Regularized Gaussian Mixture Model based discretization for gene expression data association mining

In This work we describe an algorithm for feature selection and gene clustering from high dimensional gene expression data. The method is based on measuring similarity between features/genes whereby redundancy therein is removed. This does not need any search and therefore is fast. A novel feature similarity measure, called maximum information compression index, is used. The feature selection algorithm also obtains gene clusters in a multiscale fashion. The superiority of the algorithm, in terms of speed and performance, is established on a real life molecular cancer classification dataset.

Breast cancer remains a leading cause of mortality among women worldwide, with early and accurate diagnosis being critical for effective treatment. Gene expressionprofiling has emerged as a powerful tool for understanding the molecular mechanisms of cancer and for developing predictive models. However, the high dimensionality and class imbalance inherent in gene expression data pose significant challenges for developing robust predictive models.This study aims to develop and evaluate a predictive model for classifying breast cancer subtypes using high-dimensional gene expression data, addressing the challenges of class imbalance. The objective is to improve the accuracy and reliability of breast cancer subtype prediction to facilitate better diagnostic and treatment strategies.A comprehensive dataset of breast cancer gene expression profiles was utilized, comprising numerous gene expression levels across multiple samples. To address class imbalance, resampling techniques such as Synthetic Minority Over-sampling Technique (SMOTE) and Random Under-sampling, were employed. The machine learning algorithms employed included Support Vector Machines (SVM), Random Forests, and Neural Networks. The algorithms were trained and evaluated using cross-validation to identify the most effective model. The performance of these models was assessed based on metrics such as accuracy, precision, recall, and F1-score. The results indicate that the use of SMOTE in combination with SVM provided the most balanced and accurate predictions, with an F1-score significantly higher than models without resampling. The Random Forest algorithm also showed promising results, particularly in handling the high-dimensionality aspect of the data.The study demonstrates that addressing class imbalance through advanced resampling techniques can significantly enhance the predictive accuracy of models trained on high-dimensional gene expression data. The findings underscore the potential of machine learning models, particularly SVMs and Random Forests, in improving breast cancer subtype classification.

Microarray technology makes it possible to measure expression level of thousands of genes simultaneously in an efficient and inexpensive manner. However, due to various complexities in processing microarrays, expression information of various genes may be missing due to unreliable measurements. The occurrence of missing values in gene expression data can adversely affect downstream analyses such as clustering, dimensionality reduction etc. Different algorithms have been developed to estimate the missing values in different data sets and none of these algorithm works well with all the data sets. In this work, we explore the possible application of Mutual Nearest Neighbor (MNN) algorithm to impute the missing values, which shows comparable results with other well know imputation algorithms. We also have explored five different methods for missing value imputation namely Row Average Imputation, Mean Imputation, Median Imputation, k-Nearest Neighbor Imputation and combination of kNN based feature selection (kNNFS) and kNN-based imputation. The experiments are carried out on very high dimensional gene expression data such as Notterman Carcinoma and Notterman Adenocarcinoma data and the results are illustrated.

The study explores issues related to the treatment of brain cancer caused by the heterogeneous nature of different variants of brain tumors. The objective of this study was to identify essential genes present in multiple types of brain cancer by using high dimensional gene expression data available on the Curated Microarray Database CuMiDa. The study’s dataset comprised a total of 130 samples belonging to 4 subtypes of brain cancer and 16384 gene expression variables. Thus, the penalized Elastic net method in conjunction with Multinomial Logistic Regression was used to cope with curse of dimensionality problems. Then, accuracy, Kappa statistic, Area Under the Curve, and F1-score were utilized to evaluate measures of the model efficiency. Elastic Net proved to be quite effective in the sense of the extensiveness of the variables included in the analysis and successfully restricted gene level further analysis as well as highlighted subtype specific expression signatures. The model achieved high precision and AUC values indicating that in general the model had good ability to distinguish all subtypes with some around perfect score of AUC. Robust parameter estimation was supplemented with cross validation and other predictive model validation statistical techniques done in R language programming. Thus, these findings suggest that the best model for evaluating large-scale gene expression data of brain cancers is the use of MLR with an elastic net regularization. There is ample evidence that these selected genes contribute to and serve as targets for therapy, therefore making this study a good starting point for further investigations with respect to understanding their biological role. The corresponding model is also to be applied to test its validity on some other datasets of a quite different nature. This, in turn, may suggest improved diagnostic, prognostic and therapeutic options for the brain tumor.

Metric trees are designed for improving efficiency of similarity search in high dimensional data. Searching a metric tree always terminates at leaf nodes, restricting the hierarchical search to a certain leaf level, and the linear search in leafs to a particular leaf size. This may result in performing additional unneeded distance comparisons, which increases the search time as the number of dimensions increases. It is proposed that the search adapts itself to the query in question, so as to avoid unneeded distance comparisons. Thus, the hierarchical search should terminate when no more search- space pruning can be useful, and search then continues linearly through the un-pruned data space. Hierarchical search can thus stop any where above or below the original leaf level of a metric tree. Search rules are proposed to adapt the search to the query parameters. A modification to the metric tree is also suggested to adopt the proposed rules. High dimensional gene expression data sets are used to evaluate the new algorithm, showing speed ups of 55% compared to traditional search.

