancer subtypes. This optimization process is undertaken using validation sets to evaluate and identify the most effective feature combinations. Evaluations have performance estimation error, measurable as discrepancy between validation and test set performance, and when the selection involves many models the best ones are almost certainly overestimated. This issue is also relevant in a multi-objective feature selection process where various characteristics of the biomarker panels are optimized, such as predictive performances and feature set size. Methods have been proposed to reduce the overestimation after a model has already been selected in single-objective problems, but no algorithm existed capable of reducing the overestimation during the optimization, improving model selection, or applied in the more general multi-objective domain. We propose Dual-stage Optimizer for Systematic overestimation Adjustment in Multi-Objective problems (DOSA-MO), a novel multi-objective optimization wrapper algorithm that learns how the original estimation, its variance, and the feature set size of the solutions predict the overestimation. DOSA-MO adjusts the expectation of the performance during the optimization, improving the composition of the solution set. We verify that DOSA-MO improves the performance of a state-of-the-art genetic algorithm on left-out or external sample sets, when predicting cancer subtypes and/or patient overall survival, using three transcriptomics datasets for kidney and breast cancer.

MOTIVATION: Cancer is a very heterogeneous disease that can be difficult to treat without addressing the specific mechanisms driving tumour progression in a given patient. High-throughput screening and sequencing data from cancer cell-lines has driven many developments in drug development, however, there are important aspects crucial to precision medicine that are often overlooked, namely the inherent differences between tumours in patients and the cell-lines used to model them in vitro. Recent developments in transfer learning methods for patient and cell-line data have shown progress in translating results from cell-lines to individual patients in silico. However, transfer learning can be forceful and there is a risk that clinically relevant patterns in the omics profiles of patients are lost in the process. RESULTS: We present MODAE, a novel deep learning algorithm to integrate omics profiles from cell-lines and patients for the purposes of exploring precision medicine opportunities. MODAE implements patient survival prediction as an additional task in a drug-sensitivity transfer learning schema and aims to balance autoencoding, domain adaptation, drug-sensitivity prediction, and survival prediction objectives in order to better preserve the heterogeneity between patients that is relevant to survival. While burdened with these additional tasks, MODAE performed on par with baseline survival models, but struggled in the drug-sensitivity prediction task. Nevertheless, these preliminary results were promising and show that MODAE provides a novel AI-based method for prioritizing drug treatments for high-risk patients. AVAILABILITY AND IMPLEMENTATION: https://github.com/UEFBiomedicalInformaticsLab/MODAE.

Recent research on multi-view clustering algorithms for complex disease subtyping often overlooks aspects like clustering stability and critical assessment of prognostic relevance. Furthermore, current frameworks do not allow for a comparison between data-driven and pathway-driven clustering, highlighting a significant gap in the methodology. We present the COPS R-package, tailored for robust evaluation of single and multi-omics clustering results. COPS features advanced methods, including similarity networks, kernel-based approaches, dimensionality reduction, and pathway knowledge integration. Some of these methods are not accessible through R, and some correspond to new approaches proposed with COPS. Our framework was rigorously applied to multi-omics data across seven cancer types, including breast, prostate, and lung, utilizing mRNA, CNV, miRNA, and DNA methylation data. Unlike previous studies, our approach contrasts data- and knowledge-driven multi-view clustering methods and incorporates cross-fold validation for robustness. Clustering outcomes were assessed using the ARI score, survival analysis via Cox regression models including relevant covariates, and the stability of the results. While survival analysis and gold-standard agreement are standard metrics, they vary considerably across methods and datasets. Therefore, it is essential to assess multi-view clustering methods using multiple criteria, from cluster stability to prognostic relevance, and to provide ways of comparing these metrics simultaneously to select the optimal approach for disease subtype discovery in novel datasets. Emphasizing multi-objective evaluation, we applied the Pareto efficiency concept to gauge the equilibrium of evaluation metrics in each cancer case-study. Affinity Network Fusion, Integrative Non-negative Matrix Factorization, and Multiple Kernel K-Means with linear or Pathway Induced Kernels were the most stable and effective in discerning groups with significantly different survival outcomes in several case studies.

Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases.

The network approach is quickly becoming a fundamental building block of computational methods aiming at elucidating the mechanism of action (MoA) and therapeutic effect of drugs. By modeling the effect of drugs and diseases on different biological networks, it is possible to better explain the interplay between disease perturbations and drug targets as well as how drug compounds induce favorable biological responses and/or adverse effects. Omics technologies have been extensively used to generate the data needed to study the mechanisms of action of drugs and diseases. These data are often exploited to define condition-specific networks and to study whether drugs can reverse disease perturbations. In this review, we describe network data mining algorithms that are commonly used to study drug's MoA and to improve our understanding of the basis of chronic diseases. These methods can support fundamental stages of the drug development process, including the identification of putative drug targets, the in silico screening of drug compounds and drug combinations for the treatment of diseases. We also discuss recent studies using biological and omics-driven networks to search for possible repurposed FDA-approved drug treatments for SARS-CoV-2 infections (COVID-19).

