Database Issue Research Articles

Enhancing cardiovascular disease prediction: A hybrid machine learning approach integrating oversampling and adaptive boosting techniques

<abstract> <p>This study presents a novel approach to enhance cardiovascular disease prediction using a hybrid machine learning (ML) model. Leveraging on Synthetic Minority oversampling techniques (SMOTE) and adaptive boosting (AdaBoost), we integrate these methods with prominent classifiers, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Extra Tree (ET). Focused on heart rate data as stress level indicators, our objective is to jointly predict cardiovascular disease, thereby addressing the global health challenge of early detection and accurate risk assessments. In response to class imbalance issues in cardiology databases, our hybrid model, which combines SMOTE and AdaBoost, demonstrates promising results. The inclusion of diverse classifiers, such as RF, XGBoost, and ET, enables the model to capture both linear and nonlinear relationships within the heart rate data, significantly enhancing the prediction accuracy. This powerful predictive tool empowers healthcare providers to identify individuals at a high risk for heart disease, thus facilitating timely interventions. This article underscores the pivotal role of ML and hybrid methodologies in advancing health research, particularly in cardiovascular disease prediction. By addressing the class imbalance and incorporating robust algorithms, our research contributes to the ongoing efforts to improve predictive modeling in healthcare. The findings presented here hold significance for medical practitioners and researchers striving for the early detection and prevention of cardiovascular diseases.</p> </abstract>

Clearance tests as a diagnosis method of hepatobiliary system pathologies in animals

In present-day conditions of industrial agriculture, the animal's body works at the limit of its capabilities, which leads to degenerative diseases of various organs and systems. The development of ergonomic ways of modern diagnosis of these pathologies at the early stages contributes to the maintenance of quantitative and qualitative indices of productivity of animals and to the extension of the time of their economic use. The liver with a great number of functions performed is subjected to the highest load. The aim of the article is to review the available clearance tests in order to diagnose the pathology of the hepatobiliary system of animals at the early stage, considering advantages and disadvantages of the tests. As the result of the search of themed issues in various bibliographic databases there have been selected 45 mostly cited scientific articles. The article reviews such clearance tests as indocyanine green clearance test, aminopyrine breath test, sorbitol elimination test, galactose elimination test, phenylalanine breath test, and hepatobiliary scintigraphy method. Functional tests allow not only diagnosing and differentiating hepatopathologies, but also visualizing their course and liver recovery. Unlike laboratory tests, clearance tests make it possible to evaluate the work of the liver in dynamics. The disadvantages of clearance tests are lack of information for their wide use and frequency of particular differences in elimination of specific substances. To reduce the proportion of existing shortcomings, it is possible to combine clearance tests with other laboratory methods for diagnosing hepatopathy in animals.

Small RNA structural biochemistry in a post-sequencing era.

High-throughput sequencing has had an enormous impact on small RNA research during the past decade. However, sequencing only offers a one-dimensional view of the transcriptome and is often highly biased. Additionally, the 'sequence, map and annotate' approach, used widely in small RNA research, can lead to flawed interpretations of the data, lacking biological plausibility, due in part to database issues. Even in the absence of technical biases, the loss of three-dimensional information is a major limitation to understanding RNA stability, turnover and function. For example, noncoding RNA-derived fragments seem to exist mainly as dimers, tetramers or as nicked forms of their parental RNAs, contrary to widespread assumptions. In this perspective, we will discuss main sources of bias during small RNA-sequencing, present several useful bias-reducing strategies and provide guidance on the interpretation of small RNA-sequencing results, with emphasis on RNA fragmentomics. As sequencing offers a one-dimensional projection of a four-dimensional reality, prior structure-level knowledge is often needed to make sense of the data. Consequently, while less-biased sequencing methods are welcomed, integration of orthologous experimental techniques is also strongly recommended.

The 2024 Nucleic Acids Research database issue and the online molecular biology database collection.

The 2024 Nucleic Acids Research database issue contains 180 papers from across biology and neighbouring disciplines. There are 90 papers reporting on new databases and 83 updates from resources previously published in the Issue. Updates from databases most recently published elsewhere account for a further seven. Nucleic acid databases include the new NAKB for structural information and updates from Genbank, ENA, GEO, Tarbase and JASPAR. The Issue's Breakthrough Article concerns NMPFamsDB for novel prokaryotic protein families and the AlphaFold Protein Structure Database has an important update. Metabolism is covered by updates from Reactome, Wikipathways and Metabolights. Microbes are covered by RefSeq, UNITE, SPIRE and P10K; viruses by ViralZone and PhageScope. Medically-oriented databases include the familiar COSMIC, Drugbank and TTD. Genomics-related resources include Ensembl, UCSC Genome Browser and Monarch. New arrivals cover plant imaging (OPIA and PlantPAD) and crop plants (SoyMD, TCOD and CropGS-Hub). The entire Database Issue is freely available online on the Nucleic Acids Research website (https://academic.oup.com/nar). Over the last year the NAR online Molecular Biology Database Collection has been updated, reviewing 1060 entries, adding 97 new resources and eliminating 388 discontinued URLs bringing the current total to 1959 databases. It is available at http://www.oxfordjournals.org/nar/database/c/.

The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods.

ChEMBL (https://www.ebi.ac.uk/chembl/) is a manually curated, high-quality, large-scale, open, FAIRand Global Core Biodata Resource of bioactive molecules with drug-like properties, previously described in the 2012, 2014, 2017 and 2019 Nucleic Acids Research Database Issues. Since its introduction in 2009, ChEMBL's content has changed dramatically in size and diversity of data types. Through incorporation of multiple new datasets from depositors since the 2019 update, ChEMBL now contains slightly more bioactivity data from deposited data vs data extracted from literature. In collaboration with the EUbOPEN consortium, chemical probe data is now regularly deposited into ChEMBL. Release 27 made curated data available for compounds screened for potential anti-SARS-CoV-2 activity from several large-scale drug repurposing screens. In addition, new patent bioactivity data have been added to the latest ChEMBL releases, and various new features have been incorporated, including a Natural Product likeness score, updated flags for Natural Products, a new flag for Chemical Probes, and the initial annotation of the action type for ∼270000 bioactivity measurements.

A web-based platform for the annotation and analysis of NAR-published databases.

Biological databases are essential resources for life science research, but finding and selecting the most relevant and up-to-date databases can be challenging due to the large number and diversity of available databases. The Nucleic Acids Research (NAR) journal publishes annual database issues that provide a comprehensive list of databases in the molecular biology domain. However, the information provided by NAR is limited and sometimes does not reflect the current status and quality of the databases. In this article, we present a web-based platform for the annotation and analysis of NAR-published databases. The platform allows users to manually curate and enrich the NAR entries with additional information such as availability, downloadability, source code links, cross-references, and duplicates. Statistics and visualizations on various aspects of the database landscape, such as recency, status, category, and curation history are also provided. Currently, it contains a total of 2,246 database entries of which 2,025 are unique with the majority updated within the last five years. Around 75% of all databases are still available and more than half provide a download option. Cross references to Database Commons are available for 1,889 entries. The platform is freely available online at https://nardbstatus.kalis-amts.de and aims to help researchers in database selection and decision-making. It also provides insights into the current state and challenges of a subset of all databases in the life sciences.

An annotated nomenclatural checklist of endemic vascular plants distributed in the Ukrainian Carpathians.

The current paper presents a nomenclatural checklist for vascular plants validated being (sub)endemic to and present in the flora of the Ukrainian Carpathians. This checklist is a part of the work targeted on an inventory of endemic plants distributed in the Ukrainian Carpathians. It is mainly based on the analysis of primary sources (i.e. original protologues and monographic works), but also uses the data provided in the recent online taxonomic aggregators, such as the Global Biodiversity Information Facility (GBIF), Catalogue of Life (CoL), Plants of the World Online (POWO), Euro+Med PlantBase, World Flora Online (WFO) and others. Over 7,000 specimens deposited in the leading Ukrainian herbaria were also revised and used as a supporting data source during the work on the checklist. The checklist provides a revised nomenclature, including corrections on publication dates, rediscovered taxonomic protologues, corrected authorships and revised taxonomic status for (sub)endemic (sub)species of vascular plants occurring in the Ukrainian Carpathians. It contains 1,101 names, from which 78 species and subspecies have been accepted as valid and 1023 species and infraspecific taxa are provided as synonyms. It is completed with critical notes on the nomenclature of problematic taxa and brief annotations regarding their distribution in the Ukrainian Carpathians, indicating the endemicity range and sozological status for all analysed (sub)species.The current checklist is linked with the GBIF taxonomic backbone, provides notes on detected issues and primarily focuses on its update and correction of the nomenclatural issues and taxonomic inconsistencies, but also aims at discussing issues in other popular taxonomic databases.Sabulinapauciflora is proposed as a new combination to comply with a recent revision of the genus Sabulina.

