The integration of multi-omics data holds great promise for identifying robust and clinically relevant biomarkers, yet the increasing complexity of computational methods raises questions about their practical utility. In this study, we present a comprehensive benchmarking framework that evaluates 27 feature selection strategies and 11 predictive models across three real-world disease cohorts: Alzheimer's disease, progressive supranuclear palsy, and breast cancer. We compare traditional machine learning, ensemble-based methods, and state-of-the-art deep learning models in terms of predictive performance, stability, and biological interpretability. Our results reveal that ensemble feature selection consistently improves robustness and accuracy, particularly for compact biomarker panels. Surprisingly, deep learning models did not outperform simpler classifiers such as logistic regression (L.Regression), support vector machines, or multilayer perceptrons, which often achieved comparable or superior results with lower computational cost and greater interpretability. Triple-omics yielded the highest validation, followed by dual-omics and then single-omics (Triple > Dual > Single). Biological validation against five independent databases confirmed the clinical relevance of the identified biomarkers, including both well-established and novel candidates. To support reproducibility and community adoption, we provide a web-based tool for applying our benchmarking pipeline. Our findings advocate for a pragmatic approach to biomarker discovery-prioritizing methodological transparency, reproducibility, and biological insight over algorithmic complexity.

Biomarkers play a pivotal role in disease diagnosis and prognosis by offering molecular insights into biological states. The rapid growth of high-throughput omics technologies has enabled the generation of large-scale biomarker datasets, yet analyzing these complex, high-dimensional data remains a major challenge-particularly for researchers lacking advanced computational expertise. While numerous tools exist for omics data analysis, many fall short in providing an integrated, user-friendly environment tailored specifically for biomarker discovery and interpretation. To address this gap, we present BioMark, a web-based platform designed to streamline biomarker analysis across diverse omics types. BioMark integrates robust statistical methods with widely used machine learning algorithms to support key workflows including statistical analysis, dimensionality reduction, classification, and subsequent model explanation. The platform emphasizes accessibility, offering intuitive visualizations and automated reporting to facilitate interpretation and dissemination of results. Notably, BioMark also offers a feature-ranking strategy that consolidates outputs from multiple analytical methods, enhancing the robustness of biomarker identification. By lowering the barrier to advanced biomarker analytics, BioMark empowers a broader range of researchers to uncover clinically relevant molecular signatures and accelerate translational research. Biomark is available online at https://bioinf.itu.edu.tr/biomark .

Web-based metabolomics databases store relative metabolite abundance datasets measured under different physiological conditions. However, their pathway-level analysis capabilities are mostly limited to superimposing the measurements onto the pathways of the measured metabolites. Besides, none of the existing metabolomics databases offer tools to store, manage, compare, and search metabolomics analysis results. In this paper, we present MetaboliticsDB, which features a database of metabolomics analyses and a set of associated analytics tools. It enables users to store and compare their metabolomics analysis results against others to study, for instance, the progression of a disease. Moreover, MetaboliticsDB implements a genome-scale metabolic network-based analysis tool (i.e., Metabolitics) that performs network-based flux analysis. Besides, MetaboliticsDB features an advanced querying interface offering flexible criteria, such as listing all analyses where a certain pathway experiences a major increase in activity, to help researchers identify conditions sharing a similar mechanism. Finally, MetaboliticsDB employs AI-based models to associate the studied metabolomics data with diseases. Currently, the database contains analysis results for 2,174 individuals and 40 diseases. We demonstrate MetaboliticsDB's usage with a case study on Hepatocellular Carcinoma. Our experimental evaluation shows that MetaboliticsDB provides biologically relevant metabolic network-level analysis results, disease association with high accuracy, and a scalable architecture.

The metabolic wiring of patient cells is altered drastically in many diseases, including cancer. Understanding the nature of such changes may pave the way for new therapeutic opportunities as well as the development of personalized treatment strategies for patients. In this paper, we propose an algorithm called Metabolitics, which allows systems-level analysis of changes in the biochemical network of cells in disease states. It enables the study of a disease at both reaction- and pathway-level granularities for a detailed and summarized view of disease etiology. Metabolitics employs flux variability analysis with a dynamically built objective function based on biofluid metabolomics measurements in a personalized manner. Moreover, Metabolitics builds supervised classification models to discriminate between patients and healthy subjects based on the computed metabolic network changes. The use of Metabolitics is demonstrated for three distinct diseases, namely, breast cancer, Crohn's disease, and colorectal cancer. Our results show that the constructed supervised learning models successfully differentiate patients from healthy individuals by an average f1-score of 88 percent. Besides, in addition to the confirmation of previously reported breast cancer-associated pathways, we discovered that Biotin Metabolism along with Arginine and Proline Metabolism is subject to a significant increase in flux capacity, which have not been reported before.