MOTIVATION: In modern translational research, the development of biomarkers heavily relies on use of omics technologies, but implementations with basic data mining algorithms frequently lead to false positives. Non-dominated Sorting Genetic Algorithm II (NSGA2) is an extremely effective algorithm for biomarker discovery but has been rarely evaluated against large-scale datasets. The exploration of the feature search space is the key to NSGA2 success but in specific cases NSGA2 expresses a shallow exploration of the space of possible feature combinations, possibly leading to models with low predictive performances. RESULTS: We propose two improved NSGA2 algorithms for finding subsets of biomarkers exhibiting different trade-offs between accuracy and feature number. The performances are investigated on gene expression data of breast cancer patients. The results are compared with NSGA2 and LASSO. The benchmarking dataset includes internal and external validation sets. The results show that the proposed algorithms generate a better approximation of the optimal trade-offs between accuracy and set size. Moreover, validation and test accuracies are better than those provided by NSGA2 and LASSO. Remarkably, the GA-based methods provide biomarkers that achieve a very high prediction accuracy (>80%) with a small number of features (<10), representing a valid alternative to known biomarker models, such as Pam50 and MammaPrint. AVAILABILITY AND IMPLEMENTATION: The software is publicly available on GitHub at github.com/UEFBiomedicalInformaticsLab/BIODAI/tree/main/MOO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PURPOSE: Endocrine disruptors are a rising concern due to the wide array of health issues that it can cause. Although there are tools for mode of action (MoA)-based prediction of endocrine disruption (e.g. QSAR Toolbox and iSafeRat), none of them is based on toxicogenomics data. Here, we present EDTox, an R Shiny application enabling users to explore and use a computational method that we have recently published to identify and prioritize endocrine disrupting (ED) chemicals based on toxicogenomic data. The EDTox pipeline utilizes previously trained toxicogenomic-driven classifiers to make predictions on new untested compounds by using their molecular initiating events. Furthermore, the proposed R Shiny app allows users to extend the prediction systems by training and adding new classifiers based on new available toxicogenomic data. This functionality helps users to explore the ED potential of chemicals in new, untested exposure scenarios. AVAILABILITY AND IMPLEMENTATION: This tool is available as web application (www.edtox.fi) and stand-alone software on GitHub and Zenodo (https://doi.org/10.5281/zenodo.5817093). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Typical clustering analysis for large-scale genomics data combines two unsupervised learning techniques: dimensionality reduction and clustering (DR-CL) methods. It has been demonstrated that transforming gene expression to pathway-level information can improve the robustness and interpretability of disease grouping results. This approach, referred to as biological knowledge-driven clustering (BK-CL) approach, is often neglected, due to a lack of tools enabling systematic comparisons with more established DR-based methods. Moreover, classic clustering metrics based on group separability tend to favor the DR-CL paradigm, which may increase the risk of identifying less actionable disease subtypes that have ambiguous biological and clinical explanations. Hence, there is a need for developing metrics that assess biological and clinical relevance. To facilitate the systematic analysis of BK-CL methods, we propose a computational protocol for quantitative analysis of clustering results derived from both DR-CL and BK-CL methods. Moreover, we propose a new BK-CL method that combines prior knowledge of disease relevant genes, network diffusion algorithms and gene set enrichment analysis to generate robust pathway-level information. Benchmarking studies were conducted to compare the grouping results from different DR-CL and BK-CL approaches with respect to standard clustering evaluation metrics, concordance with known subtypes, association with clinical outcomes and disease modules in co-expression networks of genes. No single approach dominated every metric, showing the importance multi-objective evaluation in clustering analysis. However, we demonstrated that, on gene expression data sets derived from TCGA samples, the BK-CL approach can find groupings that provide significant prognostic value in both breast and prostate cancers.

The drug discovery process starts with identification of a disease-modifying target. This critical step traditionally begins with manual investigation of scientific literature and biomedical databases to gather evidence linking molecular target to disease, and to evaluate the efficacy, safety and commercial potential of the target. The high-throughput and affordability of current omics technologies, allowing quantitative measurements of many putative targets (e.g. DNA, RNA, protein, metabolite), has exponentially increased the volume of scientific data available for this arduous task. Therefore, computational platforms identifying and ranking disease-relevant targets from existing biomedical data sources, including omics databases, are needed. To date, more than 30 drug target discovery (DTD) platforms exist. They provide information-rich databases and graphical user interfaces to help scientists identify putative targets and pre-evaluate their therapeutic efficacy and potential side effects. Here we survey and compare a set of popular DTD platforms that utilize multiple data sources and omics-driven knowledge bases (either directly or indirectly) for identifying drug targets. We also provide a description of omics technologies and related data repositories which are important for DTD tasks.

