Gene selection from microarray data for cancer classification--a machine learning approach

A DNA microarray can track the expression levels of thousands of genes simultaneously. Previous research has demonstrated that this technology can be useful in the classification of cancers. Cancer microarray data normally contains a small number of samples which have a large number of gene expression levels as features. To select relevant genes involved in different types of cancer remains a challenge. In order to extract useful gene information from cancer microarray data and reduce dimensionality, feature selection algorithms were systematically investigated in this study. Using a correlation-based feature selector combined with machine learning algorithms such as decision trees, nave Bayes and support vector machines, we show that classification performance at least as good as published results can be obtained on acute leukemia and diffuse large B-cell lymphoma microarray data sets. We also demonstrate that a combined use of different classification and feature selection approaches makes it possible to select relevant genes with high confidence. This is also the first paper which discusses both computational and biological evidence for the involvement of zyxin in leukaemogenesis.     

Classification of highly unbalanced CYP450 data of drugs using cost sensitive machine learning techniques

In this paper, we study the classifications of unbalanced data sets of drugs. As an example we chose a data set of 2D6 inhibitors of cytochrome P450. The human cytochrome P450 2D6 isoform plays a key role in the metabolism of many drugs in the preclinical drug discovery process. We have collected a data set from annotated public data and calculated physicochemical properties with chemoinformatics methods. On top of this data, we have built classifiers based on machine learning methods. Data sets with different class distributions lead to the effect that conventional machine learning methods are biased toward the larger class. To overcome this problem and to obtain sensitive but also accurate classifiers we combine machine learning and feature selection methods with techniques addressing the problem of unbalanced classification, such as oversampling and threshold moving. We have used our own implementation of a support vector machine algorithm as well as the maximum entropy method. Our feature selection is based on the unsupervised McCabe method. The classification results from our test set are compared structurally with compounds from the training set. We show that the applied algorithms enable the effective high throughput in silico classification of potential drug candidates.     

Application of comprehensive two-dimensional gas chromatography mass spectrometry and different types of data analysis for the investigation of cigarette particulate matter

In tobacco research, the comparison of different tobacco blends as well as the puff-dependent behaviour of cigarettes is a matter of particular interest. For the investigation of smoke characteristics, GC x GC offers different ways for data analysis, namely, compound target analysis, automated peak-based compound classification and comprehensive pixel-based data analysis. This study will show the application as well as the pros and cons of these types of data analysis for very complex matrices like cigarette particulate matter. In addition, new aspects about the recently discovered puff-dependent behaviour of compounds in cigarette smoke will be presented. Automated peak-based compound classification including mass spectrometric pattern recognition is used for the classification of tobacco particulate matter samples and the puff-dependent investigation of different compound classes. This compound group specific analysis is further reinforced by applying an even more comprehensive pixel-based analysis. This kind of analysis is used to generate fingerprints of different types of cigarettes. The combination of fast feature reduction methods like analysis of variance (ANOVA) and t-test with multivariate feature transformation methods like partial least squares discriminate analysis (PLSDA) for feature selection provides a powerful tool for a detailed inspection of different types of cigarettes.     

Feature selection for descriptor based classification models. 1. Theory and GA-SEC algorithm

The paper describes different aspects of classification models based on molecular data sets with the focus on feature selection methods. Especially model quality and avoiding a high variance on unseen data (overfitting) will be discussed with respect to the feature selection problem. We present several standard approaches and modifications of our Genetic Algorithm based on the Shannon Entropy Cliques (GA-SEC) algorithm and the extension for classification problems using boosting.     

Improved binary PSO for feature selection using gene expression data

Gene expression profiles, which represent the state of a cell at a molecular level, have great potential as a medical diagnosis tool. Compared to the number of genes involved, available training data sets generally have a fairly small sample size in cancer type classification. These training data limitations constitute a challenge to certain classification methodologies. A reliable selection method for genes relevant for sample classification is needed in order to speed up the processing rate, decrease the predictive error rate, and to avoid incomprehensibility due to the large number of genes investigated. Improved binary particle swarm optimization (IBPSO) is used in this study to implement feature selection, and the K-nearest neighbor (K-NN) method serves as an evaluator of the IBPSO for gene expression data classification problems. Experimental results show that this method effectively simplifies feature selection and reduces the total number of features needed. The classification accuracy obtained by the proposed method has the highest classification accuracy in nine of the 11 gene expression data test problems, and is comparative to the classification accuracy of the two other test problems, as compared to the best results previously published.     

