Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants

MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection.

Download Full-text

The impact of feature selection on one and two-class classification performance for plant microRNAs

PeerJ ◽

10.7717/peerj.2135 ◽

2016 ◽

Vol 4 ◽

pp. e2135 ◽

Cited By ~ 8

Author(s):

Waleed Khalifa ◽

Malik Yousef ◽

Müşerref Duygu Saçar Demirci ◽

Jens Allmer

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Feature Selection Method ◽

Mature Mirnas ◽

Classification Performance ◽

Mirna Detection ◽

To Come ◽

One Class Classification ◽

The Impact ◽

Better Than

MicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18–24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on parwith TCC given the proper set of features.

Download Full-text

A Hybrid Feature Selection Method for Improve the Accuracy of Medical Classification Process

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.a9624.1111121 ◽

2021 ◽

Vol 11 (1) ◽

pp. 50-55

Author(s):

Maria Mohammad Yousef ◽

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Dimensionality Reduction ◽

Classification Accuracy ◽

Fitness Function ◽

Machine Learning Algorithms ◽

Feature Subset Selection ◽

High Dimensionality ◽

Support Vector ◽

Feature Subset

Generally, medical dataset classification has become one of the biggest problems in data mining research. Every database has a given number of features but it is observed that some of these features can be redundant and can be harmful as well as disrupt the process of classification and this problem is known as a high dimensionality problem. Dimensionality reduction in data preprocessing is critical for increasing the performance of machine learning algorithms. Besides the contribution of feature subset selection in dimensionality reduction gives a significant improvement in classification accuracy. In this paper, we proposed a new hybrid feature selection approach based on (GA assisted by KNN) to deal with issues of high dimensionality in biomedical data classification. The proposed method first applies the combination between GA and KNN for feature selection to find the optimal subset of features where the classification accuracy of the k-Nearest Neighbor (kNN) method is used as the fitness function for GA. After selecting the best-suggested subset of features, Support Vector Machine (SVM) are used as the classifiers. The proposed method experiments on five medical datasets of the UCI Machine Learning Repository. It is noted that the suggested technique performs admirably on these databases, achieving higher classification accuracy while using fewer features.

Download Full-text

An Empirical Evaluation of Feature Selection Methods

Improving Knowledge Discovery through the Integration of Data Mining Techniques - Advances in Data Mining and Database Management ◽

10.4018/978-1-4666-8513-0.ch012 ◽

2015 ◽

pp. 233-258 ◽

Cited By ~ 1

Author(s):

Mohsin Iqbal ◽

Saif Ur Rehman ◽

Saira Gillani ◽

Sohail Asghar

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Classification Accuracy ◽

Information Gain ◽

Learning Algorithm ◽

Empirical Evaluation ◽

Machine Learning Algorithms ◽

Selection Methods ◽

The One ◽

Processing And Storage

The key objective of the chapter would be to study the classification accuracy, using feature selection with machine learning algorithms. The dimensionality of the data is reduced by implementing Feature selection and accuracy of the learning algorithm improved. We test how an integrated feature selection could affect the accuracy of three classifiers by performing feature selection methods. The filter effects show that Information Gain (IG), Gain Ratio (GR) and Relief-f, and wrapper effect show that Bagging and Naive Bayes (NB), enabled the classifiers to give the highest escalation in classification accuracy about the average while reducing the volume of unnecessary attributes. The achieved conclusions can advise the machine learning users, which classifier and feature selection methods to use to optimize the classification accuracy, and this can be important, especially at risk-sensitive applying Machine Learning whereas in the one of the aim to reduce costs of collecting, processing and storage of unnecessary data.

Download Full-text

Feature Selection Techniques and Classification Accuracy of Supervised Machine Learning in Text Mining

10.7176/jiea/9-3-06 ◽

2019 ◽

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Text Mining ◽

Classification Accuracy ◽

Supervised Machine Learning ◽

Feature Selection Techniques

Download Full-text

Resting-State Functional Network Scale Effects and Statistical Significance-Based Feature Selection in Machine Learning Classification

Computational and Mathematical Methods in Medicine ◽

10.1155/2019/9108108 ◽

2019 ◽

Vol 2019 ◽

pp. 1-18

Author(s):

Hao Guo ◽

Yao Li ◽

Godfred Kim Mensah ◽

Yong Xu ◽

Junjie Chen ◽

...