SUMMARY: Estimating efficacy of gene-target-disease associations is a fundamental step in drug discovery. An important data source for this laborious task is RNA expression, which can provide gene-disease associations on the basis of expression fold change and statistical significance. However, the simply use of the log-fold change can lead to numerous false-positive associations. On the other hand, more sophisticated methods that utilize gene co-expression networks do not consider tissue specificity. Here, we introduce Transcriptome-driven Efficacy estimates for gene-based TArget discovery (ThETA), an R package that enables non-expert users to use novel efficacy scoring methods for drug-target discovery. In particular, ThETA allows users to search for gene perturbation (therapeutics) that reverse disease-gene expression and genes that are closely related to disease-genes in tissue-specific networks. ThETA also provides functions to integrate efficacy evaluations obtained with different approaches and to build an overall efficacy score, which can be used to identify and prioritize gene(target)-disease associations. Finally, ThETA implements visualizations to show tissue-specific interconnections between target and disease-genes, and to indicate biological annotations associated with the top selected genes. AVAILABILITY AND IMPLEMENTATION: ThETA is freely available for academic use at https://github.com/vittoriofortino84/ThETA. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Omics technologies have the potential to facilitate the discovery of new biomarkers. However, only few omics-derived biomarkers have been successfully translated into clinical applications to date. Feature selection is a crucial step in this process that identifies small sets of features with high predictive power. Models consisting of a limited number of features are not only more robust in analytical terms, but also ensure cost effectiveness and clinical translatability of new biomarker panels. Here we introduce GARBO, a novel multi-island adaptive genetic algorithm to simultaneously optimize accuracy and set size in omics-driven biomarker discovery problems. RESULTS: Compared to existing methods, GARBO enables the identification of biomarker sets that best optimize the trade-off between classification accuracy and number of biomarkers. We tested GARBO and six alternative selection methods with two high relevant topics in precision medicine: cancer patient stratification and drug sensitivity prediction. We found multivariate biomarker models from different omics data types such as mRNA, miRNA, copy number variation, mutation and DNA methylation. The top performing models were evaluated by using two different strategies: the Pareto-based selection, and the weighted sum between accuracy and set size (w = 0.5). Pareto-based preferences show the ability of the proposed algorithm to search minimal subsets of relevant features that can be used to model accurate random forest-based classification systems. Moreover, GARBO systematically identified, on larger omics data types, such as gene expression and DNA methylation, biomarker panels exhibiting higher classification accuracy or employing a number of features much lower than those discovered with other methods. These results were confirmed on independent datasets. AVAILABILITY AND IMPLEMENTATION: github.com/Greco-Lab/GARBO. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Quantitative structure-activity relationship (QSAR) modelling is currently used in multiple fields to relate structural properties of compounds to their biological activities. This technique is also used for drug design purposes with the aim of predicting parameters that determine drug behaviour. To this end, a sophisticated process, involving various analytical steps concatenated in series, is employed to identify and fine-tune the optimal set of predictors from a large dataset of molecular descriptors (MDs). The search of the optimal model requires to optimize multiple objectives at the same time, as the aim is to obtain the minimal set of features that maximizes the goodness of fit and the applicability domain (AD). Hence, a multi-objective optimization strategy, improving multiple parameters in parallel, can be applied. Here we propose a new multi-niche multi-objective genetic algorithm that simultaneously enables stable feature selection as well as obtaining robust and validated regression models with maximized AD. We benchmarked our method on two simulated datasets. Moreover, we analyzed an aquatic acute toxicity dataset and compared the performances of single- and multi-objective fitness functions on different regression models. Our results show that our multi-objective algorithm is a valid alternative to classical QSAR modelling strategy, for continuous response values, since it automatically finds the model with the best compromise between statistical robustness, predictive performance, widest AD, and the smallest number of MDs. AVAILABILITY AND IMPLEMENTATION: The python implementation of MaNGA is available at https://github.com/Greco-Lab/MaNGA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Summary: Detecting and interpreting responsive modules from gene expression data by using network-based approaches is a common but laborious task. It often requires the application of several computational methods implemented in different software packages, forcing biologists to compile complex analytical pipelines. Here we introduce INfORM (Inference of NetwOrk Response Modules), an R shiny application that enables non-expert users to detect, evaluate and select gene modules with high statistical and biological significance. INfORM is a comprehensive tool for the identification of biologically meaningful response modules from consensus gene networks inferred by using multiple algorithms. It is accessible through an intuitive graphical user interface allowing for a level of abstraction from the computational steps. Availability and implementation: INfORM is freely available for academic use at https://github.com/Greco-Lab/INfORM. Supplementary information: Supplementary data are available at Bioinformatics online.

