Robust proportional overlapping analysis for feature selection in binary classification within functional genomic experiments

Modified Robust Proportional Overlapping Score for feature selection in high-dimensional micro-array data

High-dimensional microarray datasets often contain tens of thousands of genes but only a small number of samples, typically ranging from tens to a few hundred. This imbalance, known as the curse of dimensionality or the n ≪ p problem, hampers the learning process. To address this issue, this study introduces the Modified Robust Proportional Overlapping Score (MRPOS), an enhanced feature selection method based on robust measures of dispersion, specifically the Sn and Qn statistics by Rousseeuw and Croux. MRPOS identifies discriminative genes in binary class problems by evaluating gene expression overlap. This study considers the four gene expression datasets, each divided into two parts: a training subset covering 70 % of the data and a testing subset holding the remaining 30 %. The MRPOS eliminates genes with high inter-class similarity while retaining those differentiating classes. The method's performance is assessed against four established feature selection techniques using classification error rates from four gene expression datasets. Three classifiers, random forest, k-nearest neighbor (k-NN), and support vector machine (SVM), are employed, with results visualized through bar plots of classification errors. The findings highlight the distinctiveness and effectiveness of the proposed method.

Raman spectral pattern recognition of breast cancer: A machine learning strategy based on feature fusion and adaptive hyperparameter optimization

Raman spectroscopy, as a kind of molecular vibration spectroscopy, provides abundant information for measuring components and molecular structure in the early detection and diagnosis of breast cancer. Currently, portable Raman spectrometers have simplified and made equipment application more affordable, albeit at the cost of sacrificing the signal-to-noise ratio (SNR). Consequently, this necessitates a higher recognition rate from pattern recognition algorithms. Our study employs a feature fusion strategy to reduce the dimensionality of high-dimensional Raman spectra and enhance the discriminative information between normal tissues and tumors. In the conducted random experiment, the classifier achieved a performance of over 96% for all three average metrics: accuracy, sensitivity, and specificity. Additionally, we propose a multi-parameter serial encoding evolutionary algorithm (MSEA) and integrate it into the Adaptive Local Hyperplane K-nearest Neighbor classification algorithm (ALHK) for adaptive hyperparameter optimization. The implementation of serial encoding tackles the predicament of parallel optimization in multi-hyperparameter vector problems. To bolster the convergence of the optimization algorithm towards a global optimal solution, an exponential viability function is devised for nonlinear processing. Moreover, an improved elitist strategy is employed for individual selection, effectively eliminating the influence of probability factors on the robustness of the optimization algorithm. This study further optimizes the hyperparameter space through sensitivity analysis of hyperparameters and cross-validation experiments, leading to superior performance compared to the ALHK algorithm with manual hyperparameter configuration.

Feature selection for high dimensional microarray gene expression data via weighted signal to noise ratio

Feature selection in high dimensional gene expression datasets not only reduces the dimension of the data, but also the execution time and computational cost of the underlying classifier. The current study introduces a novel feature selection method called weighted signal to noise ratio (WSNR) by exploiting the weights of features based on support vectors and signal to noise ratio, with an objective to identify the most informative genes in high dimensional classification problems. The combination of two state-of-the-art procedures enables the extration of the most informative genes. The corresponding weights of these procedures are then multiplied and arranged in decreasing order. Larger weight of a feature indicates its discriminatory power in classifying the tissue samples to their true classes. The current method is validated on eight gene expression datasets. Moreover, results of the proposed method (WSNR) are also compared with four well known feature selection methods. We found that the (WSNR) outperform the other competing methods on 6 out of 8 datasets. Box-plots and Bar-plots of the results of the proposed method and all the other methods are also constructed. The proposed method is further assessed on simulated data. Simulation analysis reveal that (WSNR) outperforms all the other methods included in the study.

VSOLassoBag: a variable-selection oriented LASSO bagging algorithm for biomarker discovery in omic-based translational research

Screening biomolecular markers from high-dimensional biological data is one of the long-standing tasks for biomedical translational research. With its advantages in both feature shrinkage and biological interpretability, Least Absolute Shrinkage and Selection Operator (LASSO) algorithm is one of the most popular methods for the scenarios of clinical biomarker development. However, in practice, applying LASSO on omics-based data with high dimensions and low-sample size may usually result in an excess number of predictive variables, leading to the overfitting of the model. Here, we present VSOLassoBag, a wrapped LASSO approach by integrating an ensemble learning strategy to help select efficient and stable variables with high confidence from omics-based data. Using a bagging strategy in combination with a parametric method or inflection point search method, VSOLassoBag can integrate and vote variables generated from multiple LASSO models to determine the optimal candidates. The application of VSOLassoBag on both simulation datasets and real-world datasets shows that the algorithm can effectively identify markers for either case-control binary classification or prognosis prediction. In addition, by comparing with multiple existing algorithms, VSOLassoBag shows a comparable performance under different scenarios while resulting in fewer features than others. In summary, VSOLassoBag, which is available at https://seqworld.com/VSOLassoBag/ under the GPL v3 license, provides an alternative strategy for selecting reliable biomarkers from high-dimensional omics data. For user's convenience, we implement VSOLassoBag as an R package that provides multithreading computing configurations.

An Efficient AP-ANN-Based Multimethod Fusion Model to Detect Stress through EEG Signal Analysis

Stress is a universal emotion that every human experiences daily. Psychologists say stress may lead to heart attack, depression, hypertension, strokes, or even sudden death. Many technical explorations like stress detection through facial expression, speech, text, physical behaviors, etc., were explored, but no consensus has been reached on the best method. The advancement in biomedical engineering yielded a rapid development of electroencephalogram (EEG) signal analysis that has inspired the idea of a multimethod fusion approach for the first time which employs multiple techniques such as discrete wavelet transform (DWT) for de-noising, adaptive synthetic sampling (ADASYN) for class balancing, and affinity propagation (AP) as a stratified sampling model along with the artificial neural network (ANN) as the classifier model for human emotion classification. From the EEG recordings of the DEAP dataset, the artifacts are removed, the signal is decomposed using a DWT, and features are extracted and fused to form the feature vector. As the dataset is high-dimensional, feature selection is done and ADASYN is used to address the imbalance of classes resulting in large-scale data. The innovative idea of the proposed system is to perform sampling using affinity propagation as a stratified sampling-based clustering algorithm as it determines the number of representative samples automatically which makes it superior to the K-Means, K-Medoid, that requires the K-value. Those samples are used as inputs to various classification models, the comparison of the AP-ANN, AP-SVM, and AP-RF is done, and their most important five performance metrics such as accuracy, precision, recall, F1-score, and specificity were compared. From our experiment, the AP-ANN model provides better accuracy of 86.8% and greater precision of 85.7%, a higher F1 score of 84.9%, a recall rate of 84.1%, and a specificity value of 89.2% which altogether provides better results than the other existing algorithms.