Dataset Information

Feature selection and classifier performance on diverse bio- logical datasets.

ABSTRACT: There is an ever-expanding range of technologies that generate very large numbers of biomarkers for research and clinical applications. Choosing the most informative biomarkers from a high-dimensional data set, combined with identifying the most reliable and accurate classification algorithms to use with that biomarker set, can be a daunting task. Existing surveys of feature selection and classification algorithms typically focus on a single data type, such as gene expression microarrays, and rarely explore the model's performance across multiple biological data types.This paper presents the results of a large scale empirical study whereby a large number of popular feature selection and classification algorithms are used to identify the tissue of origin for the NCI-60 cancer cell lines. A computational pipeline was implemented to maximize predictive accuracy of all models at all parameters on five different data types available for the NCI-60 cell lines. A validation experiment was conducted using external data in order to demonstrate robustness.As expected, the data type and number of biomarkers have a significant effect on the performance of the predictive models. Although no model or data type uniformly outperforms the others across the entire range of tested numbers of markers, several clear trends are visible. At low numbers of biomarkers gene and protein expression data types are able to differentiate between cancer cell lines significantly better than the other three data types, namely SNP, array comparative genome hybridization (aCGH), and microRNA data.

SUBMITTER: Hemphill E

PROVIDER: S-EPMC4248652 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feature selection and classifier performance on diverse bio- logical datasets.

Hemphill Edward E Lindsay James J Lee Chih C Măndoiu Ion I II Nelson Craig E CE

BMC bioinformatics 20141113

<h4>Background</h4>There is an ever-expanding range of technologies that generate very large numbers of biomarkers for research and clinical applications. Choosing the most informative biomarkers from a high-dimensional data set, combined with identifying the most reliable and accurate classification algorithms to use with that biomarker set, can be a daunting task. Existing surveys of feature selection and classification algorithms typically focus on a single data type, such as gene expression ...[more]

PMID: 25434802

Similar Datasets

Project description:With the ever-increasing pace of genome sequencing, there is a great need for fast and accurate computational tools to automatically identify genes in these genomes. Although great progress has been made in the development of gene-finding algorithms during the past decades, there is still room for further improvement. In particular, the issue of recognizing short exons in eukaryotes is still not solved satisfactorily. This article is devoted to assessing various linear and kernel-based classification algorithms and selecting the best combination of Z-curve features for further improvement of the issue. Eight state-of-the-art linear and kernel-based supervised pattern recognition techniques were used to identify the short (21-192?bp) coding sequences of human genes. By measuring the prediction accuracy, the tradeoff between sensitivity and specificity and the time consumption, partial least squares (PLS) and kernel partial least squares (KPLS) algorithms were verified to be the most optimal linear and kernel-based classifiers, respectively. A surprising result was that, by making good use of the interpretability of the PLS and the Z-curve methods, 93 Z-curve features were proved to be the best selective combination. Using them, the average recognition accuracy was improved as high as 7.7% by means of KPLS when compared with what was obtained by the Fisher discriminant analysis using 189 Z-curve variables (Gao and Zhang, 2004 ). The used codes are freely available from the following approaches (implemented in MATLAB and supported on Linux and MS Windows): (1) SVM: http://www.support-vector-machines.org/SVM_soft.html. (2) GP: http://www.gaussianprocess.org. (3) KPLS and KFDA: Taylor, J.S., and Cristianini, N. 2004. Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge, UK. (4) PLS: Wise, B.M., and Gallagher, N.B. 2011. PLS-Toolbox for use with MATLAB: ver 1.5.2. Eigenvector Technologies, Manson, WA. Supplementary Material for this article is available at www.liebertonline.com/cmb.

Project description:The exponential rise in social media via microblogging sites like Twitter has sparked curiosity in sentiment analysis that exploits user feedback towards a targeted product or service. Considering its significance in business intelligence and decision-making, numerous efforts have been made in this area. However, lack of dictionaries, unannotated data, large-scale unstructured data, and low accuracies have plagued these approaches. Also, sentiment classification through classifier ensemble has been underexplored in literature. In this article, we propose a Semantic Relational Machine Learning (SRML) model that automatically classifies the sentiment of tweets by using classifier ensemble and optimal features. The model employs the Cascaded Feature Selection (CFS) strategy, a novel statistical assessment approach based on Wilcoxon rank sum test, univariate logistic regression assisted significant predictor test and cross-correlation test. It further uses the efficacy of word2vec-based continuous bag-of-words and n-gram feature extraction in conjunction with SentiWordNet for finding optimal features for classification. We experiment on six public Twitter sentiment datasets, the STS-Gold dataset, the Obama-McCain Debate (OMD) dataset, the healthcare reform (HCR) dataset and the SemEval2017 Task 4A, 4B and 4C on a heterogeneous classifier ensemble comprising fourteen individual classifiers from different paradigms. Results from the experimental study indicate that CFS supports in attaining a higher classification accuracy with up to 50% lesser features compared to count vectorizer approach. In Intra-model performance assessment, the Artificial Neural Network-Gradient Descent (ANN-GD) classifier performs comparatively better than other individual classifiers, but the Best Trained Ensemble (BTE) strategy outperforms on all metrics. In inter-model performance assessment with existing state-of-the-art systems, the proposed model achieved higher accuracy and outperforms more accomplished models employing quantum-inspired sentiment representation (QSR), transformer-based methods like BERT, BERTweet, RoBERTa and ensemble techniques. The research thus provides critical insights into implementing similar strategy into building more generic and robust expert system for sentiment analysis that can be leveraged across industries.

