Prediction of protein kinase-specific phosphorylation sites in hierarchical structure using functional information and random forest.

Reversible protein phosphorylation is one of the most important post-translational modifications, which regulates various biological cellular processes. Identification of the kinase-specific phosphorylation sites is helpful for understanding the phosphorylation mechanism and regulation processes. Although a number of computational approaches have been developed, currently few studies are concerned about hierarchical structures of kinases, and most of the existing tools use only local sequence information to construct predictive models. In this work, we conduct a systematic and hierarchy-specific investigation of protein phosphorylation site prediction in which protein kinases are clustered into hierarchical structures with four levels including kinase, subfamily, family and group. To enhance phosphorylation site prediction at all hierarchical levels, functional information of proteins, including gene ontology (GO) and protein-protein interaction (PPI), is adopted in addition to primary sequence to construct prediction models based on random forest. Analysis of selected GO and PPI features shows that functional information is critical in determining protein phosphorylation sites for every hierarchical level. Furthermore, the prediction results of Phospho.ELM and additional testing dataset demonstrate that the proposed method remarkably outperforms existing phosphorylation prediction methods at all hierarchical levels. The proposed method is freely available at http://bioinformatics.ustc.edu.cn/phos_pred/.

[Method of automatic detection of brain lesion based on wavelet feature vector].

A new method of automatic detection of brain lesion based on wavelet feature vector of CT images has been proposed in the present paper. Firstly, we created training samples by manually segmenting normal CT images into gray matter, white matter and cerebrospinal fluid sub images. Then, we obtained the cluster centers using FCM clustering algorithm. When detecting lesions, the CT images to be detected was automatically segmented into sub images, with a certain degree of over-segmenting allowed under the premise of ensuring accuracy as much as possible. Then we extended these sub images and extracted the features to compute the distances with the cluster centers and to determine whether they belonged to the three kinds of normal samples, or, otherwise, belonged to lesions. The proposed method was verified by experiments.

[Study on Grey model of electroencephalogram and features of driving fatigue].

Grey system theory was applied in analysis of Electroencephalogram (EEG) to extract features of driving fatigue in this study. Model GM(1,1) was built for EEG collected during simulative driving experiments. At the same time, the data of steering wheel movements and subjective fatigue level were analyzed as reference. The results of experiments reveal that the co-deviation of Model GM(1,1) parameter a and b, cov(a,b), coincides with the standard deviation of steering wheel movements. This indicates that Grey system theory is effective for EEG analysis and the parameters of GM(1,1) can well reflect the change of driving fatigue.

[Algorithm of brain pathology detection based on statistical atlas of attribute vectors].

To detect lesions of brain CT automatically, a statistical atlas of attribute vectors (SAAV) was designed and created to describe the multiple features of medical images. By comparing the features of study image with those of SAAV, we successfully detected various kinds of brain lesion. It was demonstrated that the algorithm is effective in detecting various kinds of lesions found on brain CT images. Further studies are needed to make the algorithm more acceptable.

[Application of fingerprint identification technology in EMR system].

Based on the deep analysis of existing fingerprint identification algorithms, this article proposes an integrative solution to adopt the fingerprint identification technology into EMRS Electronic Medical Records System. It may improve the security of EMRS and raise the working efficiency of physicians effectively.

[A method to enhance user experience of EMR based on mining association rules of incremental updating data].

The user experience (EX) of current Electronic Medical Record systems (EMR) is needed to improve. This paper proposed a new method to enhance EX of EMR. Firstly, system template and text characterization are used to make the EMR data structured. Then, the structured date are mined based on mining the association rules of incremental updating data to find the association of the elements of template of EMR and the values of elements. Finally, with the help of mined results, the users of EMR are able to input data effectively and quickly.

Detection of copy number variants and loss of heterozygosity from impure tumor samples using whole exome sequencing data.