An efficient approach for faster matching of approximate patterns in graphs

Graphs have proven to be an efficient problem representation scheme in many real-world applications and can serve to address mining of patterns in large volumes of data. This work addresses the data management issue in graph databases for shortest path queries, verification of reachability, and pattern matching queries. The key issue is to match all possible patterns in a large data graph that matches a user-provided pattern, known as the query graph. The large size of the graph makes the problem complex when searching for all patterns that are similar to the user’s query. For a given query, a match occurs when a graph with n vertices has the same label as the corresponding vertices in the query graph. This work addresses such pattern matching query problems on large graphs and presents an efficient algorithm to mine all patterns that satisfies the given query. The current work presents a novel Fast Graph Pattern (FGP) mining algorithm that performs a label-specific walk on a graph and stores all vertices that are visited during the walk and hashes them on a labeled root. Experiments are performed using five benchmark datasets, and the proposed approach is compared with three state-of-the-art methods. The obtained results suggest better performance of the current proposal by achieving five times quicker results.

An Intuitionistic Fuzzy-Rough Set-Based Classification for Anomaly Detection

The challenging issues of computer networks and databases are not only the intrusion detection but also the reduction of false positives and increase of detection rate. In any intrusion detection system, anomaly detection mainly focuses on modeling the normal behavior of the users and detecting the deviations from normal behavior, which are assumed to be potential intrusions or threats. Several techniques have already been successfully tried for this purpose. However, the normal and suspicious behaviors are hard to predict as there is no precise boundary differentiating one from another. Here, rough set theory and fuzzy set theory come into the picture. In this article, a hybrid approach consisting of rough set theory and intuitionistic fuzzy set theory is proposed for the detection of anomaly. The proposed approach is a classification approach which takes the advantages of both rough set and intuitionistic fuzzy set to deal with inherent uncertainty, vagueness, and indiscernibility in the dataset. The algorithm classifies the data instances in such a way that they can be expressed using natural language. A data instance can possibly or certainly belong to a class with degrees of membership and non-membership. The empirical study with a real-world and a synthetic dataset demonstrates that the proposed algorithm has normal true positive rates of 91.989% and 96.99% and attack true positive rates of 91.289% and 96.29%, respectively.

Review of Issues on Data Security Cybercrimes and Image: The Nigerian Case

The paper seeks to address the lapses in policy formulation and implementations on the issue of database in Nigeria and by extension the rest of developing countries that are confronting with various activities of cyber criminals. Most of these government pay leap service to boosting the image of their countries whereas it is in their sole responsibility to monitor communications and detect abuse on networks due to influence of globalization. Up till now, no dependable data base of citizenry in Nigeria and that makes it difficult to check people activities online which resulting to all security issues that presently deforming the country images. Images are measured by performance of invisible indicators. The study seeks on how Nigeria can improve her image by identifying the impact of information security and effective governance with the immediate application of automation system in the country since country’s reputation plays a major role in attracting investment and boosting the economy, as reputation negatively affected by the increasing number of cybercrime incidents.Data security and cybercrime in Nigeria are significant and need to be addressed as a matter of urgency by taking proactive steps to improve data security, enhance cybercrime enforcement, and protect the country's image, Nigeria can build a more secure and stable digital environment for its citizens. DOI : https://doi.org/10.54663/2182-9306.2023.sn12.25-41

The 2023 Nucleic Acids Research Database Issue and the online molecular biology database collection.