Project description:Microarray technology is known as one of the most important tools for collecting DNA expression data. This technology allows researchers to investigate and examine types of diseases and their origins. However, microarray data are often associated with a small sample size, a significant number of genes, imbalanced data, etc., making classification models inefficient. Thus, a new hybrid solution based on a multi-filter and adaptive chaotic multi-objective forest optimization algorithm (AC-MOFOA) is presented to solve the gene selection problem and construct the Ensemble Classifier. In the proposed solution, a multi-filter model (i.e., ensemble filter) is proposed as preprocessing step to reduce the dataset's dimensions, using a combination of five filter methods to remove redundant and irrelevant genes. Accordingly, the results of the five filter methods are combined using a voting-based function. Additionally, the results of the proposed multi-filter indicate that it has good capability in reducing the gene subset size and selecting relevant genes. Then, an AC-MOFOA based on the concepts of non-dominated sorting, crowding distance, chaos theory, and adaptive operators is presented. AC-MOFOA as a wrapper method aimed at reducing dataset dimensions, optimizing KELM, and increasing the accuracy of the classification, simultaneously. Next, in this method, an ensemble classifier model is presented using AC-MOFOA results to classify microarray data. The performance of the proposed algorithm was evaluated on nine public microarray datasets, and its results were compared in terms of the number of selected genes, classification efficiency, execution time, time complexity, hypervolume indicator, and spacing metric with five hybrid multi-objective methods, and three hybrid single-objective methods. According to the results, the proposed hybrid method could increase the accuracy of the KELM in most datasets by reducing the dataset's dimensions and achieve similar or superior performance compared to other multi-objective methods. Furthermore, the proposed Ensemble Classifier model could provide better classification accuracy and generalizability in the seven of nine microarray datasets compared to conventional ensemble methods. Moreover, the comparison results of the Ensemble Classifier model with three state-of-the-art ensemble generation methods indicate its competitive performance in which the proposed ensemble model achieved better results in the five of nine datasets.Supplementary informationThe online version contains supplementary material available at 10.1007/s00521-021-06459-9.

Project description:BackgroundIdentifying lncRNA-disease associations not only helps to better comprehend the underlying mechanisms of various human diseases at the lncRNA level but also speeds up the identification of potential biomarkers for disease diagnoses, treatments, prognoses, and drug response predictions. However, as the amount of archived biological data continues to grow, it has become increasingly difficult to detect potential human lncRNA-disease associations from these enormous biological datasets using traditional biological experimental methods. Consequently, developing new and effective computational methods to predict potential human lncRNA diseases is essential.ResultsUsing a combination of incremental principal component analysis (IPCA) and random forest (RF) algorithms and by integrating multiple similarity matrices, we propose a new algorithm (IPCARF) based on integrated machine learning technology for predicting lncRNA-disease associations. First, we used two different models to compute a semantic similarity matrix of diseases from a directed acyclic graph of diseases. Second, a characteristic vector for each lncRNA-disease pair is obtained by integrating disease similarity, lncRNA similarity, and Gaussian nuclear similarity. Then, the best feature subspace is obtained by applying IPCA to decrease the dimension of the original feature set. Finally, we train an RF model to predict potential lncRNA-disease associations. The experimental results show that the IPCARF algorithm effectively improves the AUC metric when predicting potential lncRNA-disease associations. Before the parameter optimization procedure, the AUC value predicted by the IPCARF algorithm under 10-fold cross-validation reached 0.8529; after selecting the optimal parameters using the grid search algorithm, the predicted AUC of the IPCARF algorithm reached 0.8611.ConclusionsWe compared IPCARF with the existing LRLSLDA, LRLSLDA-LNCSIM, TPGLDA, NPCMF, and ncPred prediction methods, which have shown excellent performance in predicting lncRNA-disease associations. The compared results of 10-fold cross-validation procedures show that the predictions of the IPCARF method are better than those of the other compared methods.

Dataset Information

Feature selection and classifier performance on diverse bio- logical datasets.

Publications

Feature selection and classifier performance on diverse bio- logical datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets