Classification performance assessment for imbalanced multiclass data.

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or F ß -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

Advance Monitoring of COVID-19 Incidence Based on Taxi Mobility: The Infection Ratio Measure.

The COVID-19 pandemic has had a profound impact on various aspects of our lives, affecting personal, occupational, economic, and social spheres. Much has been learned since the early 2020s, which will be very useful when the next pandemic emerges. In general, mobility and virus spread are strongly related. However, most studies analyze the impact of COVID-19 on mobility, but not much research has focused on analyzing the impact of mobility on virus transmission, especially from the point of view of monitoring virus incidence, which is extremely important for making sound decisions to control any epidemiological threat to public health. As a result of a thorough analysis of COVID-19 and mobility data, this work introduces a novel measure, the Infection Ratio (IR), which is not sensitive to underestimation of positive cases and is very effective in monitoring the pandemic's upward or downward evolution when it appears to be more stable, thus anticipating possible risk situations. For a bounded spatial context, we can infer that there is a significant threshold in the restriction of mobility that determines a change of trend in the number of infections that, if maintained for a minimum period, would notably increase the chances of keeping the spread of disease under control. Results show that IR is a reliable indicator of the intensity of infection, and an effective measure for early monitoring and decision making in smart cities.

Pairwise gene GO-based measures for biclustering of high-dimensional expression data.

BACKGROUND: Biclustering algorithms search for groups of genes that share the same behavior under a subset of samples in gene expression data. Nowadays, the biological knowledge available in public repositories can be used to drive these algorithms to find biclusters composed of groups of genes functionally coherent. On the other hand, a distance among genes can be defined according to their information stored in Gene Ontology (GO). Gene pairwise GO semantic similarity measures report a value for each pair of genes which establishes their functional similarity. A scatter search-based algorithm that optimizes a merit function that integrates GO information is studied in this paper. This merit function uses a term that addresses the information through a GO measure. RESULTS: The effect of two possible different gene pairwise GO measures on the performance of the algorithm is analyzed. Firstly, three well known yeast datasets with approximately one thousand of genes are studied. Secondly, a group of human datasets related to clinical data of cancer is also explored by the algorithm. Most of these data are high-dimensional datasets composed of a huge number of genes. The resultant biclusters reveal groups of genes linked by a same functionality when the search procedure is driven by one of the proposed GO measures. Furthermore, a qualitative biological study of a group of biclusters show their relevance from a cancer disease perspective. CONCLUSIONS: It can be concluded that the integration of biological information improves the performance of the biclustering process. The two different GO measures studied show an improvement in the results obtained for the yeast dataset. However, if datasets are composed of a huge number of genes, only one of them really improves the algorithm performance. This second case constitutes a clear option to explore interesting datasets from a clinical point of view.

Soft Computing Methods for Disulfide Connectivity Prediction.

The problem of protein structure prediction (PSP) is one of the main challenges in structural bioinformatics. To tackle this problem, PSP can be divided into several subproblems. One of these subproblems is the prediction of disulfide bonds. The disulfide connectivity prediction problem consists in identifying which nonadjacent cysteines would be cross-linked from all possible candidates. Determining the disulfide bond connectivity between the cysteines of a protein is desirable as a previous step of the 3D PSP, as the protein conformational search space is highly reduced. The most representative soft computing approaches for the disulfide bonds connectivity prediction problem of the last decade are summarized in this paper. Certain aspects, such as the different methodologies based on soft computing approaches (artificial neural network or support vector machine) or features of the algorithms, are used for the classification of these methods.

Building Transcriptional Association Networks in Cytoscape with RegNetC.

