Blind source separation and the analysis of microarray data.

We develop an approach for the exploratory analysis of gene expression data, based upon blind source separation techniques. This approach exploits higher-order statistics to identify a linear model for (logarithms of) expression profiles, described as linear combinations of "independent sources." As a result, it yields "elementary expression patterns" (the "sources"), which may be interpreted as potential regulation pathways. Further analysis of the so-obtained sources show that they are generally characterized by a small number of specific coexpressed or antiexpressed genes. In addition, the projections of the expression profiles onto the estimated sources often provides significant clustering of conditions. The algorithm relies on a large number of runs of "independent component analysis" with random initializations, followed by a search of "consensus sources." It then provides estimates for independent sources, together with an assessment of their robustness. The results obtained on two datasets (namely, breast cancer data and Bacillus subtilis sulfur metabolism data) show that some of the obtained gene families correspond to well known families of coregulated genes, which validates the proposed approach.     

Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis

 In many applications of signal processing, especially in communications and biomedicine, preprocessing is necessary to remove noise from data recorded by multiple sensors. Typically, each sensor or electrode measures the noisy mixture of original source signals. In this paper a noise reduction technique using independent component analysis (ICA) and subspace filtering is presented. In this approach we apply subspace filtering not to the observed raw data but to a demixed version of these data obtained by ICA. Finite impulse response filters are employed whose vectors are parameters estimated based on signal subspace extraction. ICA allows us to filter independent components. After the noise is removed we reconstruct the enhanced independent components to obtain clean original signals; i.e., we project the data to sensor level. Simulations as well as real application results for EEG-signal noise elimination are included to show the validity and effectiveness of the proposed approach. Received: 6 November 2000 / Accepted in revised form: 12 November 2001     

Blind source separation methods for deconvolution of complex signals in cancer biology

Two blind source separation methods (Independent Component Analysis and Non-negative Matrix Factorization), developed initially for signal processing in engineering, found recently a number of applications in analysis of large-scale data in molecular biology. In this short review, we present the common idea behind these methods, describe ways of implementing and applying them and point out to the advantages compared to more traditional statistical approaches. We focus more specifically on the analysis of gene expression in cancer. The review is finalized by listing available software implementations for the methods described.     

Effects of dipole position,orientation and noise on the accuracy of EEG source localization

Background  

The electroencephalogram (EEG) reflects the electrical activity in the brain on the surface of scalp. A major challenge in this field is the localization of sources in the brain responsible for eliciting the EEG signal measured at the scalp. In order to estimate the location of these sources, one must correctly model the sources, i.e., dipoles, as well as the volume conductor in which the resulting currents flow. In this study, we investigate the effects of dipole depth and orientation on source localization with varying sets of simulated random noise in 4 realistic head models.     

A new method for the extraction of fetal ECG from the dependent abdominal signals using blind source separation and adaptive noise cancellation techniques

Background

The electrocardiogram (ECG) is a diagnostic tool that records the electrical activity of the heart, and depicts it as a series of graph-like tracings, or waves. Being able to interpret these details allows diagnosis of a wide range of heart problems. Fetal electrocardiogram (FECG) extraction has an important impact in medical diagnostics during the mother pregnancy period. Since the observed FECG signals are often mixed with the maternal ECG (MECG) and the noise induced by the movement of electrodes or by mother motion, the separation process of the ECG signal sources from the observed data becomes quite complicated. One of its complexity is when the ECG sources are dependent, thus, in this paper we introduce a new approach of blind source separation (BSS) in the noisy context for both independent and dependent ECG signal source. This approach consist in denoising the observed ECG signals using a bilateral total variation (BTV) filter; then minimizing the Kullbak-Leibler divergence between copula densities to separate the FECG signal from the MECG one.

Results

We present simulation results illustrating the performance of our proposed method. We will consider many examples of independent/dependent source component signals. The results will be compared with those of the classical method called independent component analysis (ICA) under the same conditions. The accuracy of source estimation is evaluated through a criterion, called again the signal-to-noise-ratio (SNR). The first experiment shows that our proposed method gives accurate estimation of sources in the standard case of independent components, with performance around 27 dB in term of SNR. In the second experiment, we show the capability of the proposed algorithm to successfully separate two noisy mixtures of dependent source components - with classical criterion devoted to the independent case - fails, and that our method is able to deal with the dependent case with good performance.