Using whole-exome sequencing (WES) for the detection of chromosomal aberrations from tumor samples has become increasingly popular, as it is cost-effective and time efficient. However, factors which present in WES tumor samples, including diversity in exon size, batch effect and tumor impurity, can complicate the identification of somatic mutation in each region of the exon. To address these issues, the authors of the present study have developed a novel method, PECNV, for the detection of genomic copy number variants and loss of heterozygosity in WES datasets. PECNV combines normalized logarithm ratio of read counts (Log Ratio) and B allele frequency (BAF), and then employs expectation maximization (EM) algorithm to estimate parameters involved in the models. A comprehensive assessment of PECNV of PECNV was performed by analyzing simulated datasets contaminated with different normal cell proportion and eight real primary triple-negative breast cancer samples. PECNV demonstrated superior results compared with ExomeCNV and EXCAVATOR for the detection of genomic aberrations in WES data.

LOCSVMPSI: a web server for subcellular localization of eukaryotic proteins using SVM and profile of PSI-BLAST.

Subcellular location of a protein is one of the key functional characters as proteins must be localized correctly at the subcellular level to have normal biological function. In this paper, a novel method named LOCSVMPSI has been introduced, which is based on the support vector machine (SVM) and the position-specific scoring matrix generated from profiles of PSI-BLAST. With a jackknife test on the RH2427 data set, LOCSVMPSI achieved a high overall prediction accuracy of 90.2%, which is higher than the prediction results by SubLoc and ESLpred on this data set. In addition, prediction performance of LOCSVMPSI was evaluated with 5-fold cross validation test on the PK7579 data set and the prediction results were consistently better than the previous method based on several SVMs using composition of both amino acids and amino acid pairs. Further test on the SWISSPROT new-unique data set showed that LOCSVMPSI also performed better than some widely used prediction methods, such as PSORTII, TargetP and LOCnet. All these results indicate that LOCSVMPSI is a powerful tool for the prediction of eukaryotic protein subcellular localization. An online web server (current version is 1.3) based on this method has been developed and is freely available to both academic and commercial users, which can be accessed by at http://Bioinformatics.ustc.edu.cn/LOCSVMPSI/LOCSVMPSI.php.

[Detrended fluctuation analysis of physiological parameters during sleep].

Detrended fluctuation analysis (DFA) is fit for studies on the long-range exponential correlations of non-stationary time serial. In this paper, for elucidating the characteristics of different sleep stages, DFA is adopted to analyze the physiological data collected during sleep. The parameters such as electroencephalogram (EEG), R-R interval sequence and stroke volume (SV) are analyzed, and the scaling exponent a is calculated. The experimental results reveal that the values of a differ much in different sleep stages,that the rules of EEG and SV are alike, that alpha increases with the deepening of sleep, but in inverse for R-R interval sequence that alpha decreases with the deepening of sleep. These indicate that the method of DFA is practical in the analysis of physiological parameters.

[A novel segment-training algorithm for transmembrane helices prediction].

This paper is devoted to predicting the transmembrane helices in proteins by statistical modeling. A novel segment-training algorithm for Hidden Markov modeling based on the biological characters of transmembrane proteins has been introduced into training and predicting the topological characters of transmembrane helices such as location and orientation. Compared to the standard Balm-Welch training algorithm, this algorithm has lower complexity while prediction performance is better than or at least comparable to other existing methods. With a 10-fold cross-validation test on a database containing 160 transmembrane proteins, an HMM model trained with this algorithm outperformed two other prediction methods: TMHMM and MEMSTAT; the novel method was validated by its prediction sensitivity (97.0%) and correct location (91.3%). The results showed that this algorithm is an efficient and a reasonable supplement to modeling and prediction of transmembrane helices.

[Design of a digital spectrometer for the MRI system].

A spectrometer is one of the most important parts in a Magnetic Resonance Imaging (MRI) system. This paper describes the design of a digital MRI spectrometer. It is constructed on a PXI platform with several data acquisition boards and a high-resolution timing board. All functions of a MRI spectrometer are realized by the specially- designed software. The software architecture and its implementing details are discussed and experimental results are introduced.

Missing value estimation for DNA microarray gene expression data by Support Vector Regression imputation and orthogonal coding scheme.