The Regression Network plugin for Cytoscape (RegNetC) implements the RegNet algorithm for the inference of transcriptional association network from gene expression profiles. This algorithm is a model tree-based method to detect the relationship between each gene and the remaining genes simultaneously instead of analyzing individually each pair of genes as correlation-based methods do. Model trees are a very useful technique to estimate the gene expression value by regression models and favours localized similarities over more global similarity, which is one of the major drawbacks of correlation-based methods. Here, we present an integrated software suite, named RegNetC, as a Cytoscape plugin that can operate on its own as well. RegNetC facilitates, according to user-defined parameters, the resulted transcriptional gene association network in .sif format for visualization, analysis and interoperates with other Cytoscape plugins, which can be exported for publication figures. In addition to the network, the RegNetC plugin also provides the quantitative relationships between genes expression values of those genes involved in the inferred network, i.e., those defined by the regression models.

Biclustering on expression data: A review.

Biclustering has become a popular technique for the study of gene expression data, especially for discovering functionally related gene sets under different subsets of experimental conditions. Most of biclustering approaches use a measure or cost function that determines the quality of biclusters. In such cases, the development of both a suitable heuristics and a good measure for guiding the search are essential for discovering interesting biclusters in an expression matrix. Nevertheless, not all existing biclustering approaches base their search on evaluation measures for biclusters. There exists a diverse set of biclustering tools that follow different strategies and algorithmic concepts which guide the search towards meaningful results. In this paper we present a extensive survey of biclustering approaches, classifying them into two categories according to whether or not use evaluation metrics within the search method: biclustering algorithms based on evaluation measures and non metric-based biclustering algorithms. In both cases, they have been classified according to the type of meta-heuristics which they are based on.

Integrating biological knowledge based on functional annotations for biclustering of gene expression data.

Gene expression data analysis is based on the assumption that co-expressed genes imply co-regulated genes. This assumption is being reformulated because the co-expression of a group of genes may be the result of an independent activation with respect to the same experimental condition and not due to the same regulatory regime. For this reason, traditional techniques are recently being improved with the use of prior biological knowledge from open-access repositories together with gene expression data. Biclustering is an unsupervised machine learning technique that searches patterns in gene expression data matrices. A scatter search-based biclustering algorithm that integrates biological information is proposed in this paper. In addition to the gene expression data matrix, the input of the algorithm is only a direct annotation file that relates each gene to a set of terms from a biological repository where genes are annotated. Two different biological measures, FracGO and SimNTO, are proposed to integrate this information by means of its addition to-be-optimized fitness function in the scatter search scheme. The measure FracGO is based on the biological enrichment and SimNTO is based on the overlapping among GO annotations of pairs of genes. Experimental results evaluate the proposed algorithm for two datasets and show the algorithm performs better when biological knowledge is integrated. Moreover, the analysis and comparison between the two different biological measures is presented and it is concluded that the differences depend on both the data source and how the annotation file has been built in the case GO is used. It is also shown that the proposed algorithm obtains a greater number of enriched biclusters than other classical biclustering algorithms typically used as benchmark and an analysis of the overlapping among biclusters reveals that the biclusters obtained present a low overlapping. The proposed methodology is a general-purpose algorithm which allows the integration of biological information from several sources and can be extended to other biclustering algorithms based on the optimization of a merit function.

Configurable pattern-based evolutionary biclustering of gene expression data.

BACKGROUND: Biclustering algorithms for microarray data aim at discovering functionally related gene sets under different subsets of experimental conditions. Due to the problem complexity and the characteristics of microarray datasets, heuristic searches are usually used instead of exhaustive algorithms. Also, the comparison among different techniques is still a challenge. The obtained results vary in relevant features such as the number of genes or conditions, which makes it difficult to carry out a fair comparison. Moreover, existing approaches do not allow the user to specify any preferences on these properties. RESULTS: Here, we present the first biclustering algorithm in which it is possible to particularize several biclusters features in terms of different objectives. This can be done by tuning the specified features in the algorithm or also by incorporating new objectives into the search. Furthermore, our approach bases the bicluster evaluation in the use of expression patterns, being able to recognize both shifting and scaling patterns either simultaneously or not. Evolutionary computation has been chosen as the search strategy, naming thus our proposal Evo-Bexpa (Evolutionary Biclustering based in Expression Patterns). CONCLUSIONS: We have conducted experiments on both synthetic and real datasets demonstrating Evo-Bexpa abilities to obtain meaningful biclusters. Synthetic experiments have been designed in order to compare Evo-Bexpa performance with other approaches when looking for perfect patterns. Experiments with four different real datasets also confirm the proper performing of our algorithm, whose results have been biologically validated through Gene Ontology.