Predicting promising academic papers is useful for a variety of parties, including researchers, universities, scientific councils, and policymakers. Researchers may benefit from such data to narrow down their reading list and focus on what will be important, and policymakers may use predictions to infer rising fields for a more strategic distribution of resources. This paper proposes a novel technique to predict a paper's future impact (i.e., number of citations) by using temporal and topological features derived from citation networks. We use a behavioral modeling approach in which the temporal change in the number of citations a paper gets is clustered, and new papers are evaluated accordingly. Then, within each cluster, we model the impact prediction as a regression problem where the objective is to predict the number of citations that a paper will get in the near or far future, given the early citation performance of the paper. The results of empirical evaluations on data from several well-known citation databases show that the proposed framework performs significantly better than the state of the art approaches.

Contact: [email protected]

New graph structures where node labels are members of hierarchically organized ontologies or taxonomies have become commonplace in different domains, e.g., life sciences. It is a challenging task to mine for frequent patterns in this new graph model which we call taxonomy-superimposed graphs, as there may be many patterns that are implied by the generalization/specialization hierarchy of the associated node label taxonomy. Hence, standard graph mining techniques are not directly applicable. In this paper, we present Taxogram, a taxonomy-superimposed graph mining algorithm that can efficiently discover frequent graph structures in a database of taxonomy-superimposed graphs. Taxogram has two advantages: (i) It performs a subgraph isomorphism test once per class of patterns which are structurally isomorphic, but have different labels, and (ii) it reconciles standard graph mining methods with taxonomy-based graph mining and takes advantage of well-studied methods in the literature. Taxogram has three stages: (a) relabeling nodes in the input database, (b) mining pattern classes/families and constructing associated occurrence indices, and (c) computing patterns and eliminating useless (i.e., over-generalized) patterns by post-processing occurrence indices. Experimental results show that Taxogram is significantly more efficient and more scalable compared to other alternative approaches. 1.

MOTIVATION: As the blueprints of cellular actions, biological pathways characterize the roles of genomic entities in various cellular mechanisms, and as such, their availability, manipulation and queriability over the web is important to facilitate ongoing biological research. RESULTS: In this article, we present the new features of PathCase, a system to store, query, visualize and analyze metabolic pathways at different levels of genetic, molecular, biochemical and organismal detail. The new features include: (i) a web-based system with a new architecture, containing a server-side and a client-side, and promoting scalability, and flexible and easy adaptation of different pathway databases, (ii) an interactive client-side visualization tool for metabolic pathways, with powerful visualization capabilities, and with integrated gene and organism viewers, (iii) two distinct querying capabilities: an advanced querying interface for computer savvy users, and built-in queries for ease of use, that can be issued directly from pathway visualizations and (iv) a pathway functionality analysis tool. PathCase is now available for three different datasets, namely, KEGG pathways data, sample pathways from the literature and BioCyc pathways for humans. AVAILABILITY: Available online at http://nashua.case.edu/pathways

BACKGROUND: Genes and gene products are frequently annotated with Gene Ontology concepts based on the evidence provided in genomics articles. Manually locating and curating information about a genomic entity from the biomedical literature requires vast amounts of human effort. Hence, there is clearly a need forautomated computational tools to annotate the genes and gene products with Gene Ontology concepts by computationally capturing the related knowledge embedded in textual data. RESULTS: In this article, we present an automated genomic entity annotation system, GEANN, which extracts information about the characteristics of genes and gene products in article abstracts from PubMed, and translates the discoveredknowledge into Gene Ontology (GO) concepts, a widely-used standardized vocabulary of genomic traits. GEANN utilizes textual "extraction patterns", and a semantic matching framework to locate phrases matching to a pattern and produce Gene Ontology annotations for genes and gene products. In our experiments, GEANN has reached to the precision level of 78% at therecall level of 61%. On a select set of Gene Ontology concepts, GEANN either outperforms or is comparable to two other automated annotation studies. Use of WordNet for semantic pattern matching improves the precision and recall by 24% and 15%, respectively, and the improvement due to semantic pattern matching becomes more apparent as the Gene Ontology terms become more general. CONCLUSION: GEANN is useful for two distinct purposes: (i) automating the annotation of genomic entities with Gene Ontology concepts, and (ii) providing existing annotations with additional "evidence articles" from the literature. The use of textual extraction patterns that are constructed based on the existing annotations achieve high precision. The semantic pattern matching framework provides a more flexible pattern matching scheme with respect to "exactmatching" with the advantage of locating approximate pattern occurrences with similar semantics. Relatively low recall performance of our pattern-based approach may be enhanced either by employing a probabilistic annotation framework based on the annotation neighbourhoods in textual data, or, alternatively, the statistical enrichment threshold may be adjusted to lower values for applications that put more value on achieving higher recall values.

