scholarly journals Construction of the Classification Model Using Key Genes Identified Between Benign and Malignant Thyroid Nodules From Comprehensive Transcriptomic Data

2022 ◽  
Vol 12 ◽  
Author(s):  
Qingxia Yang ◽  
Yaguo Gong

Thyroid nodules are present in upto 50% of the population worldwide, and thyroid malignancy occurs in only 5–15% of nodules. Until now, fine-needle biopsy with cytologic evaluation remains the diagnostic choice to determine the risk of malignancy, yet it fails to discriminate as benign or malignant in one-third of cases. In order to improve the diagnostic accuracy and reliability, molecular testing based on transcriptomic data has developed rapidly. However, gene signatures of thyroid nodules identified in a plenty of transcriptomic studies are highly inconsistent and extremely difficult to be applied in clinical application. Therefore, it is highly necessary to identify consistent signatures to discriminate benign or malignant thyroid nodules. In this study, five independent transcriptomic studies were combined to discover the gene signature between benign and malignant thyroid nodules. This combined dataset comprises 150 malignant and 93 benign thyroid samples. Then, there were 279 differentially expressed genes (DEGs) discovered by the feature selection method (Student’s t test and fold change). And the weighted gene co-expression network analysis (WGCNA) was performed to identify the modules of highly co-expressed genes, and 454 genes in the gray module were discovered as the hub genes. The intersection between DEGs by the feature selection method and hub genes in the WGCNA model was identified as the key genes for thyroid nodules. Finally, four key genes (ST3GAL5, NRCAM, MT1F, and PROS1) participated in the pathogenesis of malignant thyroid nodules were validated using an independent dataset. Moreover, a high-performance classification model for discriminating thyroid nodules was constructed using these key genes. All in all, this study might provide a new insight into the key differentiation of benign and malignant thyroid nodules.

2010 ◽  
Vol 44-47 ◽  
pp. 1130-1134
Author(s):  
Sheng Li ◽  
Pei Lin Zhang ◽  
Bing Li

Feature selection is a key step in hydraulic system fault diagnosis. Some of the collected features are unrelated to classification model, and some are high correlated to other features. These features are harmful for establishing classification model. In order to solve this problem, genetic algorithm-partial least squares (GA-PLS) is proposed for selecting the representative and optimal features. K nearest neighbor algorithm (KNN) is used for diagnosing and classifying hydraulic system faults. For expressing better performance of GA-PLS, the original data of a model engineering hydraulic system is used, and the results of GA-PLS are compared with all feature used and GA. The experimental results show that, the proposed feature method can diagnose and classify hydraulic system faults more efficiently with using fewer features.


Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 301 ◽  
Author(s):  
Jie Cao ◽  
Da Wang ◽  
Zhaoyang Qu ◽  
Hongyu Sun ◽  
Bin Li ◽  
...  

Network traffic classification based on machine learning is an important branch of pattern recognition in computer science. It is a key technology for dynamic intelligent network management and enhanced network controllability. However, the traffic classification methods still facing severe challenges: The optimal set of features is difficult to determine. The classification method is highly dependent on the effective characteristic combination. Meanwhile, it is also important to balance the experience risk and generalization ability of the classifier. In this paper, an improved network traffic classification model based on a support vector machine is proposed. First, a filter-wrapper hybrid feature selection method is proposed to solve the false deletion of combined features caused by a traditional feature selection method. Second, to balance the empirical risk and generalization ability of support vector machine (SVM) traffic classification model, an improved parameter optimization algorithm is proposed. The algorithm can dynamically adjust the quadratic search area, reduce the density of quadratic mesh generation, improve the search efficiency of the algorithm, and prevent the over-fitting while optimizing the parameters. The experiments show that the improved traffic classification model achieves higher classification accuracy, lower dimension and shorter elapsed time and performs significantly better than traditional SVM and the other three typical supervised ML algorithms.


2020 ◽  
Vol 3 (1) ◽  
pp. 58-63
Author(s):  
Y. Mansour Mansour ◽  
Majed A. Alenizi

Emails are currently the main communication method worldwide as it proven in its efficiency. Phishing emails in the other hand is one of the major threats which results in significant losses, estimated at billions of dollars. Phishing emails is a more dynamic problem, a struggle between the phishers and defenders where the phishers have more flexibility in manipulating the emails features and evading the anti-phishing techniques. Many solutions have been proposed to mitigate the phishing emails impact on the targeted sectors, but none have achieved 100% detection and accuracy. As phishing techniques are evolving, the solutions need to be evolved and generalized in order to mitigate as much as possible. This article presents a new emergent classification model based on hybrid feature selection method that combines two common feature selection methods, Information Gain and Genetic Algorithm that keep only significant and high-quality features in the final classifier. The Proposed hybrid approach achieved 98.9% accuracy rate against phishing emails dataset comprising 8266 instances and results depict enhancement by almost 4%. Furthermore, the presented technique has contributed to reducing the search space by reducing the number of selected features.