Contact map prediction using a large-scale ensemble of rule sets and the fusion of multiple predicted structural features.

MOTIVATION: The prediction of a protein's contact map has become in recent years, a crucial stepping stone for the prediction of the complete 3D structure of a protein. In this article, we describe a methodology for this problem that was shown to be successful in CASP8 and CASP9. The methodology is based on (i) the fusion of the prediction of a variety of structural aspects of protein residues, (ii) an ensemble strategy used to facilitate the training process and (iii) a rule-based machine learning system from which we can extract human-readable explanations of the predictor and derive useful information about the contact map representation. RESULTS: The main part of the evaluation is the comparison against the sequence-based contact prediction methods from CASP9, where our method presented the best rank in five out of the six evaluated metrics. We also assess the impact of the size of the ensemble used in our predictor to show the trade-off between performance and training time of our method. Finally, we also study the rule sets generated by our machine learning system. From this analysis, we are able to estimate the contribution of the attributes in our representation and how these interact to derive contact predictions. AVAILABILITY: http://icos.cs.nott.ac.uk/servers/psp.html. CONTACT: natalio.krasnogor@nottingham.ac.uk SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

An effective measure for assessing the quality of biclusters.

Biclustering is becoming a popular technique for the study of gene expression data. This is mainly due to the capability of biclustering to address the data using various dimensions simultaneously, as opposed to clustering, which can use only one dimension at the time. Different heuristics have been proposed in order to discover interesting biclusters in data. Such heuristics have one common characteristic: they are guided by a measure that determines the quality of biclusters. It follows that defining such a measure is probably the most important aspect. One of the popular quality measure is the mean squared residue (MSR). However, it has been proven that MSR fails at identifying some kind of patterns. This motivates us to introduce a novel measure, called virtual error (VE), that overcomes this limitation. Results obtained by using VE confirm that it can identify interesting patterns that could not be found by MSR.

CarGene: characterisation of sets of genes based on metabolic pathways analysis.

The great amount of biological information provides scientists with an incomparable framework for testing the results of new algorithms. Several tools have been developed for analysing gene-enrichment and most of them are Gene Ontology-based tools. We developed a Kyoto Encyclopedia of Genes and Genomes (Kegg)-based tool that provides a friendly graphical environment for analysing gene-enrichment. The tool integrates two statistical corrections and simultaneously analysing the information about many groups of genes in both visual and textual manner. We tested the usefulness of our approach on a previous analysis (Huttenshower et al.). Furthermore, our tool is freely available (http://www.upo.es/eps/bigs/cargene.html).

GO-based functional dissimilarity of gene sets.

BACKGROUND: The Gene Ontology (GO) provides a controlled vocabulary for describing the functions of genes and can be used to evaluate the functional coherence of gene sets. Many functional coherence measures consider each pair of gene functions in a set and produce an output based on all pairwise distances. A single gene can encode multiple proteins that may differ in function. For each functionality, other proteins that exhibit the same activity may also participate. Therefore, an identification of the most common function for all of the genes involved in a biological process is important in evaluating the functional similarity of groups of genes and a quantification of functional coherence can helps to clarify the role of a group of genes working together. RESULTS: To implement this approach to functional assessment, we present GFD (GO-based Functional Dissimilarity), a novel dissimilarity measure for evaluating groups of genes based on the most relevant functions of the whole set. The measure assigns a numerical value to the gene set for each of the three GO sub-ontologies. CONCLUSIONS: Results show that GFD performs robustly when applied to gene set of known functionality (extracted from KEGG). It performs particularly well on randomly generated gene sets. An ROC analysis reveals that the performance of GFD in evaluating the functional dissimilarity of gene sets is very satisfactory. A comparative analysis against other functional measures, such as GS2 and those presented by Resnik and Wang, also demonstrates the robustness of GFD.