The 2023 Nucleic Acids Research Database Issue contains 178 papers ranging across biology and related fields. There are 90 papers reporting on new databases and 82 updates from resources previously published in the Issue. Six more papers are updates from databases most recently published elsewhere. Major nucleic acid databases reporting updates include Genbank, ENA, ChIPBase, JASPAR, mirDIP and the Issue's first Breakthrough Article, NACDDB for Circular Dichroism data. Updates from BMRB and RCSB cover experimental protein structural data while AlphaFold 2 computational structure predictions feature widely. STRING and REBASE are stand-out updates in the signalling and enzymes section. Immunology-related databases include CEDAR, the second Breakthrough Article, for cancer epitopes and receptors alongside returning IPD-IMGT/HLA and the new PGG.MHC. Genomics-related resources include Ensembl, GWAS Central and UCSC Genome Browser. Major returning databases for drugs and their targets include Open Targets, DrugCentral, CTD and Pubchem. The EMPIAR image archive appears in the Issue for the first time. The entire database Issue is freely available online on the Nucleic Acids Research website (https://academic.oup.com/nar). The NAR online Molecular Biology Database Collection has been updated, revisiting 463 entries, adding 92 new resources and eliminating 96 discontinued URLs so bringing the current total to 1764 databases. It is available at http://www.oxfordjournals.org/nar/database/c/.

RCSB Protein Data Bank (RCSB.org): delivery of experimentally-determined PDB structures alongside one million computed structure models of proteins from artificial intelligence/machine learning.

The Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB), founding member of the Worldwide Protein Data Bank (wwPDB), is the US data center for the open-access PDB archive. As wwPDB-designated Archive Keeper, RCSB PDB is also responsible for PDB data security. Annually, RCSB PDB serves>10 000 depositors of three-dimensional (3D) biostructures working on all permanently inhabited continents. RCSB PDB delivers data from its research-focused RCSB.org web portal to many millions of PDB data consumers based in virtually every United Nations-recognized country, territory, etc. This Database Issue contribution describes upgrades to the research-focused RCSB.org web portal that created a one-stop-shop for open access to ∼200 000 experimentally-determined PDB structures of biological macromolecules alongside>1 000 000 incorporated Computed Structure Models (CSMs) predicted using artificial intelligence/machine learning methods. RCSB.org is a 'living data resource.' Every PDB structure and CSM is integrated weekly with related functional annotations from external biodata resources, providing up-to-date information for the entire corpus of 3D biostructure data freely available from RCSB.org with no usage limitations. Within RCSB.org, PDB structures and the CSMs are clearly identified as to their provenance and reliability. Both are fully searchable, and can be analyzed and visualized using the full complement of RCSB.org web portal capabilities.

Searching for “rare diamonds”? Industrial districts and innovation in Spain and Italy

PurposeThis paper aims to test the existence of the so-called industrial district effect on innovation (iMID effect) in Spain and Italy and to compare the intensity of this effect between both countries. There is previous evidence of this effect for Spain, although, to the best of the authors’ knowledge, it has never been measured for Italy.Design/methodology/approachInnovation intensity by local production system is measured using patents per million employees and analysed using the mean, the median, 3D maps and statistical tests.FindingsIndustrial districts generate between a third and a quarter of all technological innovations in Spain and Italy. The evidence about the district effect in innovation in Spain is consistent with previous studies. The novelty is that there is also evidence of this effect for Italy and its intensity is higher than for Spain. Almost one-half of the industrial districts fit in the most innovative quartile of local production systems, and they are located in the most innovative part of each country.Research limitations/implicationsLimitations of this study include minor database issues. Implications include new focus on the general relevance of industrial districts as highly innovative local production systems and top innovators.Practical implicationsReorientation of territorial and innovation policies.Social implicationsEffect on development and well-being through technical progress.Originality/valueThis article provides, for the first time, to the best of the authors’ knowledge, a measurement of the industrial district effect on innovation in Italy. The paper compares the results between Spain and Italy and allows for generalization of previous evidence, concluding that highly innovative industrial districts are not “rare diamonds”, revealing as an alternative and an extraordinarily powerful place-based innovation model.