Information-theoretic approaches to SVM feature selection for metagenome read classification

Analysis of DNA sequences isolated directly from the environment, known as metagenomics, produces a large quantity of genome fragments that need to be classified into specific taxa. Most composition-based classification methods use all features instead of a subset of features that may maximize classifier accuracy. We show that feature selection methods can boost performance of taxonomic classifiers. This work proposes three different filter-based feature selection methods that stem from information theory: (1) a technique that combines Kullback-Leibler, Mutual Information, and distance information, (2) a text mining technique, TF-IDF, and (3) minimum redundancy-maximum-relevance (mRMR). The feature selection methods are compared by how well they improve support vector machine classification of genomic reads. Overall, the 6mer mRMR method performs well, especially on the phyla-level. If the number of total features is very large, feature selection becomes difficult because a small subset of features that captures a majority of the data variance is less likely to exist. Therefore, we conclude that there is a trade-off between feature set size and feature selection method to optimize classification performance. For larger feature set sizes, TF-IDF works better for finer-resolutions while mRMR performs the best out of any method for N=6 for all taxonomic levels.     

A novel divide-and-merge classification for high dimensional datasets

High dimensional datasets contain up to thousands of features, and can result in immense computational costs for classification tasks. Therefore, these datasets need a feature selection step before the classification process. The main idea behind feature selection is to choose a useful subset of features to significantly improve the comprehensibility of a classifier and maximize the performance of a classification algorithm. In this paper, we propose a one-per-class model for high dimensional datasets. In the proposed method, we extract different feature subsets for each class in a dataset and apply the classification process on the multiple feature subsets. Finally, we merge the prediction results of the feature subsets and determine the final class label of an unknown instance data. The originality of the proposed model is to use appropriate feature subsets for each class. To show the usefulness of the proposed approach, we have developed an application method following the proposed model. From our results, we confirm that our method produces higher classification accuracy than previous novel feature selection and classification methods.     

近红外光谱技术结合主成分分析法用于子宫内膜癌的诊断

应用近红外光谱技术结合化学计量学方法研究了子宫内膜癌组织近红外光谱特征提取和早期诊断的可行性. 测定了154 例子宫内膜组织切片的近红外光谱, 选取适宜的波段和光谱预处理方法进行主成分分析, 很好地区分了癌变、增生和正常子宫内膜组织切片, 并且分辨出处于不同分化期的组织切片, 为子宫内膜癌的早期诊断提供了可靠依据. 该法快速、简便, 有望发展成为一种新型的肿瘤无创诊断方法.     

Data analysis for electronic nose systems

Electronic noses (e-noses) employ an array of chemical gas sensors and have been widely used for the analysis of volatile organic compounds. Pattern recognition provides a higher degree of selectivity and reversibility to the systems leading to an extensive range of applications. These range from the food and medical industry to environmental monitoring and process control. Many types of data analysis techniques have been used on the data produced. This review covers aspects of analysis from data normalisation methods to pattern recognition and classification techniques. An overview of data visualisation such as non-linear mapping and multivariate statistical techniques is given. Focus is then on the use of artificial intelligence techniques such as neural networks and fuzzy logic for classification and genetic algorithms for feature (sensor) selection. Application areas are covered with examples of the types of systems and analysis methods currently in use. Future trends in the analysis of sensor array data are discussed.     

Informatics for cross-sample analysis with comprehensive two-dimensional gas chromatography and high-resolution mass spectrometry (GCxGC-HRMS)

This paper describes informatics for cross-sample analysis with comprehensive two-dimensional gas chromatography (GCxGC) and high-resolution mass spectrometry (HRMS). GCxGC-HRMS analysis produces large data sets that are rich with information, but highly complex. The size of the data and volume of information requires automated processing for comprehensive cross-sample analysis, but the complexity poses a challenge for developing robust methods. The approach developed here analyzes GCxGC-HRMS data from multiple samples to extract a feature template that comprehensively captures the pattern of peaks detected in the retention-times plane. Then, for each sample chromatogram, the template is geometrically transformed to align with the detected peak pattern and generate a set of feature measurements for cross-sample analyses such as sample classification and biomarker discovery. The approach avoids the intractable problem of comprehensive peak matching by using a few reliable peaks for alignment and peak-based retention-plane windows to define comprehensive features that can be reliably matched for cross-sample analysis. The informatics are demonstrated with a set of 18 samples from breast-cancer tumors, each from different individuals, six each for Grades 1-3. The features allow classification that matches grading by a cancer pathologist with 78% success in leave-one-out cross-validation experiments. The HRMS signatures of the features of interest can be examined for determining elemental compositions and identifying compounds.     

A L1-regularized feature selection method for local dimension reduction on microarray data

Dimension reduction is a crucial technique in machine learning and data mining, which is widely used in areas of medicine, bioinformatics and genetics. In this paper, we propose a two-stage local dimension reduction approach for classification on microarray data. In first stage, a new L1-regularized feature selection method is defined to remove irrelevant and redundant features and to select the important features (biomarkers). In the next stage, PLS-based feature extraction is implemented on the selected features to extract synthesis features that best reflect discriminating characteristics for classification. The suitability of the proposal is demonstrated in an empirical study done with ten widely used microarray datasets, and the results show its effectiveness and competitiveness compared with four state-of-the-art methods. The experimental results on St Jude dataset shows that our method can be effectively applied to microarray data analysis for subtype prediction and the discovery of gene coexpression.     