Predicting protein distance maps according to physicochemical properties.

The prediction of protein structures is a current issue of great significance in structural bioinformatics. More specifically, the prediction of the tertiary structure of a protein consists in determining its three-dimensional conformation based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Many approaches cited in the literature use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, implemented with parallel multithreading, we used a set of 30 physicochemical amino acid properties selected from the AAindex database. Several protein tertiary structure prediction methods produce a contact map. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. We performed several preliminary analysis of the protein physicochemical data distributions using 3D surfaces. Three main pattern types were found in 3D surfaces, thus it is possible to extract rules in order to predict distances between amino acids according to their physicochemical properties. We performed an experimental validation of our method using five non-homologous protein sets and we showed the generality of this method and its prediction quality using the amino acid properties considered. Finally, we included a study of the algorithm efficiency according to the number of most similar fragments considered and we notably improved the precision with the studied proteins sets.

A biclustering algorithm for extracting bit-patterns from binary datasets.

MOTIVATION: Binary datasets represent a compact and simple way to store data about the relationships between a group of objects and their possible properties. In the last few years, different biclustering algorithms have been specially developed to be applied to binary datasets. Several approaches based on matrix factorization, suffix trees or divide-and-conquer techniques have been proposed to extract useful biclusters from binary data, and these approaches provide information about the distribution of patterns and intrinsic correlations. RESULTS: A novel approach to extracting biclusters from binary datasets, BiBit, is introduced here. The results obtained from different experiments with synthetic data reveal the excellent performance and the robustness of BiBit to density and size of input data. Also, BiBit is applied to a central nervous system embryonic tumor gene expression dataset to test the quality of the results. A novel gene expression preprocessing methodology, based on expression level layers, and the selective search performed by BiBit, based on a very fast bit-pattern processing technique, provide very satisfactory results in quality and computational cost. The power of biclustering in finding genes involved simultaneously in different cancer processes is also shown. Finally, a comparison with Bimax, one of the most cited binary biclustering algorithms, shows that BiBit is faster while providing essentially the same results. AVAILABILITY: The source and binary codes, the datasets used in the experiments and the results can be found at: http://www.upo.es/eps/bigs/BiBit.html CONTACT: dsrodbae@upo.es SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Biclustering of gene expression data by correlation-based scatter search.

BACKGROUND: The analysis of data generated by microarray technology is very useful to understand how the genetic information becomes functional gene products. Biclustering algorithms can determine a group of genes which are co-expressed under a set of experimental conditions. Recently, new biclustering methods based on metaheuristics have been proposed. Most of them use the Mean Squared Residue as merit function but interesting and relevant patterns from a biological point of view such as shifting and scaling patterns may not be detected using this measure. However, it is important to discover this type of patterns since commonly the genes can present a similar behavior although their expression levels vary in different ranges or magnitudes. METHODS: Scatter Search is an evolutionary technique that is based on the evolution of a small set of solutions which are chosen according to quality and diversity criteria. This paper presents a Scatter Search with the aim of finding biclusters from gene expression data. In this algorithm the proposed fitness function is based on the linear correlation among genes to detect shifting and scaling patterns from genes and an improvement method is included in order to select just positively correlated genes. RESULTS: The proposed algorithm has been tested with three real data sets such as Yeast Cell Cycle dataset, human B-cells lymphoma dataset and Yeast Stress dataset, finding a remarkable number of biclusters with shifting and scaling patterns. In addition, the performance of the proposed method and fitness function are compared to that of CC, OPSM, ISA, BiMax, xMotifs and Samba using Gene the Ontology Database.