BACKGROUND: Gene expression profiling has become a useful biological resource in recent years, and it plays an important role in a broad range of areas in biology. The raw gene expression data, usually in the form of large matrix, may contain missing values. The downstream analysis methods that postulate complete matrix input are thus not applicable. Several methods have been developed to solve this problem, such as K nearest neighbor impute method, Bayesian principal components analysis impute method, etc. In this paper, we introduce a novel imputing approach based on the Support Vector Regression (SVR) method. The proposed approach utilizes an orthogonal coding input scheme, which makes use of multi-missing values in one row of a certain gene expression profile and imputes the missing value into a much higher dimensional space, to obtain better performance. RESULTS: A comparative study of our method with the previously developed methods has been presented for the estimation of the missing values on six gene expression data sets. Among the three different input-vector coding schemes we tried, the orthogonal input coding scheme obtains the best estimation results with the minimum Normalized Root Mean Squared Error (NRMSE). The results also demonstrate that the SVR method has powerful estimation ability on different kinds of data sets with relatively small NRMSE. CONCLUSION: The SVR impute method shows better performance than, or at least comparable with, the previously developed methods in present research. The outstanding estimation ability of this impute method is partly due to the use of the most missing value information by incorporating orthogonal input coding scheme. In addition, the solid theoretical foundation of SVR method also helps in estimation of performance together with orthogonal input coding scheme. The promising estimation ability demonstrated in the results section suggests that the proposed approach provides a proper solution to the missing value estimation problem. The source code of the SVR method is available from http://202.38.78.189/downloads/svrimpute.html for non-commercial use.

PPSP: prediction of PK-specific phosphorylation site with Bayesian decision theory.

BACKGROUND: As a reversible and dynamic post-translational modification (PTM) of proteins, phosphorylation plays essential regulatory roles in a broad spectrum of the biological processes. Although many studies have been contributed on the molecular mechanism of phosphorylation dynamics, the intrinsic feature of substrates specificity is still elusive and remains to be delineated. RESULTS: In this work, we present a novel, versatile and comprehensive program, PPSP (Prediction of PK-specific Phosphorylation site), deployed with approach of Bayesian decision theory (BDT). PPSP could predict the potential phosphorylation sites accurately for approximately 70 PK (Protein Kinase) groups. Compared with four existing tools Scansite, NetPhosK, KinasePhos and GPS, PPSP is more accurate and powerful than these tools. Moreover, PPSP also provides the prediction for many novel PKs, say, TRK, mTOR, SyK and MET/RON, etc. The accuracy of these novel PKs are also satisfying. CONCLUSION: Taken together, we propose that PPSP could be a potentially powerful tool for the experimentalists who are focusing on phosphorylation substrates with their PK-specific sites identification. Moreover, the BDT strategy could also be a ubiquitous approach for PTMs, such as sumoylation and ubiquitination, etc.

[Nonlinear analysis of multi-channel EEG and its application to mental workload detection].

Mental workload research is important to people's health and work efficiency, Psychophysiological measures such as electroencephalography (EEG), ECG and respiration measures can be used to predict mental workload level. A Multi-channel phase-space reconstruction method is proposed in this paper which rearranges signal serials by the correlation coefficients and select time delay by signal determinism. The study of determinism and correlation dimension on simulative data exhibits a good performance. The result of EEG series shows a clearly consistency to workload level variety. The method is useful for multi-channel signals nonlinear analysis and mental workload detection.

[Prediction of protein solvent accessibility with Markov chain model].

Residues in protein sequences can be classified into two (exposed / buried) or three (exposed/intermediate/buried) states according to their relative solvent accessibility. Markov chain model (MCM) had been adopted for statistical modeling and prediction. Different orders of MCM and classification thresholds were explored to find the best parameters. Prediction results for two different data sets and different cut-off thresholds were evaluated and compared with some existing methods, such as neural network, information theory and support vector machine. The best prediction accuracies achieved by the MCM method were 78.9% for the two-state prediction problem and 67.7% for the three-state prediction problem, respectively. A comprehensive comparison for all these results shows that the prediction accuracy and the correlative coefficient of the MCM method are better than or comparable to those obtained by the other prediction methods. At the same time, the advantage of this method is the lower computation complexity and better time-consuming performance.