Functional characterizations of pathways provide new opportunities in defining, understanding, and comparing existing biological pathways, and in helping discover new ones in different organisms. In this paper, we present and evaluate computational techniques for categorizing pathways, based upon the Gene Ontology (GO) annotations of enzymes within metabolic pathways. Our approach is to use the notion of functionality templates, GO-functional graphs of pathways. Pathway categorization is then achieved through learning models built on different characteristics of functionality templates. We have experimentally evaluated the accuracy of automated pathway categorization with respect to different learning models and their parameters. Using KEGG metabolic pathways, the pathway categorization tool reaches to 90% and higher accuracy.

MOTIVATION: Biological pathways provide significant insights on the interaction mechanisms of molecules. Presently, many essential pathways still remain unknown or incomplete for newly sequenced organisms. Moreover, experimental validation of enormous numbers of possible pathway candidates in a wet-lab environment is time- and effort-extensive. Thus, there is a need for comparative genomics tools that help scientists predict pathways in an organism's biological network. RESULTS: In this article, we propose a technique to discover unknown pathways in organisms. Our approach makes in-depth use of Gene Ontology (GO)-based functionalities of enzymes involved in metabolic pathways as follows: i. Model each pathway as a biological functionality graph of enzyme GO functions, which we call pathway functionality template. ii. Locate frequent pathway functionality patterns so as to infer previously unknown pathways through pattern matching in metabolic networks of organisms. We have experimentally evaluated the accuracy of the presented technique for 30 bacterial organisms to predict around 1500 organism-specific versions of 50 reference pathways. Using cross-validation strategy on known pathways, we have been able to infer pathways with 86% precision and 72% recall for enzymes (i.e. nodes). The accuracy of the predicted enzyme relationships has been measured at 85% precision with 64% recall. AVAILABILITY: Code upon request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Biological Web data sources have now become essential information sources for researchers. However, their use is tedious, labor-intensive, repetitive, and possibly involve the integration of data from multiple Web data sources. In this paper, as a first step towards the full integration of Web data sources, we propose a framework that allows an integrated use of biological sources in a task-oriented manner. We define and experimentally evaluate a toolkit-based framework for semi-automatically constructing an integrated (software) system that automates and optimizes the execution of a biology-related computational task at hand. To test and refine the principles of the framework, we build and evaluate "pathway-infer" as a benchmark integrated system

Signaling pathways are chains of interacting proteins, through which the cell converts a (usually) extracellular signal into a biological response. The number of known signaling pathways in the biological literature and on the Web has been increasing at a very high rate, thus demanding a need for efficient ways of storing, visualizing, querying, and mining signaling pathways. In this paper, first we briefly compare the data modeling and visualization capabilities of existing signaling pathways systems. Then, we present a signaling pathway data model and its visualization that subsumes the existing models. Our model visualizes a signaling pathway (a) as a nested graph, (b) with explicit location information (e.g., cell, tissue, organelle, nucleus, etc.), and (c) in four abstraction levels, namely, the levels of molecule-to-molecule signaling steps, collapsed sub-pathways, molecule-to-pathway connections, and pathway-to-pathway connections. We model (1) the effects of specific signaling steps, (2) state changes of signaling molecules, (3) various (extensible) structural/physical changes of signaling molecules such as complex formation, dissociation, assembly, oligomerization, di-/trimerization, cleavage and degradation, (4) condensation/hydrolysis signaling steps, and (5) exchanges and translocations as signaling steps. The visualization model gracefully models incomplete information and hierarchical levels of signaling molecules. Finally, we introduce a completely new visualization dimension for pathways, namely, gene ontology (GO)-based functional visualizations of pathways. We believe that functional visualizations of pathways provides new opportunities in understanding, defining and comparing existing pathways, and in helping discover new ones