Prognostic transcriptional association networks: a new supervised approach based on regression trees.

MOTIVATION: The application of information encoded in molecular networks for prognostic purposes is a crucial objective of systems biomedicine. This approach has not been widely investigated in the cardiovascular research area. Within this area, the prediction of clinical outcomes after suffering a heart attack would represent a significant step forward. We developed a new quantitative prediction-based method for this prognostic problem based on the discovery of clinically relevant transcriptional association networks. This method integrates regression trees and clinical class-specific networks, and can be applied to other clinical domains. RESULTS: Before analyzing our cardiovascular disease dataset, we tested the usefulness of our approach on a benchmark dataset with control and disease patients. We also compared it to several algorithms to infer transcriptional association networks and classification models. Comparative results provided evidence of the prediction power of our approach. Next, we discovered new models for predicting good and bad outcomes after myocardial infarction. Using blood-derived gene expression data, our models reported areas under the receiver operating characteristic curve above 0.70. Our model could also outperform different techniques based on co-expressed gene modules. We also predicted processes that may represent novel therapeutic targets for heart disease, such as the synthesis of leucine and isoleucine. AVAILABILITY: The SATuRNo software is freely available at http://www.lsi.us.es/isanepo/toolsSaturno/.

Inferring gene regression networks with model trees.

BACKGROUND: Novel strategies are required in order to handle the huge amount of data produced by microarray technologies. To infer gene regulatory networks, the first step is to find direct regulatory relationships between genes building the so-called gene co-expression networks. They are typically generated using correlation statistics as pairwise similarity measures. Correlation-based methods are very useful in order to determine whether two genes have a strong global similarity but do not detect local similarities. RESULTS: We propose model trees as a method to identify gene interaction networks. While correlation-based methods analyze each pair of genes, in our approach we generate a single regression tree for each gene from the remaining genes. Finally, a graph from all the relationships among output and input genes is built taking into account whether the pair of genes is statistically significant. For this reason we apply a statistical procedure to control the false discovery rate. The performance of our approach, named REGNET, is experimentally tested on two well-known data sets: Saccharomyces Cerevisiae and E.coli data set. First, the biological coherence of the results are tested. Second the E.coli transcriptional network (in the Regulon database) is used as control to compare the results to that of a correlation-based method. This experiment shows that REGNET performs more accurately at detecting true gene associations than the Pearson and Spearman zeroth and first-order correlation-based methods. CONCLUSIONS: REGNET generates gene association networks from gene expression data, and differs from correlation-based methods in that the relationship between one gene and others is calculated simultaneously. Model trees are very useful techniques to estimate the numerical values for the target genes by linear regression functions. They are very often more precise than linear regression models because they can add just different linear regressions to separate areas of the search space favoring to infer localized similarities over a more global similarity. Furthermore, experimental results show the good performance of REGNET.

Gene association analysis: a survey of frequent pattern mining from gene expression data.

Establishing an association between variables is always of interest in genomic studies. Generation of DNA microarray gene expression data introduces a variety of data analysis issues not encountered in traditional molecular biology or medicine. Frequent pattern mining (FPM) has been applied successfully in business and scientific data for discovering interesting association patterns, and is becoming a promising strategy in microarray gene expression analysis. We review the most relevant FPM strategies, as well as surrounding main issues when devising efficient and practical methods for gene association analysis (GAA). We observed that, so far, scalability achieved by efficient methods does not imply biological soundness of the discovered association patterns, and vice versa. Ideally, GAA should employ a balanced mining model taking into account best practices employed by methods reviewed in this survey. Integrative approaches, in which biological knowledge plays an important role within the mining process, are becoming more reliable.

Filling the gap between biology and computer science.

This editorial introduces BioData Mining, a new journal which publishes research articles related to advances in computational methods and techniques for the extraction of useful knowledge from heterogeneous biological data. We outline the aims and scope of the journal, introduce the publishing model and describe the open peer review policy, which fosters interaction within the research community.