Late detection of plant diseases leads to irreparable losses for farmers, threatening global food security, economic stability, and environmental sustainability. This research introduces the Multi-Objective Genetic Algorithm Explainer (MOGAE), a novel model-agnostic local explainer for image data aimed at the early detection of citrus diseases. MOGAE enhances eXplainable Artificial Intelligence (XAI) by leveraging the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with an adaptive Bit Flip Mutation (BFM) incorporating densify and sparsify operators to adjust superpixel granularity automatically. This innovative approach simplifies the explanation process by eliminating several critical hyperparameters required by traditional methods like Local Interpretable Model-Agnostic Explanations (LIME). To develop the citrus disease classification model, we preprocess the leaf dataset through stratified data splitting, oversampling, and augmentation techniques, then fine-tuning a pre-trained Residual Network 50 layers (ResNet50) model. MOGAE’s effectiveness is demonstrated through comparative analyses with the Ensemble-based Genetic Algorithm Explainer (EGAE) and LIME, showing superior accuracy and interpretability using criteria such as numeric accuracy of explanation and Number of Function Evaluations (NFE). We assess accuracy both intuitively and numerically by measuring the Euclidean distance between expert-provided explanations and those generated by the explainer. The appendix also includes an extensive evaluation of MOGAE on the melanoma dataset, highlighting its versatility and robustness in other domains. The related implementation code for the fine-tuned ResNet50 and MOGAE is available at https://github.com/KhaosResearch/Plant-disease-explanation . • MOGAE eliminates several critical hyperparameters LIME requires, simplifying the explanation process. • MOGAE delivers more accurate and interpretable explanations than LIME, enhancing the reliability of the model’s decisions. • The integration of adaptive Bit Flip Mutation with densify and sparsify operators in NSGA-II significantly improves the algorithm’s exploration capabilities within MOGAE. • Comprehensive evaluations of MOGAE are conducted using both the citrus leaf diseases dataset and the melanoma dataset, demonstrating its versatility and effectiveness across different domains.

Feature selection has a prominent role in high-dimensional datasets to increase classification accuracy, decrease the learning algorithm computational time, and present the most informative features to decision-makers. This paper proposes a two-stage hybrid feature selection for high dimensional medical datasets: Maximum Pattern Recognition - Multi-objective Discrete Evolution Strategy (MPR-MDES). MPR is a rapid filter ranker that significantly outperforms existing frequency-based rankers in recognizing non-linear patterns, effectively eliminating a majority of non-informative features. Then, the wrapper Multi-objective Discrete Evolution Strategy(MDES) uses the remaining features and obtains sets of solutions which are automatically presented to decision-makers.The experiments conducted on large medical datasets demonstrate that MPR-MDES achieves considerable improvements compared to state-of-the-art methods, in terms of both classification accuracy and dimensionality reduction. In this sense, the proposal successfully performs when presenting informative feature sets to decision-makers. The implementation is available on https://github.com/KhaosResearch/MPR-MDES.

Data quality should be at the core of many Artificial Intelligence initiatives from the very first moment in which data is required for a successful analysis. Measurement and evaluation of the level of quality are crucial to determining whether data can be used for the tasks at hand. Conscientious of this importance, industry and academia have proposed several data quality measurements and assessment frameworks over the last two decades. Unfortunately, there is no common and shared vocabulary for data quality terms. Thus, it is difficult and time-consuming to integrate data quality analysis within a (Big) Data workflow for performing Artificial Intelligence tasks. One of the main reasons is that, except for a reduced number of proposals, the presented vocabularies are neither machine-readable nor processable, needing human processing to be incorporated. This paper proposes a unified data quality measurement and assessment information model. This model can be used in different environments and contexts to describe data quality measurement and evaluation concerns. The model has been developed as an ontology to make it interoperable and machine-readable. For better interoperability and applicability, this ontology, BIGOWL4DQ, has been developed as an extension of a previously developed ontology for describing knowledge management in Big Data analytics. This extended ontology provides a data quality measurement and assessment framework required when designing Artificial Intelligence workflows and integrated reasoning capacities. Thus, BIGOWL4DQ can be used to describe Big Data analysis and assess the data quality before the analysis. Our proposal has been validated with two use cases. First, the semantic proposal has been assessed using an academic use case. And second, a real-world case study within an Artificial Intelligence workflow has been conducted to endorse our work.