[Off-line experiments and analysis of independent brain--computer interface].

In order to study event-related desynchronization (ERD) related to voluntary movement, we designed two experiments. In the first experiment, untrained subjects were required to imagine the action of typing with left or right index finger for about 1 second before real action, whereas they were required to type instantly after instruction in the second experiment. By analyzing spontaneous EEG signals between the instruction and the action, we predicted which finger was used. The prediction accuracy in the first experiment fell from 85% to 71% with the progress of experiment, the average accuracy being 78%, whereas the prediction result was almost random guess in the second experiment. The results demonstrate that (1) ERD patterns are significantly affected by the effective duration of motion imagination, (2) unconscious reduction of this duration can decrease the prediction accuracy. Therefore, when designing subsequent BCI experiments, we should devote our attention to the question of how to keep the effective duration of motion imagination.

[Quasi-Newton iteration algorithm for ICA and its application in VEP feature extraction].

Some noises still exist in the single-trial averaged visual evoked potentials (VEP), so further extraction of the above results is of significance. Independent component analysis (ICA)can separate the sources from their mixtures and make the output statistically as independent as possible; it can remove noises effectively. In this paper, the principle, experiment analyses and results of ICA based on quasi-Newton iteration rule for VEP feature extraction are introduced, It is compared with the fixed-point FastICA algorithm. The experiment results show that the provided algorithm may reinforce signals effectively and extract distinct P300 from the single-trial averaged VEP. It is of good applicability.

[Implementation of sector imaging mode with high signal-to-noise ratio in the high frame rate ultrasonic imaging system].

The high frame rate (HFR) ultrasonic imaging system, which is developed with limited diffraction beams, constructs images at a high frame rate. However the rectangular imaging area, to some extent, restricts the far field imaging information. At the same time, because of one transmission for constructing image, the system suffers from low SNR. In this paper we present a computationally efficient method to construct sector mode image and to increase the SNR in HFR system. The method uses Golay complementary sequence as excitation to realize two transmission events. Each event simultaneously transmits two plane waves with different transmission angle. Then the received echo signals related to different angle are separated according to orthogonality of Golay complementary sequence and used to construct two images of different area by HFR method. Finally the two images are synthesized to one frame of sector mode image.

[Controlling of the high-voltage generator in a direct radiography system].

A proposal is presented to improve the original complicated control of the exposure parameters in the direct radiography system (DR). The interface circuitry of the high-voltage generator is redesigned using RS-232 serial COM port. The data and signals are transmitted between the personal computer and the high-voltage generator in the serial mode. A program package is designed to realize the control of the exposure parameters of the high-voltage generator in DR on the PC machine. Experiment results have shown that the proposed console operates steadily and it is capable of providing a more convenient operation console for the direct radiography system.

NTSMDA: prediction of miRNA-disease associations by integrating network topological similarity.

Recently, accumulating studies have indicated that microRNAs (miRNAs) play an important role in exploring the pathogenesis of various human diseases at the molecular level and may result in the design of specific tools for diagnosis, treatment evaluation and prevention. Experimental identification of disease-related miRNAs is time-consuming and labour-intensive. Hence, there is a stressing need to propose efficient computational methods to detect more potential miRNA-disease associations. Currently, several computational approaches for identifying disease-related miRNAs on the miRNA-disease network have gained much attention by means of integrating miRNA functional similarities and disease semantic similarities. However, these methods rarely consider the network topological similarity of the miRNA-disease association network. Here, in this paper we develop an improved computational method named NTSMDA that is based on known miRNA-disease network topological similarity to exploit more potential disease-related miRNAs. We achieve an AUC of 89.4% by using the leave-one-out cross-validation experiment, demonstrating the excellent predictive performance of NTSMDA. Furthermore, predicted highly ranked miRNA-disease associations of breast neoplasms, lung neoplasms and prostatic neoplasms are manually confirmed by different related databases and literature, providing evidence for the good performance and potential value of the NTSMDA method in inferring miRNA-disease associations. The R code and readme file of NTSMDA can be downloaded from .