Conclusions

In this work, we focus specifically on the separation of the ECG signal sources taken from skin two electrodes located on a pregnant woman’s body. The ECG separation is interpreted as a noisy linear BSS problem with instantaneous mixtures. Firstly, a denoising step is required to reduce the noise due to motion artifacts using a BTV filter as a very effective one-pass filter for denoising. Then, we use the Kullbak-Leibler divergence between copula densities to separate the fetal heart rate from the mother one, for both independent and dependent cases.

     

Advances in blind source separation (BSS) and independent component analysis (ICA) for nonlinear mixtures

In this paper, we review recent advances in blind source separation (BSS) and independent component analysis (ICA) for nonlinear mixing models. After a general introduction to BSS and ICA, we discuss in more detail uniqueness and separability issues, presenting some new results. A fundamental difficulty in the nonlinear BSS problem and even more so in the nonlinear ICA problem is that they provide non-unique solutions without extra constraints, which are often implemented by using a suitable regularization. In this paper, we explore two possible approaches. The first one is based on structural constraints. Especially, post-nonlinear mixtures are an important special case, where a nonlinearity is applied to linear mixtures. For such mixtures, the ambiguities are essentially the same as for the linear ICA or BSS problems. The second approach uses Bayesian inference methods for estimating the best statistical parameters, under almost unconstrained models in which priors can be easily added. In the later part of this paper, various separation techniques proposed for post-nonlinear mixtures and general nonlinear mixtures are reviewed.     

Complex networks and deep learning for EEG signal analysis

Electroencephalogram (EEG) signals acquired from brain can provide an effective representation of the human’s physiological and pathological states. Up to now, much work has been conducted to study and analyze the EEG signals, aiming at spying the current states or the evolution characteristics of the complex brain system. Considering the complex interactions between different structural and functional brain regions, brain network has received a lot of attention and has made great progress in brain mechanism research. In addition, characterized by autonomous, multi-layer and diversified feature extraction, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, including brain state research. Both of them show strong ability in EEG signal analysis, but the combination of these two theories to solve the difficult classification problems based on EEG signals is still in its infancy. We here review the application of these two theories in EEG signal research, mainly involving brain–computer interface, neurological disorders and cognitive analysis. Furthermore, we also develop a framework combining recurrence plots and convolutional neural network to achieve fatigue driving recognition. The results demonstrate that complex networks and deep learning can effectively implement functional complementarity for better feature extraction and classification, especially in EEG signal analysis.     

Comparative analysis of changes in short EEG segments during music perception based on event-related synchronization/desynchronization and wavelet synchronicity

The goal of the pilot study was to analyze the characteristics of changes in short EEG segments recorded from 32 sites during perception of musical melodies by healthy subjects depending on logical (recognition) and emotional (pleasant/unpleasant) estimation of the melody. For this purpose, the changes in event-related synchronization/desynchronization and the indices of wavelet synchrony of EEG responses were compared in 31 healthy subjects (18 to 60 years old). It has been shown that melody recognition during logical estimation of music is accompanied by event-related desynchronization in the left frontal-parietal-temporal area. Emotional estimation of a melody is characterized by event-related synchronization in the left frontal-temporal area for pleasant melodies, desynchronization in the temporal area for unpleasant melodies, and desynchronization in the occipital area for melodies inducing no emotional response. The analysis of EEG wavelet synchronization characterizing reactive changes in the interaction between cortical areas shows that the most distinct topographic differences are associated with the type of music processing: logical (familiar/unfamiliar) or emotional (pleasant/unpleasant). The changes in interhemispheric connections between the associative cortical areas (central, frontal, temporal) are greater during emotional estimation, while the changes in inter- and intrahemispheric connections between the projection areas of the acoustic analyzer (temporal area) are greater during logical estimation. It is assumed that the revealed event-related synchronization/desynchronization is most likely to reflect the activation component of musical fragment estimation, whereas wavelet analysis provides insight into the character of musical stimulus processing.     

