Sitanshu Sekhar Sahu

Brief Communication: A novel feature representation method based on Chou's pseudo amino acid composition for protein structural class prediction

During last few decades accurate determination of protein structural class using a fast and suitable computational method has been a challenging problem in protein science. In this context a meaningful representation of a protein sample plays a key role in achieving higher prediction accuracy. In this paper based on the concept of Chous pseudo amino acid composition (Chou, K.C., 2001. Proteins 43, 246-255), a new feature representation method is introduced which is composed of the amino acid composition information, the amphiphilic correlation factors and the spectral characteristics of the protein. Thus the sample of a protein is represented by a set of discrete components which incorporate both the sequence order and the length effect. On the basis of such a statistical framework a simple radial basis function network based classifier is introduced to predict protein structural class. A set of exhaustive simulation studies demonstrates high success rate of classification using the self-consistency and jackknife test on the benchmark datasets.

An Improved S-Transform for Time-Frequency Analysis

The time-frequency representation (TFR) has been used as a powerful technique to identify, measure and process the time varying nature of signals. In the recent past S-transform gained a lot of interest in time-frequency localization due to its superiority over all the existing identical methods. It produces the progressive resolution of the wavelet transform maintaining a direct link to the Fourier transform. The S-transform has an advantage in that it provides multi resolution analysis while retaining the absolute phase of each frequency component of the signal. But it suffers from poor energy concentration in the time-frequency domain. It gives degradation in time resolution at lower frequency and poor frequency resolution at higher frequency. In this paper we propose a modified Gaussian window which scales with the frequency in a efficient manner to provide improved energy concentration of the S-transform. The potentiality of the proposed method is analyzed using a variety of test signals. The results of the study reveal that the proposed scheme can resolve the time-frequency localization in a better way than the standard S-transform.

Identification of Protein-Coding Regions in DNA Sequences Using A Time-Frequency Filtering Approach

Accurate identification of protein-coding regions (exons) in DNA sequences has been a challenging task in bioinformatics. Particularly the coding regions have a 3-base periodicity, which forms the basis of all exon identification methods. Many signal processing tools and techniques have been applied successfully for the identification task but still improvement in this direction is needed. In this paper, we have introduced a new promising model-independent time-frequency filtering technique based on S-transform for accurate identification of the coding regions. The S-transform is a powerful linear time-frequency representation useful for filtering in time-frequency domain. The potential of the proposed technique has been assessed through simulation study and the results obtained have been compared with the existing methods using standard datasets. The comparative study demonstrates that the proposed method outperforms its counterparts in identifying the coding regions.

Efficient Localization of Hot Spots in Proteins Using a Novel S-Transform Based Filtering Approach

Protein-protein interactions govern almost all biological processes and the underlying functions of proteins. The interaction sites of protein depend on the 3D structure which in turn depends on the amino acid sequence. Hence, prediction of protein function from its primary sequence is an important and challenging task in bioinformatics. Identification of the amino acids (hot spots) that leads to the characteristic frequency signifying a particular biological function is really a tedious job in proteomic signal processing. In this paper, we have proposed a new promising technique for identification of hot spots in proteins using an efficient time-frequency filtering approach known as the S-transform filtering. The S-transform is a powerful linear time-frequency representation and is especially useful for the filtering in the time-frequency domain. The potential of the new technique is analyzed in identifying hot spots in proteins and the result obtained is compared with the existing methods. The results demonstrate that the proposed method is superior to its counterparts and is consistent with results based on biological methods for identification of the hot spots. The proposed method also reveals some new hot spots which need further investigation and validation by the biological community.

Time Localised Band Filtering Using Modified S-Transform

A noisy time series, with both signal and noise varying in frequency and in time, presents special challenges for improving the signal to noise ratio. A modified S-transform time-frequency representation is used to filter a synthetic time series in a two step filtering process. The filter method appears robust within a wide range of background noise levels.