Feature selection in small-sample high-dimensional datasets enhances classification accuracy and reduces computational time for model training. This paper introduces the filter Classification Error Impurity (CEI) as a frequency-based ranker that improves upon existing methods by better identifying non-linear patterns. According to this, the top features identified by the ensemble of CEI, along with Mutual Information (MI) and Fisher Ratio (FR), form the feature space utilized by the Adaptive Genetic Algorithm with External Repository (AGAwER) to identify the optimal feature combination in a wrapper approach. AGAwER leverages an external repository, incorporating the best solutions to enrich the Genetic Algorithm’s (GA) population, thus promoting diversity and enhancing exploration. As a result, a hybrid method called CMF-AGAwER is proposed, which surpasses existing modern feature selection methods. The implementation and data are accessible on GitHub at https://github.com/KhaosResearch/CMF-AGAwER.

Ontologies have become a standard for knowledge representation across several domains. In Life Sciences, numerous ontologies have been introduced to represent human knowledge, often providing overlapping or conflicting perspectives. These ontologies are usually published as OWL or OBO, and are often registered in open repositories, e.g., BioPortal. However, the task of finding the concepts (classes and their properties) defined in the existing ontologies and the relationships between these concepts across different ontologies – for example, for developing a new ontology aligned with the existing ones – requires a great deal of manual effort in searching through the public repositories for candidate ontologies and their entities. In this work, we develop a new tool, KNIT, to automatically explore open repositories to help users fetch the previously designed concepts using keywords. User-specified keywords are then used to retrieve matching names of classes or properties. KNIT then creates a draft knowledge graph populated with the concepts and relationships retrieved from the existing ontologies. Furthermore, following the process of ontology learning, our tool refines this first draft of an ontology. We present three BioPortal-specific use cases for our tool. These use cases outline the development of new knowledge graphs and ontologies in the sub-domains of biology: genes and diseases, virome and drugs.

Abstract Reasoning is the process of inferring new knowledge and identifying inconsistencies within ontologies. Traditional techniques often prove inadequate when reasoning over large Knowledge Bases containing millions or billions of facts. This article introduces NORA, a persistent and scalable OWL reasoner built on top of Apache Spark, designed to address the challenges of reasoning over extensive and complex ontologies. NORA exploits the scalability of NoSQL databases to effectively apply inference rules to Big Data ontologies with large ABoxes. To facilitate scalable reasoning, OWL data, including class and property hierarchies and instances, are materialized in the Apache Cassandra database. Spark programs are then evaluated iteratively, uncovering new implicit knowledge from the dataset and leading to enhanced performance and more efficient reasoning over large‐scale ontologies. NORA has undergone a thorough evaluation with different benchmarking ontologies of varying sizes to assess the scalability of the developed solution.

Modern applications of Big Data are transcending from being scalable solutions of data processing and analysis, to now provide advanced functionalities with the ability to exploit and understand the underpinning knowledge. This change is promoting the development of tools in the intersection of data processing, data analysis, knowledge extraction and management. In this paper, we propose TITAN, a software platform for managing all the life cycle of science workflows from deployment to execution in the context of Big Data applications. This platform is characterised by a design and operation mode driven by semantics at different levels: data sources, problem domain and workflow components. The proposed platform is developed upon an ontological framework of meta-data consistently managing processes and models and taking advantage of domain knowledge. TITAN comprises a well-grounded stack of Big Data technologies including Apache Kafka for inter-component communication, Apache Avro for data serialisation and Apache Spark for data analytics. A series of use cases are conducted for validation, which comprises workflow composition and semantic meta-data management in academic and real-world fields of human activity recognition and land use monitoring from satellite images.

BACKGROUND: The analysis of gene expression levels is used in many clinical studies to know how patients evolve or to find new genetic biomarkers that could help in clinical decision making. However, the techniques and software available for these analyses are not intended for physicians, but for geneticists. However, enabling physicians to make initial discoveries on these data would benefit in the clinical assay development. RESULTS: Melanoma is a highly immunogenic tumor. Therefore, in recent years physicians have incorporated immune system altering drugs into their therapeutic arsenal against this disease, revolutionizing the treatment of patients with an advanced stage of the cancer. This has led us to explore and deepen our knowledge of the immunology surrounding melanoma, in order to optimize the approach. Within this project we have developed a database for collecting relevant clinical information for melanoma patients, including the storage of patient gene expression levels obtained from the NanoString platform (several samples are taken from each patient). The Immune Profiling Panel is used in this case. This database is being exploited through the analysis of the different expression profiles of the patients. This analysis is being done with Python, and a parallel version of the algorithms is available with Apache Spark to provide scalability as needed. CONCLUSIONS: VIGLA-M, the visual analysis tool for gene expression levels in melanoma patients is available at http://khaos.uma.es/melanoma/ . The platform with real clinical data can be accessed with a demo user account, physician, using password physician_test_7634 (if you encounter any problems, contact us at this email address: mailto: [email protected]). The initial results of the analysis of gene expression levels using these tools are providing first insights into the patients' evolution. These results are promising, but larger scale tests must be developed once new patients have been sequenced, to discover new genetic biomarkers.