A Dynamic Decision Support System for Selection of Cloud Storage Provider

In recent years, the cloud computing model has gained increasing attention and popularity in the field of information technology. For this reason, people are migrating their applications to public, private, or hybrid cloud environments. Many cloud vendors offer similar features with varying costs, so an appropriate choice will be the key to guaranteeing comparatively low operational costs for an organization. The motivation for this work is the necessity to select an appropriate cloud storage provider offering for the migration of applications with less cost and high performance. However, the selection of a suitable cloud storage provider is a complex problem that entails various technical and organizational aspects. In this research, a dynamic Decision Support System (DSS) for selection of an appropriate cloud storage provider is proposed. A web-based application is implemented using PHP and MySQL to facilitate decision makers. The proposed mechanism has been optimized in a way that enables the system to address static database issues for which a user might not acquire the best solution. It focuses on comparing and ranking cloud storage providers by using two modules: scraping and parsing. The evaluation of the proposed system is carried out with appropriate test cases and compared with existing tools and frameworks.

Rhea, the reaction knowledgebase in 2022.

Rhea (https://www.rhea-db.org) is an expert-curated knowledgebase of biochemical reactions based on the chemical ontology ChEBI (Chemical Entities of Biological Interest) (https://www.ebi.ac.uk/chebi). In this paper, we describe a number of key developments in Rhea since our last report in the database issue of Nucleic Acids Research in 2019. These include improved reaction coverage in Rhea, the adoption of Rhea as the reference vocabulary for enzyme annotation in the UniProt knowledgebase UniProtKB (https://www.uniprot.org), the development of a new Rhea website, and the designation of Rhea as an ELIXIR Core Data Resource. We hope that these and other developments will enhance the utility of Rhea as a reference resource to study and engineer enzymes and the metabolic systems in which they function.

The Human Disease Ontology 2022 update.

The Human Disease Ontology (DO) (www.disease-ontology.org) database, has significantly expanded the disease content and enhanced our userbase and website since the DO’s 2018 Nucleic Acids Research DATABASE issue paper. Conservatively, based on available resource statistics, terms from the DO have been annotated to over 1.5 million biomedical data elements and citations, a 10× increase in the past 5 years. The DO, funded as a NHGRI Genomic Resource, plays a key role in disease knowledge organization, representation, and standardization, serving as a reference framework for multiscale biomedical data integration and analysis across thousands of clinical, biomedical and computational research projects and genomic resources around the world. This update reports on the addition of 1,793 new disease terms, a 14% increase of textual definitions and the integration of 22 137 new SubClassOf axioms defining disease to disease connections representing the DO’s complex disease classification. The DO’s updated website provides multifaceted etiology searching, enhanced documentation and educational resources.

An Unsupervised and Robust Line and Word Segmentation Method for Handwritten and Degraded Printed Document

Segmentation of text lines and words in an unconstrained handwritten or a machine-printed degraded document is a challenging document analysis problem due to the heterogeneity in the document structure. Often there is un-even skew between the lines and also broken words in a document. In this article, the contribution lies in segmentation of a document page image into lines and words. We have proposed an unsupervised, robust, and simple statistical method to segment a document image that is either handwritten or machine-printed (degraded or otherwise). In our proposed method, the segmentation is treated as a two-class classification problem. The classification is done by considering the distribution of gap size (between lines and between words) in a binary page image. Our method is very simple and easy to implement. Other than the binarization of the input image, no pre-processing is necessary. There is no need of high computational resources. The proposed method is unsupervised in the sense that no annotated document page images are necessary. Thus, the issue of a training database does not arise. In fact, given a document page image, the parameters that are needed for segmentation of text lines and words are learned in an unsupervised manner. We have applied our proposed method on several popular publicly available handwritten and machine-printed datasets (ISIDDI, IAM-Hist, IAM, PBOK) of different Indian and other languages containing different fonts. Several experimental results are presented to show the effectiveness and robustness of our method. We have experimented on ICDAR-2013 handwriting segmentation contest dataset and our method outperforms the winning method. In addition to this, we have suggested a quantitative measure to compute the level of degradation of a document page image.