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Resting State ◽

Classification Accuracy ◽

Statistical Significance ◽

Brain Networks ◽

Selection Strategy ◽

Topological Properties ◽

Functional Brain ◽

Network Scale

In recent years, functional brain network topological features have been widely used as classification features. Previous studies have found that network node scale differences caused by different network parcellation definitions significantly affect the structure of the constructed network and its topological properties. However, we still do not know how network scale differences affect the classification accuracy, performance of classification features, and effectiveness of the feature selection strategy using P values in terms of the machine learning method. This study used five scale parcellations, involving 90, 256, 497, 1003, and 1501 nodes. Three local properties of resting-state functional brain networks were selected (degree, betweenness centrality, and nodal efficiency), and the support vector machine method was used to construct classifiers to identify patients with major depressive disorder. We analyzed the impact of the five scales on classification accuracy. In addition, the effectiveness and redundancy of features obtained by the different scale parcellations were compared. Finally, traditional statistical significance (P value) was verified as a feature selection criterion. The results showed that the feature effectiveness of different scales was similar; in other words, parcellation with more regions did not provide more effective discriminative features. Nevertheless, parcellation with more regions did provide a greater quantity of discriminative features, which led to an improvement in the accuracy of the classification. However, due to the close distance between brain regions, the redundancy of parcellation with more regions was also greater. The traditional P value feature selection strategy is feasible with different scales, but our analysis showed that the traditional P<0.05 threshold was too strict for feature selection. This study provides an important reference for the selection of network scales when applying topological properties of brain networks to machine learning methods.

Download Full-text

Evaluation of standard and semantically-augmented distance metrics for neurology patients

10.21203/rs.3.rs-20018/v2 ◽

2020 ◽

Author(s):

Daniel B Hier ◽

Jonathan Kopel ◽

Steven U Brint ◽

Donald C Wunsch II ◽

Gayla R Olbricht ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Clustering Algorithms ◽

Signs And Symptoms ◽

Machine Learning Algorithms ◽

Learning Performance ◽

Distance Metrics ◽

Distance Metric ◽

Cosine Distance ◽

Cluster Quality

Abstract Background: When patient distances are calculated based on phenotype, signs and symptoms are often converted to concepts from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric often dominates the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks. Methods: We converted the neurological signs and symptoms from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated inter-patient distances by four different metrics (cosine distance, a semantically augmented cosine distance, Jaccard distance, and a semantically augmented bipartite distance). Semantic augmentation for two of the metrics depended on concept similarities from a hierarchical neuro-ontology. For machine learning algorithms, we used the patient diagnosis as the ground truth label and patient signs and symptoms as the machine learning features . We assessed classification accuracy for four classifiers and cluster quality for two clustering algorithms for each of the distance metrics. Results: Inter-patient distances were smaller when the distance metric was semantically augmented. Classification accuracy and cluster quality were not significantly different by distance metric. Conclusion: Using patient diagnoses as labels and patient signs and symptoms as features, we did not find improved classification accuracy or improved cluster quality with semantically augmented distance metrics. Semantic augmentation reduced inter-patient distances but did not improve machine learning performance.

Download Full-text

Evaluation of standard and semantically-augmented distance metrics for neurology patients

10.21203/rs.3.rs-20018/v3 ◽

2020 ◽

Author(s):

Daniel B Hier ◽

Jonathan Kopel ◽

Steven U Brint ◽

Donald C Wunsch II ◽

Gayla R Olbricht ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Clustering Algorithms ◽

Signs And Symptoms ◽

Ground Truth ◽

Machine Learning Algorithms ◽

Distance Metrics ◽

Distance Metric ◽

Cosine Distance ◽

Cluster Quality

Abstract Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks. Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by four different metrics (cosine distance, a semantically augmented cosine distance, Jaccard distance, and a semantically augmented bipartite distance). Semantic augmentation for two of the metrics depended on concept similarities from a hierarchical neuro-ontology. For machine learning algorithms, we used the patient diagnosis as the ground truth label and patient findings as machine learning features. We assessed classification accuracy for four classifiers and cluster quality for two clustering algorithms for each of the distance metrics.Results: Inter-patient distances were smaller when the distance metric was semantically augmented. Classification accuracy and cluster quality were not significantly different by distance metric.Conclusion: Although semantic augmentation reduced inter-patient distances, we did not find improved classification accuracy or improved cluster quality with semantically augmented patient distance metrics.

Download Full-text

A Novel Method of Constrained Feature Selection by the Measurement of Pairwise Constraints Uncertainty

10.21203/rs.3.rs-31751/v2 ◽

2020 ◽

Author(s):