MOTIVATION: Life Sciences have emerged as a key domain in the Linked Data community because of the diversity of data semantics and formats available through a great variety of databases and web technologies. Thus, it has been used as the perfect domain for applications in the web of data. Unfortunately, bioinformaticians are not exploiting the full potential of this already available technology, and experts in Life Sciences have real problems to discover, understand and devise how to take advantage of these interlinked (integrated) data. RESULTS: In this article, we present Bioqueries, a wiki-based portal that is aimed at community building around biological Linked Data. This tool has been designed to aid bioinformaticians in developing SPARQL queries to access biological databases exposed as Linked Data, and also to help biologists gain a deeper insight into the potential use of this technology. This public space offers several services and a collaborative infrastructure to stimulate the consumption of biological Linked Data and, therefore, contribute to implementing the benefits of the web of data in this domain. Bioqueries currently contains 215 query entries grouped by database and theme, 230 registered users and 44 end points that contain biological Resource Description Framework information. AVAILABILITY: The Bioqueries portal is freely accessible at http://bioqueries.uma.es. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract Background Saccharomyces cerevisiae is recognized as a model system representing a simple eukaryote whose genome can be easily manipulated. Information solicited by scientists on its biological entities (Proteins, Genes, RNAs...) is scattered within several data sources like SGD, Yeastract, CYGD-MIPS, BioGrid, PhosphoGrid, etc. Because of the heterogeneity of these sources, querying them separately and then manually combining the returned results is a complex and time-consuming task for biologists most of whom are not bioinformatics expert. It also reduces and limits the use that can be made on the available data. Results To provide transparent and simultaneous access to yeast sources, we have developed YeastMed: an XML and mediator-based system. In this paper, we present our approach in developing this system which takes advantage of SB-KOM to perform the query transformation needed and a set of Data Services to reach the integrated data sources. The system is composed of a set of modules that depend heavily on XML and Semantic Web technologies. User queries are expressed in terms of a domain ontology through a simple form-based web interface. Conclusions YeastMed is the first mediation-based system specific for integrating yeast data sources. It was conceived mainly to help biologists to find simultaneously relevant data from multiple data sources. It has a biologist-friendly interface easy to use. The system is available at http://www.khaos.uma.es/yeastmed/ .

High-throughput experiments have produced large amounts of heterogeneous data in the life sciences. These data are usually represented in different formats (and sometimes in technical documents) on the Web. Inevitably, life science researchers have to deal with all these data and different formats to perform their daily research, but it is simply not possible for a single human mind to analyse all these data. The integration of data in the life sciences is a key component in the analysis of biological processes. These data may contain errors, but the curation of the vast amount of data generated in the 'omic' era cannot be done by individual researchers. To address this problem, community-driven tools could be used to assist with data analysis. In this article, we focus on a tool with social networking capabilities built on top of the SBMM (Systems Biology Metabolic Modelling) Assistant to enable the collaborative improvement of metabolic pathway models (the application is freely available at http://sbmm.uma.es/SPA).

SUMMARY: We present Systems Biology Metabolic Modeling Assistant (SBMM Assistant), a tool built using an ontology-based mediator, and designed to facilitate metabolic modeling through the integration of data from repositories that contain valuable metabolic information. This software can be used for the visualization, design and management of metabolic networks; selection, integration and storage of metabolic information; and as an assistant for kinetic modeling. AVAILABILITY: SBMM Assistant for academic use is freely available at http://www.sbmm.uma.es.

BACKGROUND: The analysis of information in the biological domain is usually focused on the analysis of data from single on-line data sources. Unfortunately, studying a biological process requires having access to disperse, heterogeneous, autonomous data sources. In this context, an analysis of the information is not possible without the integration of such data. METHODS: KA-SB is a querying and analysis system for final users based on combining a data integration solution with a reasoner. Thus, the tool has been created with a process divided into two steps: 1) KOMF, the Khaos Ontology-based Mediator Framework, is used to retrieve information from heterogeneous and distributed databases; 2) the integrated information is crystallized in a (persistent and high performance) reasoner (DBOWL). This information could be further analyzed later (by means of querying and reasoning). RESULTS: In this paper we present a novel system that combines the use of a mediation system with the reasoning capabilities of a large scale reasoner to provide a way of finding new knowledge and of analyzing the integrated information from different databases, which is retrieved as a set of ontology instances. This tool uses a graphical query interface to build user queries easily, which shows a graphical representation of the ontology and allows users o build queries by clicking on the ontology concepts. CONCLUSION: These kinds of systems (based on KOMF) will provide users with very large amounts of information (interpreted as ontology instances once retrieved), which cannot be managed using traditional main memory-based reasoners. We propose a process for creating persistent and scalable knowledgebases from sets of OWL instances obtained by integrating heterogeneous data sources with KOMF. This process has been applied to develop a demo tool http://khaos.uma.es/KA-SB, which uses the BioPax Level 3 ontology as the integration schema, and integrates UNIPROT, KEGG, CHEBI, BRENDA and SABIORK databases.

