Search

Nonparametric feature selection for high-dimensional data is an important and challenging problem in the fields of statistics and machine learning. Most of the existing methods for feature selection focus on parametric or additive models which may suffer from model misspecification. In this paper, we propose a new framework to perform nonparametric feature selection for both regression and classification problems. Under this framework, we learn prediction functions through empirical risk minimization over a reproducing kernel Hilbert space. The space is generated by a novel tensor product kernel, which depends on a set of parameters that determines the importance of the features. Computationally, we minimize the empirical risk with a penalty to estimate the prediction and kernel parameters simultaneously. The solution can be obtained by iteratively solving convex optimization problems. We study the theoretical property of the kernel feature space and prove the oracle selection property and Fisher consistency of our proposed method. Finally, we demonstrate the superior performance of our approach compared to existing methods via extensive simulation studies and applications to two real studies., (© 2022 The International Biometric Society.)

Objectives. We aimed to establish an effective machine learning (ML) model for predicting the risk of distant metastasis (DM) in medullary thyroid carcinoma (MTC). Methods. Demographic data of MTC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database of the National Institutes of Health between 2004 and 2015 to develop six ML algorithm models. Models were evaluated based on accuracy, precision, recall rate, F1-score, and area under the receiver operating characteristic curve (AUC). The association between clinicopathological characteristics and target variables was interpreted. Analyses were performed using traditional logistic regression (LR). Results. In total, 2049 patients were included and 138 developed DM. Multivariable LR showed that age, sex, tumor size, extrathyroidal extension, and lymph node metastasis were predictive features for DM in MTC. Among the six ML models, the random forest (RF) had the best predictability in assessing the risk of DM in MTC, with an accuracy, precision, recall rate, F1-score, and AUC higher than those of the traditional binary LR model. Conclusion. RF was superior to traditional LR in predicting the risk of DM in MTC and can provide a valuable reference for clinicians in decision-making. [ABSTRACT FROM AUTHOR]

Subcellular localization attempts to assign proteins to one of the cell compartments that performs specific biological functions. Finding the link between proteins, biological functions, and subcellular localization is an effective way to investigate the general organization of living cells in a systematic manner. However, determining the subcellular localization of proteins by traditional experimental approaches is difficult. Here, protein–protein interaction networks, functional enrichment on gene ontology and pathway, and a set of proteins having confirmed subcellular localization were applied to build prediction models for human protein subcellular localizations. To build an effective predictive model, we employed a variety of robust machine learning algorithms, including Boruta feature selection, minimum redundancy maximum relevance, Monte Carlo feature selection, and LightGBM. Then, the incremental feature selection method with random forest and support vector machine was used to discover the essential features. Furthermore, 38 key features were determined by integrating results of different feature selection methods, which may provide critical insights into the subcellular location of proteins. Their biological functions of subcellular localizations were discussed according to recent publications. In summary, our computational framework can help advance the understanding of subcellular localization prediction techniques and provide a new perspective to investigate the patterns of protein subcellular localization and their biological importance. [ABSTRACT FROM AUTHOR]

Methylation is one of the most common and considerable modifications in biological systems mediated by multiple enzymes. Recent studies have shown that methylation has been widely identified in different RNA molecules. RNA methylation modifications have various kinds, such as 5-methylcytosine (m5C). However, for individual methylation sites, their functions still remain to be elucidated. Testing of all methylation sites relies heavily on high-throughput sequencing technology, which is expensive and labor consuming. Thus, computational prediction approaches could serve as a substitute. In this study, multiple machine learning models were used to predict possible RNA m5C sites on the basis of mRNA sequences in human and mouse. Each site was represented by several features derived from k -mers of an RNA subsequence containing such site as center. The powerful max-relevance and min-redundancy (mRMR) feature selection method was employed to analyse these features. The outcome feature list was fed into incremental feature selection method, incorporating four classification algorithms, to build efficient models. Furthermore, the sites related to features used in the models were also investigated. [ABSTRACT FROM AUTHOR]

COVID-19, a severe respiratory disease caused by a new type of coronavirus SARS-CoV-2, has been spreading all over the world. Patients infected with SARS-CoV-2 may have no pathogenic symptoms, i.e., presymptomatic patients and asymptomatic patients. Both patients could further spread the virus to other susceptible people, thereby making the control of COVID-19 difficult. The two major challenges for COVID-19 diagnosis at present are as follows: (1) patients could share similar symptoms with other respiratory infections, and (2) patients may not have any symptoms but could still spread the virus. Therefore, new biomarkers at different omics levels are required for the large-scale screening and diagnosis of COVID-19. Although some initial analyses could identify a group of candidate gene biomarkers for COVID-19, the previous work still could not identify biomarkers capable for clinical use in COVID-19, which requires disease-specific diagnosis compared with other multiple infectious diseases. As an extension of the previous study, optimized machine learning models were applied in the present study to identify some specific qualitative host biomarkers associated with COVID-19 infection on the basis of a publicly released transcriptomic dataset, which included healthy controls and patients with bacterial infection, influenza, COVID-19, and other kinds of coronavirus. This dataset was first analysed by Boruta, Max-Relevance and Min-Redundancy feature selection methods one by one, resulting in a feature list. This list was fed into the incremental feature selection method, incorporating one of the classification algorithms to extract essential biomarkers and build efficient classifiers and classification rules. The capacity of these findings to distinguish COVID-19 with other similar respiratory infectious diseases at the transcriptomic level was also validated, which may improve the efficacy and accuracy of COVID-19 diagnosis. [ABSTRACT FROM AUTHOR]