Kamal Berahmand ◽

Mehrdad Rostami ◽

Saman Forouzandeh

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Rapid Growth ◽

Classification Accuracy ◽

High Speed ◽

Large Scale ◽

Learning Algorithm ◽

Target Class ◽

Partially Labeled Data ◽

Novel Method

Abstract In the past decades, the rapid growth of computer and database technologies has led to the rapid growth of large-scale datasets. On the other hand, data mining applications with high dimensional datasets that require high speed and accuracy are rapidly increasing. Semi-supervised learning is a class of machine learning in which unlabeled data and labeled data are used simultaneously to improve feature selection. The goal of feature selection over partially labeled data (semi-supervised feature selection) is to choose a subset of available features with the lowest redundancy with each other and the highest relevancy to the target class, which is the same objective as the feature selection over entirely labeled data. This method actually used the classification to reduce ambiguity in the range of values. First, the similarity values of each pair are collected, and then these values are divided into intervals, and the average of each interval is determined. In the next step, for each interval, the number of pairs in this range is counted. Finally, by using the strength and similarity matrices, a new constraint feature selection ranking is proposed. The performance of the presented method was compared to the performance of the state-of-the-art, and well-known semi-supervised feature selection approaches on eight datasets. The results indicate that the proposed approach improves previous related approaches with respect to the accuracy of the constrained score. In particular, the numerical results showed that the presented approach improved the classification accuracy by about 3% and reduced the number of selected features by 1%. Consequently, it can be said that the proposed method has reduced the computational complexity of the machine learning algorithm despite increasing the classification accuracy.

Download Full-text

Evaluation of standard and semantically-augmented distance metrics for neurology patients

10.21203/rs.3.rs-20018/v4 ◽

2020 ◽

Author(s):

Daniel B Hier ◽

Jonathan Kopel ◽

Steven U Brint ◽

Donald C Wunsch II ◽

Gayla R Olbricht ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Clustering Algorithms ◽

Signs And Symptoms ◽

Ground Truth ◽

Machine Learning Algorithms ◽

Distance Metrics ◽

Distance Metric ◽

Cosine Distance ◽

Cluster Quality

Abstract Background: Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks.Methods: We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by four different metrics (cosine distance, a semantically augmented cosine distance, Jaccard distance, and a semantically augmented bipartite distance). Semantic augmentation for two of the metrics depended on concept similarities from a hierarchical neuro-ontology. For machine learning algorithms, we used the patient diagnosis as the ground truth label and patient findings as machine learning features . We assessed classification accuracy for four classifiers and cluster quality for two clustering algorithms for each of the distance metrics.Results: Inter-patient distances were smaller when the distance metric was semantically augmented. Classification accuracy and cluster quality were not significantly different by distance metric.Conclusion: Although semantic augmentation reduced inter-patient distances, we did not find improved classification accuracy or improved cluster quality with semantically augmented patient distance metrics when applied to a dataset of neurology patients. Further work is needed to assess the utility of semantically augmented patient distances.

Download Full-text

An application of machine learning with feature selection to improve diagnosis and classification of neurodegenerative disorders

BMC Bioinformatics ◽

10.1186/s12859-019-3027-7 ◽

2019 ◽

Vol 20 (1) ◽

Cited By ~ 7

Author(s):

Josefa Díaz Álvarez ◽

Jordi A. Matias-Guiu ◽

María Nieves Cabrera-Martín ◽

José L. Risco-Martín ◽

José L. Ayala

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Selection Process ◽

Clustering Algorithms ◽

Primary Progressive Aphasia ◽

Experimental Tests ◽

Machine Learning Techniques ◽

Positron Emission ◽

Before And After

Abstract Background The analysis of health and medical data is crucial for improving the diagnosis precision, treatments and prevention. In this field, machine learning techniques play a key role. However, the amount of health data acquired from digital machines has high dimensionality and not all data acquired from digital machines are relevant for a particular disease. Primary Progressive Aphasia (PPA) is a neurodegenerative syndrome including several specific diseases, and it is a good model to implement machine learning analyses. In this work, we applied five feature selection algorithms to identify the set of relevant features from 18F-fluorodeoxyglucose positron emission tomography images of the main areas affected by PPA from patient records. On the other hand, we carried out classification and clustering algorithms before and after the feature selection process to contrast both results with those obtained in a previous work. We aimed to find the best classifier and the more relevant features from the WEKA tool to propose further a framework for automatic help on diagnosis. Dataset contains data from 150 FDG-PET imaging studies of 91 patients with a clinic prognosis of PPA, which were examined twice, and 28 controls. Our method comprises six different stages: (i) feature extraction, (ii) expertise knowledge supervision (iii) classification process, (iv) comparing classification results for feature selection, (v) clustering process after feature selection, and (vi) comparing clustering results with those obtained in a previous work. Results Experimental tests confirmed clustering results from a previous work. Although classification results for some algorithms are not decisive for reducing features precisely, Principal Components Analisys (PCA) results exhibited similar or even better performances when compared to those obtained with all features. Conclusions Although reducing the dimensionality does not means a general improvement, the set of features is almost halved and results are better or quite similar. Finally, it is interesting how these results expose a finer grain classification of patients according to the neuroanatomy of their disease.

Download Full-text