2020 ◽  
Vol 12 (1) ◽  
pp. 113 ◽  
Author(s):  
Andrew Hennessy ◽  
Kenneth Clarke ◽  
Megan Lewis

Hyperspectral sensing, measuring reflectance over visible to shortwave infrared wavelengths, has enabled the classification and mapping of vegetation at a range of taxonomic scales, often down to the species level. Classification with hyperspectral measurements, acquired by narrow band spectroradiometers or imaging sensors, has generally required some form of spectral feature selection to reduce the dimensionality of the data to a level suitable for the construction of a classification model. Despite the large number of hyperspectral plant classification studies, an in-depth review of feature selection methods and resultant waveband selections has not yet been performed. Here, we present a review of the last 22 years of hyperspectral vegetation classification literature that evaluates the overall waveband selection frequency, waveband selection frequency variation by taxonomic, structural, or functional group, and the influence of feature selection choice by comparing such methods as stepwise discriminant analysis (SDA), support vector machines (SVM), and random forests (RF). This review determined that all characteristics of hyperspectral plant studies influence the wavebands selected for classification. This includes the taxonomic, structural, and functional groups of the target samples, the methods, and scale at which hyperspectral measurements are recorded, as well as the feature selection method used. Furthermore, these influences do not appear to be consistent. Moreover, the considerable variability in waveband selection caused by the feature selectors effectively masks the analysis of any variability between studies related to plant groupings. Additionally, questions are raised about the suitability of SDA as a feature selection method, with it producing waveband selections at odds with the other feature selectors. Caution is recommended when choosing a feature selector for hyperspectral plant classification: We recommend multiple methods being performed. The resultant sets of selected spectral features can either be evaluated individually by multiple classification models or combined as an ensemble for evaluation by a single classifier. Additionally, we suggest caution when relying upon waveband recommendations from the literature to guide waveband selections or classifications for new plant discrimination applications, as such recommendations appear to be weakly generalizable between studies.


2021 ◽  
Author(s):  
Kun Yu ◽  
Weidong Xie ◽  
Linjie Wang ◽  
Wei Li

Abstract Background Finding significant genes or proteins from gene chip data for disease diagnosis and drug development is an important task, and the challenge comes from the curse of the data dimension. It is of great significance to use machine learning methods to find important features from the data and build an accurate classification model. Results The proposed Method has proved superior to the published advanced hybrid feature selection method and traditional feature selection method on different public microarray data sets. In addition, the results on the cleft lip and palate data set with known biomarkers provided by the cooperative hospital show that compared with other methods, our method can preferentially select these biomarkers. Method In this paper, a feature selection algorithm ILRC based on clustering and improved L1 regularization is proposed. In this method, the features are first clustered, and the redundant features in the sub-clusters are deleted. Then all the remaining features are iteratively evaluated using ILR, and the final result is output according to the cumulative weight reordering. Conclusion The proposed method can effectively remove redundant features. The algorithm's output has high stability and classification accuracy and can potentially select potential biomarkers.


2019 ◽  
Vol 2 (2) ◽  
pp. 58 ◽  
Author(s):  
Utomo Pujianto ◽  
Asa Luki Setiawan ◽  
Harits Ar Rosyid ◽  
Ali M. Mohammad Salah

Diabetes is a metabolic disorder disease in which the pancreas does not produce enough insulin or the body cannot use insulin produced effectively. The HbA1c examination, which measures the average glucose level of patients during the last 2-3 months, has become an important step to determine the condition of diabetic patients. Knowledge of the patient's condition can help medical staff to predict the possibility of patient readmissions, namely the occurrence of a patient requiring hospitalization services back at the hospital. The ability to predict patient readmissions will ultimately help the hospital to calculate and manage the quality of patient care. This study compares the performance of the Naïve Bayes method and C4.5 Decision Tree in predicting readmissions of diabetic patients, especially patients who have undergone HbA1c examination. As part of this study we also compare the performance of the classification model from a number of scenarios involving a combination of preprocessing methods, namely Synthetic Minority Over-Sampling Technique (SMOTE) and Wrapper feature selection method, with both classification techniques. The scenario of C4.5 method combined with SMOTE and feature selection method produces the best performance in classifying readmissions of diabetic patients with an accuracy value of 82.74 %, precision value of 87.1 %, and recall value of 82.7 %.


2021 ◽  
pp. 1-11
Author(s):  
Ya Gao

The network provides a convenient mechanism for publishing and obtaining documents, and has now become a gathering place for all kinds of information. In the network, the amount of information increases exponentially, and how to dig useful patterns or knowledge from the massive network culture has become a hot topic for scholars. In data mining, in order to enable readers to quickly obtain the content of interest, research text classification, and automatically classify text data according to a certain classification model. Internet cultural text data has the characteristics of unstructured, subjective, high-dimensional, etc., which makes it difficult for text mining algorithms to extract effective and easy-to-understand classification rules, and the computational complexity is too high. This paper proposes a feature selection method based on robust features, using sample deviation and variance as the criteria for feature attributes to rank the importance of feature attributes, and select the best feature attribute subset. The experimental results show that the classification accuracy of the feature selection method based on sample deviation and variance proposed in this paper is higher than the traditional word frequency as the feature selection method, which proves the feasibility and superiority of the feature selection method proposed in this paper.


2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Kun Yu ◽  
Weidong Xie ◽  
Linjie Wang ◽  
Wei Li

Abstract Background Finding significant genes or proteins from gene chip data for disease diagnosis and drug development is an important task. However, the challenge comes from the curse of the data dimension. It is of great significance to use machine learning methods to find important features from the data and build an accurate classification model. Results The proposed method has proved superior to the published advanced hybrid feature selection method and traditional feature selection method on different public microarray data sets. In addition, the biomarkers selected using our method show a match to those provided by the cooperative hospital in a set of clinical cleft lip and palate data. Method In this paper, a feature selection algorithm ILRC based on clustering and improved L1 regularization is proposed. The features are firstly clustered, and the redundant features in the sub-clusters are deleted. Then all the remaining features are iteratively evaluated using ILR. The final result is given according to the cumulative weight reordering. Conclusion The proposed method can effectively remove redundant features. The algorithm’s output has high stability and classification accuracy, which can potentially select potential biomarkers.


Sign in / Sign up

Export Citation Format

Share Document