Prediction of hepatotoxicity in humans remains an unresolved challenge. Recently, an in vitro/in silico method was established to predict blood concentrations of test compounds with an increased risk of causing human hepatotoxicity. In the present study, we addressed the question whether gene expression data can improve the quality of hepatotoxicity prediction compared to cytotoxicity analysis alone. A particular challenge is that high-dimensional gene expression data must be sum­marized into variables that allow the determination of the lowest test compound concentration that causes altered gene expression. To address this challenge, we analyzed 60 hepatotoxic and non-hepatotoxic substances in a concentration-dependent manner for cytotoxicity and expression of 3,524 probes previously reported to be influenced by hepatotoxicants. The toxicity separation index (TSI) was applied to quantify how well specific summary variables of gene expression can differen­tiate between the set of hepatotoxic and non-hepatotoxic substances. The best TSI was obtained when the lowest concentration of a test compound that led to differential expression of two genes when compared to vehicle controls was considered positive. Furthermore, the best gene expression-based summary variable was superior to cytotoxicity-based variables alone, and the combination of the best summary variables of gene expression and cytotoxicity data further improved the TSI compared to each category alone. In conclusion, the method used to derive summary variables of gene expression is critical, and the best summary variables improve the prediction of hepatotoxic substances in relation to oral doses and blood concentrations in humans.

Prediction of hepatotoxicity in humans remains an unresolved challenge. Recently, an in vitro/in silico method was established to predict blood concentrations of test compounds with an increased risk of causing human hepatotoxicity. In the present study, we addressed the question whether gene expression data can improve the quality of hepatotoxicity prediction compared to cytotoxicity analysis alone. A particular challenge is that high-dimensional gene expression data must be sum­marized into variables that allow the determination of the lowest test compound concentration that causes altered gene expression. To address this challenge, we analyzed 60 hepatotoxic and non-hepatotoxic substances in a concentration-dependent manner for cytotoxicity and expression of 3,524 probes previously reported to be influenced by hepatotoxicants. The toxicity separation index (TSI) was applied to quantify how well specific summary variables of gene expression can differen­tiate between the set of hepatotoxic and non-hepatotoxic substances. The best TSI was obtained when the lowest concentration of a test compound that led to differential expression of two genes when compared to vehicle controls was considered positive. Furthermore, the best gene expression-based summary variable was superior to cytotoxicity-based variables alone, and the combination of the best summary variables of gene expression and cytotoxicity data further improved the TSI compared to each category alone. In conclusion, the method used to derive summary variables of gene expression is critical, and the best summary variables improve the prediction of hepatotoxic substances in relation to oral doses and blood concentrations in humans. Plain language summary Liver injury is a relevant side effect of many drugs. It represents the most common cause of acute liver failure in Western countries as well as the most common reason for late-stage drug development failure or withdrawal of drugs from the market. We show that a genome-wide gene expression analysis of cultured human hepatocytes exposed to drugs can identify hepatotoxic and non-hepato­toxic substances. To achieve this, we have developed a technique to summarize all gene expression variables to determine the lowest concentration at which a test substance begins to influence gene expression. We find that the cell test must include the highest concentration of the drug that is intended to be reached in the blood of patients at therapeutic doses. This approach can reduce the number of animals needed in pre-clinical safety studies as liver-damaging drug candidates would be detected and eliminated prior to studies in rodents.

<p>Classifying high-dimensional data are a challenging task in data mining. Gene expression data is a type of high-dimensional data that has thousands of features. The study was proposing a method to extract knowledge from high-dimensional gene expression data by selecting features and classifying. Lasso was used for selecting features and the classification and regression tree (CART) algorithm was used to construct the decision tree model. To examine the stability of the lasso decision tree, we performed bootstrap aggregating (Bagging) with 50 replications. The gene expression data used was an ovarian tumor dataset that has 1,545 observations, 10,935 gene features, and binary class. The findings of this research showed that the lasso decision tree could produce an interpretable model that theoretically correct and had an accuracy of 89.32%. Meanwhile, the model obtained from the majority vote gave an accuracy of 90.29% which showed an increase in accuracy of 1% from the single lasso decision tree model. The slightly increasing accuracy shows that the lasso decision tree classifier is stable.</p>