BACKGROUND: Protein-protein interactions can be considered the basic skeleton for living organism self-organization and homeostasis. Impressive quantities of experimental data are being obtained and computational tools are essential to integrate and to organize this information. This paper presents Protopia, a biological tool that offers a way of searching for proteins and their interactions in different Protein Interaction Web Databases, as a part of a multidisciplinary initiative of our institution for the integration of biological data http://asp.uma.es. RESULTS: The tool accesses the different Databases (at present, the free version of Transfac, DIP, Hprd, Int-Act and iHop), and results are expressed with biological protein names or databases codes and can be depicted as a vector or a matrix. They can be represented and handled interactively as an organic graph. Comparison among databases is carried out using the Uniprot codes annotated for each protein. CONCLUSION: The tool locates and integrates the current information stored in the aforementioned databases, and redundancies among them are detected. Results are compatible with the most important network analysers, so that they can be compared and analysed by other world-wide known tools and platforms. The visualization possibilities help to attain this goal and they are especially interesting for handling multiple-step or complex networks.

This work is about an experiment in which we have compared the textual rendering of ontologies in order to get more accurate alignments between them. The experiments we have performed consist on three main steps: rendering in a textual way two ontologies, comparing the obtained text with several algorithms for text comparing and, using the obtained result as a factor to improve the alignments between them. As result, we got some evidences that this technique gives us a good measure of the similarity of ontologies and, therefore can allow us to improve the effectiveness of the alignment process.

BACKGROUND: Amines are biogenic amino acid derivatives, which play pleiotropic and very important yet complex roles in animal physiology. For many other relevant biomolecules, biochemical and molecular data are being accumulated, which need to be integrated in order to be effective in the advance of biological knowledge in the field. For this purpose, a multidisciplinary group has started an ontology-based system named the Amine System Project (ASP) for which amine-related information is the validation bench. RESULTS: In this paper, we describe the Ontology-Based Mediator developed in the Amine System Project (http://asp.uma.es) using the infrastructure of Semantic Directories, and how this system has been used to solve a case related to amine metabolism-related protein structures. CONCLUSIONS: This infrastructure is used to publish and manage not only ontologies and their relationships, but also metadata relating to the resources committed with the ontologies. The system developed is available at http://asp.uma.es/WebMediator.

MOTIVATION: In addition to existing bioinformatics software, a lot of new tools are being developed world wide to supply services for an ever growing, widely dispersed and heterogeneous collection of biological data. The integration of these resources under a common platform is a challenging task. To this end, several groups are developing integration technologies, in which services are usually registered in some sort of catalogue to allow novel discovering and accessing mechanisms to be implemented. However, each service demands specific interfaces to accommodate their parameters and it is a complicated task linking the different service inputs and outputs to solve a biological problem. RESULTS: In this work we address the design and implementation of a versatile web client to access BioMOBY compatible services (a system by which a client can interact with multiple sources of biological data regardless of the underlying format or schema) using the service description stored in the BioMOBY catalogue. The automatic interface generator significantly reduces developing time and produces uniform service access mechanisms. The design and proof of concept (for such a client) including the generic interface generator have been developed and implemented in the National Institute for Bioinformatics in Spain. AVAILABILITY: The INB (National Institute for Bioinformatics, Spain) platform is available at www.inab.org/MOWServ

Abstract In this work we present an architecture for XML‐based mediator systems and a framework for helping systems developers in the construction of mediator‐services for the integration of heterogeneous data sources. A unique feature of our architecture is its capability to manage (proprietary) user's software tools and algorithms, modelled as Extended Value Added Services (EVASs), and integrated in the data flow. The mediator offers a view of the system as a single data source where EVASs are readily available for enhancing query processing. A Web‐based graphic interface has been developed to allow dynamic and flexible EVASs inter‐connection, thus creating complex distributed bioinformatics machines. The feasibility and usefulness of our ideas has been validated by the development of a mediator system (Bio‐Broker) and by a diverse set of applications aimed at combining gene expression data with genomic, sequence‐based and structural information, so as to provide a general, transparent and powerful solution that integrates data analysis tools and algorithms. Copyright © 2006 John Wiley & Sons, Ltd.