Efficiency of neural transmission as a function of synaptic noise, threshold, and source characteristics

There has been a growing interest in the estimation of information carried by a single neuron and multiple single units or population of neurons to specific stimuli. In this paper we analyze, inspired by article of Levy and Baxter (2002), the efficiency of a neuronal communication by considering dendrosomatic summation as a Shannon-type channel (1948) and by considering such uncertain synaptic transmission as part of the dendrosomatic computation. Specifically, we study Mutual Information between input and output signals for different types of neuronal network architectures by applying efficient entropy estimators. We analyze the influence of the following quantities affecting transmission abilities of neurons: synaptic failure, activation threshold, firing rate and type of the input source. We observed a number of surprising non-intuitive effects. It turns out that, especially for lower activation thresholds, significant synaptic noise can lead even to twofold increase of the transmission efficiency. Moreover, the efficiency turns out to be a non-monotonic function of the activation threshold. We find a universal value of threshold for which a local maximum of Mutual Information is achieved for most of the neuronal architectures, regardless of the type of the source (correlated and non-correlated). Additionally, to reach the global maximum the optimal firing rates must increase with the threshold. This effect is particularly visible for lower firing rates. For higher firing rates the influence of synaptic noise on the transmission efficiency is more advantageous. Noise is an inherent component of communication in biological systems, hence, based on our analysis, we conjecture that the neuronal architecture was adjusted to make more effective use of this attribute.     

Multivariate denoising methods combining wavelets and principal component analysis for mass spectrometry data

The identification of new diagnostic or prognostic biomarkers is one of the main aims of clinical cancer research. In recent years, there has been a growing interest in using mass spectrometry for the detection of such biomarkers. The MS signal resulting from MALDI‐TOF measurements is contaminated by different sources of technical variations that can be removed by a prior pre‐processing step. In particular, denoising makes it possible to remove the random noise contained in the signal. Wavelet methodology associated with thresholding is usually used for this purpose. In this study, we adapted two multivariate denoising methods that combine wavelets and PCA to MS data. The objective was to obtain better denoising of the data so as to extract the meaningful proteomic biological information from the raw spectra and reach meaningful clinical conclusions. The proposed methods were evaluated and compared with the classical soft thresholding denoising method using both real and simulated data sets. It was shown that taking into account common structures of the signals by adding a dimension reduction step on approximation coefficients through PCA provided more effective denoising when combined with soft thresholding on detail coefficients.     

Fourier and wavelet transform analysis, a tool for visualizing regular patterns in DNA sequences

A correlation function that compares each base in a DNA sequence to its various neighbours and which is subsequently processed by Fourier and wavelet transforms has been developed. The procedure has been applied to sequences from the human chromosome 22, to nef genes from various HIV clones and to myosin heavy chain DNA. It permits to readily visualize regular features in DNA which are related to the stability of heteroduplexes formed upon strand slippage.     

复杂疾病驱使的融合SDA-SVM集成基因挖掘方法

提出了一种新颖的复杂疾病驱使的融合SDA-SVM(Stepwise Discriminant Analysis-Support Vector Machine,SDA-SVM)技术的集成基因挖掘方法。该集成方法融合逐步判别分析和支持向量机的优点,能够有效地进行复杂疾病相关基因的深度挖掘,使得挖掘出的基因能够较好地识别疾病类型和亚型。通过将该方法应用于一套弥散性大B细胞淋巴瘤DNA表达谱数据,并与其它基因挖掘方法对比,结果表明该方法挖掘出的基因具有较高的疾病相关性和较强的疾病类型识别能力。     

Lipoprotein separation in a novel iodixanol density gradient, for composition, density, and phenotype analysis