This study investigates the adaptation of DeepInsight for cancer subtype classification using high-dimensional gene expression data. Originally designed for non-image data, DeepInsight has been adapted for cancer classification. We evaluated DeepInsight's performance against several models, including support vector machines, LightGBM, neural networks, and decision trees, with and without the application of the Synthetic Minority Oversampling Technique. The study utilized gene expression data from breast, lung, and colon cancers. A novel multi-class feature selection method was introduced, using modified aggregated class activation maps to identify key genes across different cancer subtypes. These critical genes were further analyzed through Gene Ontology to explore their roles in significant biological processes. DeepInsight consistently outperformed traditional models in terms of F1 score across breast, lung, and colon cancer datasets, effectively addressing multi-class classification challenges. Notably, several top genes were identified as significant across multiple methods. Furthermore, we conducted a Gene Ontology analysis on the critical genes, including the top genes identified by DeepInsight and the common genes recognized through multiple methods. The adaptation of DeepInsight provides an approach to cancer subtype classification by transforming high-dimensional gene expression data into image representations. Utilizing aggregated class activation maps, it effectively identifies critical pixels within these images, enabling the discovery of distinct genes that may not be highlighted by other methods. DeepInsight demonstrates potential as a valuable tool for classifying cancer subtypes and critical genes.

Feature selection becomes a central task when 'signature' profiles specific to a pathological status have to be extracted from high dimensional gene expression or proteomic data. In the present paper, we propose a feature selection method based on Singular Value Decomposition (SVD) and apply it to SELDI-TOF/MS proteomic data from a cohort of Type 2 Diabetics affected by Glomerulosclerosis and Membranous Nephropathy. We have selected a profile composed of 24 proteins that seems to be an effective signature for the pathology at hand, allowing to efficiently discriminate between the considered subtype of diabetes.

If the samples, features and information values in a real-valued information system are cells, genes and gene expression values, respectively, then for convenience, this system is said to be a single cell gene space. In the era of big data, people are faced with high dimensional gene expression data with redundancy and noise causing its strong uncertainty. D-S evidence theory excels at tackling the problem of uncertainty, and its conditions to be met are weaker than Bayesian probability theory. Therefore, this paper studies the gene selection in a single cell gene space to remove noise and redundancy with D-S evidence theory. The distance between two cells in each gene is first defined. Then, the tolerance relation is established according to the defined distance. In addition, the belief and plausibility functions to grasp the uncertainty of a single cell gene space are introduced on the basis of the tolerance classes. Statistical analysis shows that they can effectively measure the uncertainty of a single cell gene space. Furthermore, several gene selection algorithms in a single cell gene space are presented using the proposed belief and plausibility. Finally, the performance of the proposed algorithm is compared to other algorithms on some published single-cell data sets. Experimental results and statistical tests show that the classification and clustering performance of the presented algorithm not only exceeds the other three state-of-the-art algorithms, but also its gene reduction rate is very high.

For high dimensional gene expression data, one important goal is to identify a small number of genes that are associated with progression of the disease or survival of the patients. In this paper, we consider the problem of variable selection for multivariate survival data. We propose an estimation procedure for high dimensional accelerated failure time (AFT) models with bivariate censored data. The method extends the Buckley-James method by minimizing a penalized [Formula: see text] loss function with a penalty function induced from a bivariate spike-and-slab prior specification. In the proposed algorithm, censored observations are imputed using the Kaplan-Meier estimator, which avoids a parametric assumption on the error terms. Our empirical studies demonstrate that the proposed method provides better performance compared to the alternative procedures designed for univariate survival data regardless of whether the true events are correlated or not, and conceptualizes a formal way of handling bivariate survival data for AFT models. Findings from the analysis of a myeloma clinical trial using the proposed method are also presented.

The increasing application of microarray technology is generating large amounts of high dimensional gene expression data. Genes participating in the same biological process tend to have similar expression patterns, and clustering is one of the most useful and efficient methods for identifying these patterns. Due to the complexity of microarray profiles, there are some limitations in directly applying traditional clustering techniques to the microarray data. Recently, researchers have proposed clustering algorithms custom tailored to overcome their limitations for microarray analysis. In this chapter, we first introduce the microarray technique. Next, we review seven representative clustering algorithms: K-means, quality-based clustering, hierarchical agglomerative clustering, self-organizing neural network-based clustering, graph-theory-based clustering, model-based clustering, and subspace clustering. All these algorithms have shown their applicability to the microarray profiles.We also survey several criteria for evaluating clustering results. Biology plays an important role in the evaluation of clustering results. We discuss possible research directions to equip clustering techniques with underlying biological interpretations for better microarray profile analysis.

Feature selection based on sensitivity analysis of fuzzy ISODATA

Autism Spectrum Disorder (ASD) is defined as polygenetic developmental and neurobiological disorders that cover a variety of development delays in social interactions. In recent years, computational methods using gene expression data have been proved to be effective in predicting ASD at the early stage. Feature selection methods directly affect the prediction performance of the ASD prognosis methods. With the advances of computational methods and exploding of high-dimensional ASD gene expression data, there is a need to examine the performance of different computational techniques in predicting ASD. In this paper, we review and conduct a comparison study of 22 different feature selection methods for predicting ASD from gene expression data. The methods are categorised into traditional methods (14 methods) and network-based methods (8 methods). The experimental results have shown that the network-based methods generally outperform the traditional feature selection methods in all three accuracy measures, including AUC (area under the curve), F1-score, and Matthews Correlation Coefficient.