Classification of Rat FTIR Colon Cancer Data Using Waveletsand BPNN

本文提出了一种新的基于水平衰减全反射-傅里叶变换红外光谱（HATR-FTIR）的小波特征提取与反向传播人工神经网络模式分类方法以提高FTIR对早期大鼠结肠癌的诊断准确率．对60只DMH诱导的SD大鼠,44只诱导鼠的第二代鼠,36只正常SD大鼠的结肠正常组织、异常增生、早癌及进展期癌组织所获得的的HATR-FTIR,利用连续小波多尺度分析法提取12个特征量,采用反向传播人工神经网络进行分类,识别准确率分别为100%、94%、97.5%及100%．实验结果表明此方法对早期结肠癌具有较高的诊断率．     

Predicting experimental properties of proteins from sequence by machine learning techniques

Efficient target selection methods are an important prerequisite for increasing the success rate and reducing the cost of high-throughput structural genomics efforts. There is a high demand for sequence-based methods capable of predicting experimentally tractable proteins and filtering out potentially difficult targets at different stages of the structural genomic pipeline. Simple empirical rules based on anecdotal evidence are being increasingly superseded by rigorous machine-learning algorithms. Although the simplicity of less advanced methods makes them more human understandable, more sophisticated formalized algorithms possess superior classification power. The quickly growing corpus of experimental success and failure data gathered by structural genomics consortia creates a unique opportunity for retrospective data mining using machine learning techniques and results in increased quality of classifiers. For example, the current solubility prediction methods are reaching the accuracy of over 70%. Furthermore, automated feature selection leads to better insight into the nature of the correlation between amino acid sequence and experimental outcome. In this review we summarize methods for predicting experimental success in cloning, expression, soluble expression, purification and crystallization of proteins with a special focus on publicly available resources. We also describe experimental data repositories and machine learning techniques used for classification and feature selection.     

Swarm intelligence based wavelet coefficient feature selection for mass spectral classification: An application to proteomics data

This paper introduces the ant colony algorithm, a novel swarm intelligence based optimization method, to select appropriate wavelet coefficients from mass spectral data as a new feature selection method for ovarian cancer diagnostics. By determining the proper parameters for the ant colony algorithm (ACA) based searching algorithm, we perform the feature searching process for 100 times with the number of selected features fixed at 5. The results of this study show: (1) the classification accuracy based on the five selected wavelet coefficients can reach up to 100% for all the training, validating and independent testing sets; (2) the eight most popular selected wavelet coefficients of the 100 runs can provide 100% accuracy for the training set, 100% accuracy for the validating set, and 98.8% accuracy for the independent testing set, which suggests the robustness and accuracy of the proposed feature selection method; and (3) the mass spectral data corresponding to the eight popular wavelet coefficients can be located by reverse wavelet transformation and these located mass spectral data still maintain high classification accuracies (100% for the training set, 97.6% for the validating set, and 98.8% for the testing set) and also provide sufficient physical and medical meaning for future ovarian cancer mechanism studies. Furthermore, the corresponding mass spectral data (potential biomarkers) are in good agreement with other studies which have used the same sample set. Together these results suggest this feature extraction strategy will benefit the development of intelligent and real-time spectroscopy instrumentation based diagnosis and monitoring systems.     

Two-dimensional linear discriminant analysis for classification of three-way chemical data

The two-dimensional linear discriminant analysis (2D-LDA) algorithm was originally proposed in the context of face image processing for the extraction of features with maximal discriminant power. However, despite its promising performance in image processing tasks, the 2D-LDA algorithm has not yet been used in applications involving chemical data. The present paper bridges this gap by investigating the use of 2D-LDA in classification problems involving three-way spectral data. The investigation was concerned with simulated data, as well as real-life data sets involving the classification of dry-cured Parma ham according to ageing by surface autofluorescence spectrometry and the classification of edible vegetable oils according to feedstock using total synchronous fluorescence spectrometry. The results were compared with those obtained by using the spectral data with no feature extraction, U-PLS-DA (Partial Least Squares Discriminant Analysis applied to the unfolded data), and LDA employing TUCKER-3 or PARAFAC scores. In the simulated data set, all methods yielded a correct classification rate of 100%. However, in the Parma ham and vegetable oil data sets, better classification rates were obtained by using 2D-LDA (86% and 100%), compared with no feature extraction (76% and 77%), U-PLS-DA (81% and 92%), PARAFAC-LDA (76% and 86%) and TUCKER3-LDA (86% and 93%).     

