AgeGuess, a Methylomic Prediction Model for Human Ages

Gao, Xiaoqian; Liu, Shuai; Song, Haoqiu; Feng, Xin; Duan, Meiyu; Huang, Lan; Zhou, Fengfeng

doi:10.3389/fbioe.2020.00080

Cited by 10 publications

(11 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ridge regression (Ridge) evaluates a subset of features for their connections with the class labels ( Gao et al, 2020 ; Xu et al, 2020 ). Ridge provides a model-based trade-off between the fitting and complexity of the features by adding the L2 regularization to the regression model.…”

Section: Methodsmentioning

confidence: 99%

EnRank: An Ensemble Method to Detect Pulmonary Hypertension Biomarkers Based on Feature Selection and Machine Learning Models

Liu¹,

Fu²,

Zhang³

et al. 2021

Front. Genet.

Self Cite

View full text Add to dashboard Cite

Pulmonary hypertension (PH) is a common disease that affects the normal functioning of the human pulmonary arteries. The peripheral blood mononuclear cells (PMBCs) served as an ideal source for a minimally invasive disease diagnosis. This study hypothesized that the transcriptional fluctuations in the PMBCs exposed to the PH arteries may stably reflect the disease. However, the dimension of a human transcriptome is much higher than the number of samples in all the existing datasets. So, an ensemble feature selection algorithm, EnRank, was proposed to integrate the ranking information of four popular feature selection algorithms, i.e., T-test (Ttest), Chi-squared test (Chi2), ridge regression (Ridge), and Least Absolute Shrinkage and Selection Operator (Lasso). Our results suggested that the EnRank-detected biomarkers provided useful information from these four feature selection algorithms and achieved very good prediction accuracy in predicting the PH patients. Many of the EnRank-detected biomarkers were also supported by the literature.

show abstract

Section: Methodsmentioning

confidence: 99%

EnRank: An Ensemble Method to Detect Pulmonary Hypertension Biomarkers Based on Feature Selection and Machine Learning Models

Liu¹,

Fu²,

Zhang³

et al. 2021

Front. Genet.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The last step of Crystall further refined the subset of selected features using the BackFS strategy [92]. The first two steps of Crystall eliminated features with small absolute values of the model coefficients, instead of the regression performance metric MAE.…”

Section: Crystall a Feature Selection Algorithm To Estimate Thementioning

confidence: 99%

“…The regression performance metric MAE is used to compare the features selected by Crystall-Step1 and Crystall. The previous studies demonstrated that the module BackFS performs very well on various feature selection problems, but its time complexity is very high [92]. So a wrapper is integrated as the second step of Crystall.…”

Section: E Regression Performance Comparison Of Feature Selection Almentioning

confidence: 99%

Survival Time Prediction of Breast Cancer Patients Using Feature Selection Algorithm Crystall

Liu

Zheng

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Breast cancer is one of main causes of death for women. Most of the existing survival analyses focus on the features' associations with whether the patients may survive five years or not. The personalized question remains largely unresolved about how long a breast cancer patient will live. This study aims to predict the patient-specific survival time of breast cancer patients. It formulates the personalized question into two machine learning problems. The first problem is the binary classification of whether a patient will live longer than five years or not. The second one is to build a regression model to predict the patient's survival time within five years. The methylome of a breast cancer patient is used for the prediction. A new algorithm Crystall is presented to find the methylomic features for this regression model. Our models perform well in the above two problems, and achieve the mean absolute error (MAE) of about 1 month for predicting how long a breast cancer patient will live within five years. The detected biomarker genes demonstrate close connections with breast cancers.

show abstract

“…The parameter k denotes the number of selected features and is a common parameter in all the methods evaluated in this study. There is no fixed procedure in the literature for determining the optimum value of k, but in many research works [48][49][50][51] , it is set to 50 which seems to be satisfactory in many cases. However, we take k in a wider range from 10 and 90 to ensure a fairground for comparison.…”

Section: Datasetsmentioning

confidence: 99%

Dimensionality reduction using singular vectors

Afshar

Usefi

2021

Sci Rep

View full text Add to dashboard Cite

A common problem in machine learning and pattern recognition is the process of identifying the most relevant features, specifically in dealing with high-dimensional datasets in bioinformatics. In this paper, we propose a new feature selection method, called Singular-Vectors Feature Selection (SVFS). Let $$D= [A \mid \mathbf {b}]$$ D = [ A ∣ b ] be a labeled dataset, where $$\mathbf {b}$$ b is the class label and features (attributes) are columns of matrix A. We show that the signature matrix $$S_A=I-A^{\dagger }A$$ S A = I - A † A can be used to partition the columns of A into clusters so that columns in a cluster correlate only with the columns in the same cluster. In the first step, SVFS uses the signature matrix $$S_D$$ S D of D to find the cluster that contains $$\mathbf {b}$$ b . We reduce the size of A by discarding features in the other clusters as irrelevant features. In the next step, SVFS uses the signature matrix $$S_A$$ S A of reduced A to partition the remaining features into clusters and choose the most important features from each cluster. Even though SVFS works perfectly on synthetic datasets, comprehensive experiments on real world benchmark and genomic datasets shows that SVFS exhibits overall superior performance compared to the state-of-the-art feature selection methods in terms of accuracy, running time, and memory usage. A Python implementation of SVFS along with the datasets used in this paper are available at https://github.com/Majid1292/SVFS.

show abstract

AgeGuess, a Methylomic Prediction Model for Human Ages

Cited by 10 publications

References 73 publications

EnRank: An Ensemble Method to Detect Pulmonary Hypertension Biomarkers Based on Feature Selection and Machine Learning Models

EnRank: An Ensemble Method to Detect Pulmonary Hypertension Biomarkers Based on Feature Selection and Machine Learning Models

Survival Time Prediction of Breast Cancer Patients Using Feature Selection Algorithm Crystall

Dimensionality reduction using singular vectors

Contact Info

Product

Resources

About