Cat Swarm Optimization Based Functional Link Artificial Neural Network Filter for Gaussian Noise Removal from Computed Tomography Images

Gaussian noise is one of the dominant noises, which degrades the quality of acquired Computed Tomography CT image data. It creates difficulties in pathological identification or diagnosis of any disease. Gaussian noise elimination is desirable to improve the clarity of a CT image for clinical, diagnostic, and postprocessing applications. This paper proposes an evolutionary nonlinear adaptive filter approach, using Cat Swarm Functional Link Artificial Neural Network CS-FLANN to remove the unwanted noise. The structure of the proposed filter is based on the Functional Link Artificial Neural Network FLANN and the Cat Swarm Optimization CSO is utilized for the selection of optimum weight of the neural network filter. The applied filter has been compared with the existing linear filters, like the mean filter and the adaptive Wiener filter. The performance indices, such as peak signal to noise ratio PSNR, have been computed for the quantitative analysis of the proposed filter. The experimental evaluation established the superiority of the proposed filtering technique over existing methods.

Identification of Glacial Isostatic Adjustment in Eastern Canada Using S Transform Filtering of GPS Observations

Over the years, a number of different models and techniques have been proposed to both quantify and explain the glacial isostatic adjustment (GIA) process. There are serious challenges, however, to obtaining accurate results from measurements, due to noise in the data and the long periods of time necessary to identify the relatively small-magnitude signal in certain regions. The primary difficulty, in general, is that most of the geophysical signals that occur in addition to GIA are nonstationary in nature. These signals are also corrupted by random as well as correlated noise added during data acquisition. The nonstationary characteristic of the data makes it difficult for traditional frequency-domain denoising approaches to be effective. Time–frequency filters present a more robust and reliable alternative to deal with this problem. This paper proposes an extended S transform filtering approach to separate the various signals and isolate that associated with GIA. Continuous global positioning system (GPS) data from eastern Canada for the period from June 2001 to June 2006 are analyzed here, and the vertical velocities computed after filtering are consistent with the GIA models put forward by other researchers.

Improved protein structural class prediction using genetic algorithm and artificial immune system

Predicting the structure of a protein from primary sequence is one of the challenging problems in Molecular biology. In this context, protein structural class information provides a key idea of their structure and also other features related to the biological function. In this paper we present a new optimization approach based on Genetic algorithm (GA) and artificial immune system (AIS) for predicting the protein structural class. It uses the maximum component coefficient principle in association with the amino acid composition feature vector to efficiently classify the protein structures. The effectiveness is evaluated by comparing the results with that obtained from other existing methods using a standard database. Especially for all α and α + β class protein, the rate of accurate prediction by the proposed methods is much higher than their counterparts.

A new approach for identification of hot spots in proteins using S-Transform filtering

Prediction of protein function from its sequence is an important and challenging task in Bioinformatics. The biological function of a protein primarily depends on the amino acid sequence within it. Identification of the amino acids (hot spots) that leads to the characteristic frequency signifying a particular biological function is really a tedious job in proteomic signal processing. In this paper we have proposed a new technique for identification of hot spots in proteins using an efficient time-frequency filtering approach known as the S-Transform filtering. The S-Transform is a powerful linear time-frequency representation and is especially useful for the filtering in the time-frequency domain. The potentiality of the new technique is analysed in identifying hot spots in proteins and the result obtained is compared with other existing methods. It reveals that the proposed method is superior to its counterparts and is consistent with results based on biological methodologies for identification of the hot spots. This new method also reveals some new hot spots which needs further investigation by the biological community.

Accidental Event Detection Based on Optical Flow Analysis

Event detection, in simple terms, means detection of the incidences occurring around us satisfying the threshold condition of some predefined criteria. In present scenario, event detection is gaining importance because of its versatility regarding predefined criteria, threshold conditions and its widespread applications. Many works have been done in this area. In the present paper, our goal is to detect the accidents occurring on the streets, roads and highways. For this, we have done the correlation analysis of optical flow and exhaustive simulation has been performed to show its effectiveness. The results based on optical flow of frames and its correlation show that the event is detected more accurately compared to the results obtained due to correlation only. Also, an exhaustive study has been performed on various accidental scenarios and it has been observed that the proposed method accurately identifies the accidental scenario in every case, be it any kind of traffic (more dense or less).