The use of high-throughput RNA sequencing to predict dynamic operon structures in prokaryotic genomes has recently gained popularity in bioinformatics. We provide the R implementation of a novel method that uses transcriptomic features extracted from RNA-seq transcriptome profiles to develop ensemble classifiers for condition-dependent operon predictions. The CONDOP package provides a deeper insight into RNA-seq data analysis and allows scientists to highlight the operon organization in the context of transcriptional regulation with a few lines of code. AVAILABILITY AND IMPLEMENTATION: CONDOP is implemented in R and is freely available at CRAN. CONTACT: [email protected] information: Supplementary data are available at Bioinformatics online.

BACKGROUND: DAVID is the most popular tool for interpreting large lists of gene/proteins classically produced in high-throughput experiments. However, the use of DAVID website becomes difficult when analyzing multiple gene lists, for it does not provide an adequate visualization tool to show/compare multiple enrichment results in a concise and informative manner. RESULT: We implemented a new R-based graphical tool, BACA (Bubble chArt to Compare Annotations), which uses the DAVID web service for cross-comparing enrichment analysis results derived from multiple large gene lists. BACA is implemented in R and is freely available at the CRAN repository ( http://cran.r-project.org/web/packages/BACA/ ). CONCLUSION: The package BACA allows R users to combine multiple annotation charts into one output graph by passing DAVID website.

BACKGROUND: OMICs technologies allow to assay the state of a large number of different features (e.g., mRNA expression, miRNA expression, copy number variation, DNA methylation, etc.) from the same samples. The objective of these experiments is usually to find a reduced set of significant features, which can be used to differentiate the conditions assayed. In terms of development of novel feature selection computational methods, this task is challenging for the lack of fully annotated biological datasets to be used for benchmarking. A possible way to tackle this problem is generating appropriate synthetic datasets, whose composition and behaviour are fully controlled and known a priori. RESULTS: Here we propose a novel method centred on the generation of networks of interactions among different biological molecules, especially involved in regulating gene expression. Synthetic datasets are obtained from ordinary differential equations based models with known parameters. Our results show that the generated datasets are well mimicking the behaviour of real data, for popular data analysis methods are able to selectively identify existing interactions. CONCLUSIONS: The proposed method can be used in conjunction to real biological datasets in the assessment of data mining techniques. The main strength of this method consists in the full control on the simulated data while retaining coherence with the real biological processes. The R package MVBioDataSim is freely available to the scientific community at http://neuronelab.unisa.it/?p=1722.

BACKGROUND: Multiple high-throughput molecular profiling by omics technologies can be collected for the same individuals. Combining these data, rather than exploiting them separately, can significantly increase the power of clinically relevant patients subclassifications. RESULTS: We propose a multi-view approach in which the information from different data layers (views) is integrated at the levels of the results of each single view clustering iterations. It works by factorizing the membership matrices in a late integration manner. We evaluated the effectiveness and the performance of our method on six multi-view cancer datasets. In all the cases, we found patient sub-classes with statistical significance, identifying novel sub-groups previously not emphasized in literature. Our method performed better as compared to other multi-view clustering algorithms and, unlike other existing methods, it is able to quantify the contribution of single views on the final results. CONCLUSION: Our observations suggest that integration of prior information with genomic features in the subtyping analysis is an effective strategy in identifying disease subgroups. The methodology is implemented in R and the source code is available online at http://neuronelab.unisa.it/a-multi-view-genomic-data-integration-methodology/ .

BACKGROUND: Inferring operon maps is crucial to understanding the regulatory networks of prokaryotic genomes. Recently, RNA-seq based transcriptome studies revealed that in many bacterial species the operon structure vary with the change of environmental conditions. Therefore, new computational solutions that use both static and dynamic data are necessary to create condition specific operon predictions. RESULTS: In this work, we propose a novel classification method that integrates RNA-seq based transcriptome profiles with genomic sequence features to accurately identify the operons that are expressed under a measured condition. The classifiers are trained on a small set of confirmed operons and then used to classify the remaining gene pairs of the organism studied. Finally, by linking consecutive gene pairs classified as operons, our computational approach produces condition-dependent operon maps. We evaluated our approach on various RNA-seq expression profiles of the bacteria Haemophilus somni, Porphyromonas gingivalis, Escherichia coli and Salmonella enterica. Our results demonstrate that, using features depending on both transcriptome dynamics and genome sequence characteristics, we can identify operon pairs with high accuracy. Moreover, the combination of DNA sequence and expression data results in more accurate predictions than each one alone. CONCLUSION: We present a computational strategy for the comprehensive analysis of condition-dependent operon maps in prokaryotes. Our method can be used to generate condition specific operon maps of many bacterial organisms for which high-resolution transcriptome data is available.