Separation of lipoproteins by traditional sequential salt density floatation is a prolonged process ( approximately 72 h) with variable recovery, whereas iodixanol-based, self-generating density gradients provide a rapid ( approximately 4 h) alternative. A novel, three-layered iodixanol gradient was evaluated for its ability to separate lipoprotein fractions in 63 subjects with varying degrees of dyslipidemia. Lipoprotein cholesterol, triglycerides, and apolipoproteins were measured in 21 successive iodixanol density fractions. Iodixanol fractionation was compared with sequential floatation ultracentrifugation. Iodixanol gradient formation showed a coefficient of variation of 0.29% and total lipid recovery from the gradient of 95.4% for cholesterol and 84.7% for triglyceride. Recoveries for VLDL-, LDL-, and HDL-cholesterol, triglycerides, and apolipoproteins were approximately 10% higher with iodixanol compared with sequential floatation. The iodixanol gradient effectively discriminated classic lipoproteins and their subfractions, and there was evidence for improved resolution of lipoproteins with the iodixanol gradient. LDL particles subfractionated by the gradient showed good correlation between density and particle size with small, dense LDL (<25.5 nm) separated in fractions with density >1.028 g/dl. The new iodixanol density gradient enabled rapid separation with improved resolution and recovery of all lipoproteins and their subfractions, providing important information with regard to LDL phenotype from a single centrifugation step with minimal in-vitro modification of lipoproteins.     

The effects of morphine on the relationship between fetal EEG, breathing and blood pressure signals using fast wavelet transform

In this study, we introduce the fast wavelet transform (WT) as a method for investigating the effects of morphine on the electroencephalogram (EEG), respiratory activity and blood pressure in fetal lambs. Morphine was infused intravenously at 25 mg/h. The EEG, respiratory activity and blood pressure signals were analyzed using WT. We performed wavelet decomposition for five sets of parameters D _2j where -1 < j 5. The five series WTs represent the detail signal bandwidths: 1, 16–32 Hz; 2, 8–16 Hz; 3, 4–8 Hz; 4, 2–4 Hz; 5, 1–2 Hz. Before injection of the high-dose morphine, power in the EEG was high in all six frequency bandwidths. The respiratory and blood pressure signals showed common frequency components with respect to time and were coincident with the low-voltage fast activity (LVFA) EEG signal. Respiratory activity was observed during only some of the LVFA periods, and was completely absent during high-voltage slow activity (HVSA) EEG. The respiratory signal showed dominant power in the fourth wavelet band, and less power in the third and fifth bands. The blood pressure signal was also characterized by dominant power in the fourth wavelet band. This power was significantly increased during periods of respiratory activity. There was a strong relationship between fetal EEG, blood pressure and breathing movements. However, the injection of high-dose morphine resulted in a disruption of the normal cyclic pattern between the two EEG states and a significant increase in power in the first wavelet band. In addition, the high-dose drug resulted in a significant increase in the power of respiratory signal in the fourth and fifth wavelet bands, while power was reduced in the third wavelet band. Breathing activity was also continuous after the drug. The high-dose morphine also caused a temporary power shift from the third wavelet band to the fourth wavelet band for the 30-min period after injection of drug. Finally, high-dose morphine completely destroyed the correlation between EEG, breathing and blood pressure signals.     

HPLC fingerprints combined with principal component analysis,hierarchical cluster analysis and linear discriminant analysis for the classification and differentiation of Peganum sp. indigenous to China

Introduction – Seeds of wild Peganum harmala Linn., P. multisectum (Maxim) Bobr., P. nigellastrum Bunge and a probable indeterminate species, herein referred to as P. variety, are commonly used in Chinese medicine. These seeds cannot be differentiated based on morphology. Objective – Seeds of P. harmala Linn., P. multisectum (Maxim) Bobr., P. nigellastrum Bunge and P. variety were collected in different provinces in China and their HPLC profiles were recorded for statistical analysis and pattern recognition. Methodology – HPLC chromatograms of seed extracts were recorded under the same conditions. Individual HPLC chromatograms for each species were evaluated against the mean chromatogram for the same species generated using a similarity evaluation computer program. Data from chromatographic fingerprints were also processed using principal component analysis (PCA), hierarchical cluster analysis (HCA) and linear discriminant analysis (LDA). Results – The Peganum sp. seed extracts had similar HPLC fingerprints but with some inter‐specific differences. The chromatographic fingerprints combined with PCA, HCA and LDA could distinguish the seeds of the different species of Peganum investigated. Conclusion – HPLC fingerprints can be used to authenticate and differentiate the seeds of three different species of genus Peganum indigenous to China. The results indicated that the unidentified P. variety might indeed be a new species or variety. Copyright © 2009 John Wiley & Sons, Ltd.