Dealing with missing information on covariates for excess mortality hazard regression models - Making the imputation model compatible with the substantive model.

Missing data is a common issue in epidemiological databases. Among the different ways of dealing with missing data, multiple imputation has become more available in common statistical software packages. However, the incompatibility between the imputation and substantive model, which can arise when the associations between variables in the substantive model are not taken into account in the imputation models or when the substantive model is itself nonlinear, can lead to invalid inference. Aiming at analysing population-based cancer survival data, we extended the multiple imputation substantive model compatible-fully conditional specification (SMC-FCS) approach, proposed by Bartlett etal. in 2015 to accommodate excess hazard regression models. The proposed approach was compared with the standard fully conditional specification multiple imputation procedure and with the complete-case analysis using a simulation study. The SMC-FCS approach produced unbiased estimates in both scenarios tested, while the fully conditional specification produced biased estimates and poor empirical coverages probabilities. The SMC-FCS algorithm was then used for handling missing data in the evaluation of socioeconomic inequalities in survival from colorectal cancer patients diagnosed in the North Region of Portugal. The analysis using SMC-FCS showed a clearer trend in higher excess hazards for patients coming from more deprived areas. The proposed algorithm was implemented in R software and is presented as Supplementary Material.

Geospatial database use for land consolidation objectives in Ukraine

The issue of geospatial database provisioning for land consolidation objectives in Ukraine has been scrutinized in the article. The thematic justification is predefined by the increasing need for land consolidation and the need for the provision of the land consolidation process with the updated, full and valid data. The goal of the research is the substantiation of a set of the subject geospatial data as a constituent of the national infrastructure needed for managerial decisions on agricultural land consolidation and the respective land management plan development. Basic geospatial data sets predefined by the legislation in effect have been examined from the prospect of land consolidation. Thematic geospatial data sets have been suggested. The use of the suggested geospatial data sets in the course of the key stages of land consolidation has been analysed. The use of geospatial data at the implementation of a land consolidation project using the land reallotment optimization model has been examined. The research results can be used at the land consolidation decision making support, land resources management, development of specialized geoportals, in the following scientific researches on the development of the national geospatial data infrastructure, land consolidation in Ukraine.

Application of machine learning techniques for selecting the most suitable enhanced oil recovery method; challenges and opportunities

A reliable method for selecting the most suitable Enhanced Oil Recovery (EOR) method is of a high necessity in reservoir engineering. Machine Learning (ML) techniques have been widely adopted as an effective and fast approach in primary stage of EOR screening. This paper presents a step-by-step procedure of applying ML in EOR screening with focusing on two main goals. Firstly, the problem of EOR screening is investigated from ML point of view. A large database consisting of more than 1000 experiences of worldwide EOR projects has been gathered from various sources. On the basis of this database, several ML models have been developed for predicting the suitable category of EOR methods for a candidate reservoir. These models include: Shallow and Deep Artificial Neural Networks (ANN), Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF) and Dimension Reduction using Principal Component Analysis (PCA). Almost all models performed well in predicting non-observed data with an average accuracy ranging from 80 to 90%. However, RF and the deep ANN models delivered the best performance with an average accuracy of 90%. The results demonstrated that RF model performed much better in comparison with the DT model and improved the classification accuracy from 85 to 91%. In case of ANNs, it was observed that the deeper ANN developed here, improved the classification accuracy from 83 to 90% in comparison with the shallow ANN with one hidden layer. The weakest performance was delivered by NB classifier with an average accuracy of 49%. As the second purpose of this research, reliability of screening results from applying ML techniques is discussed in details. Because, this approach suffers from some serious limitations and challenges, which could unfavorably affect the screening results and never had been considered in previous works. In this work, potential challenges and limitations associated with this well-known approach are introduced from database issues to modeling problems. Accordingly, an important conclusion is that application of ML, although providing a very good insight into primary EOR screening, should not be relied upon as the only method for predictions. It is recommended that the obtained results from this approach should be cross-checked with other EOR screening approaches or with methods based on expert's knowledge.