Two-dimensional wavelet analysis based classification of gas chromatogram differential mobility spectrometry signals

This study introduces two-dimensional (2-D) wavelet analysis to the classification of gas chromatogram differential mobility spectrometry (GC/DMS) data which are composed of retention time, compensation voltage, and corresponding intensities. One reported method to process such large data sets is to convert 2-D signals to 1-D signals by summing intensities either across retention time or compensation voltage, but it can lose important signal information in one data dimension. A 2-D wavelet analysis approach keeps the 2-D structure of original signals, while significantly reducing data size. We applied this feature extraction method to 2-D GC/DMS signals measured from control and disordered fruit and then employed two typical classification algorithms to testify the effects of the resultant features on chemical pattern recognition. Yielding a 93.3% accuracy of separating data from control and disordered fruit samples, 2-D wavelet analysis not only proves its feasibility to extract feature from original 2-D signals but also shows its superiority over the conventional feature extraction methods including converting 2-D to 1-D and selecting distinguishable pixels from training set. Furthermore, this process does not require coupling with specific pattern recognition methods, which may help ensure wide applications of this method to 2-D spectrometry data.     

A tutorial on support vector machine-based methods for classification problems in chemometrics

This tutorial provides a concise overview of support vector machines and different closely related techniques for pattern classification. The tutorial starts with the formulation of support vector machines for classification. The method of least squares support vector machines is explained. Approaches to retrieve a probabilistic interpretation are covered and it is explained how the binary classification techniques can be extended to multi-class methods. Kernel logistic regression, which is closely related to iteratively weighted least squares support vector machines, is discussed. Different practical aspects of these methods are addressed: the issue of feature selection, parameter tuning, unbalanced data sets, model evaluation and statistical comparison. The different concepts are illustrated on three real-life applications in the field of metabolomics, genetics and proteomics.     

Taxonomy dimension reduction for colorectal cancer prediction

A growing number of people suffer from colorectal cancer, which is one of the most common cancers. It is essential to diagnose and treat the cancer as early as possible. The disease may change the microorganism communities in the gut, and it could be an efficient method to employ gut microorganisms to predict colorectal cancer. In this study, we selected operational taxonomic units that include several kinds of microorganisms to predict colorectal cancer. To find the most important microorganisms and obtain the best prediction performance, we explore effective feature selection methods. We employ three main steps. First, we use a single method to reduce features. Next, to reduce the number of features, we integrate the dimension reduction methods correlation-based feature selection and maximum relevance–maximum distance (MRMD 1.0 and MRMD 2.0). Then, we selected the important features according to the taxonomy files. In this study, we created training and test sets to obtain a more objective evaluation. Random forest, naïve Bayes, and decision tree classifiers were evaluated. The results show that the methods proposed in this study are better than hierarchical feature engineering. The proposed method, which combines correlation-based feature selection with MRMD 2.0, performed the best on the CRC2 dataset. The dataset and methods can be found in http://lab.malab.cn/data/microdata/data.html.     

Compact cancer biomarkers discovery using a swarm intelligence feature selection algorithm

Biomarker discovery is a typical application from functional genomics. Due to the large number of genes studied simultaneously in microarray data, feature selection is a key step. Swarm intelligence has emerged as a solution for the feature selection problem. However, swarm intelligence settings for feature selection fail to select small features subsets. We have proposed a swarm intelligence feature selection algorithm based on the initialization and update of only a subset of particles in the swarm. In this study, we tested our algorithm in 11 microarray datasets for brain, leukemia, lung, prostate, and others. We show that the proposed swarm intelligence algorithm successfully increase the classification accuracy and decrease the number of selected features compared to other swarm intelligence methods.     

Detection of non‐small cell lung cancer cells based on microfluidic polarization microscopic image analysis

In early diagnosis of lung cancer, a polarization microscopy is a powerful tool to obtain the optical information of biological tissues. In this paper, a new microfluidic polarization imaging and analysis method was proposed for the detection and classification of cancer‐associated fibroblasts and the two kinds of non‐small cell lung cancer cells, A549 and H322. A polarizing microscopy system was constructed based on a commercial microscope to obtain 3*3 Mueller matrix of cells. Based on the Muller matrix decomposition algorithm and analysis in spatial domain and frequency domain, appropriate classification parameters were selected for the characterization of different polarization characteristics of cells. Finally, the logistic regression models based on machine learning were applied to determine optimal feature parameters and classify cells. This method integrated the morphological information of the cells, and the polarization characteristics of the cells in different polarization states. It is for the first time that the polarization microscopic image analysis method has been applied to the detection and classification of non‐small cell lung cancer cells. The results show that the presented microfluidic polarization microscopic image analysis method could classify cells effectively. Compared with the Muller matrix measurement and calculation methods, the method proposed in this paper was greatly simplified in both the acquisition of polarized images and the analysis and processing of polarized images.