Identification Of Protein Coding Regions Research Articles

Optimization method of protein coding region identification based on IHHO-CNN-LSTM

Optimization method of protein coding region identification based on IHHO-CNN-LSTM

An efficient way of identification of protein coding regions of eukaryotic genes using digital FIR filter governed by Ramanujan's Sum

An efficient way of identification of protein coding regions of eukaryotic genes using digital FIR filter governed by Ramanujan's Sum

Bidirectional filtering approach for the improved protein coding region identification in eukaryotes

Bidirectional filtering approach for the improved protein coding region identification in eukaryotes

An efficient way of identification of protein coding regions of Eukaryotic genes using digital FIR filter governed by Ramanujan’s Sum

An efficient way of identification of protein coding regions of Eukaryotic genes using digital FIR filter governed by Ramanujan’s Sum

SAVMD: An adaptive signal processing method for identifying protein coding regions

The identification of protein coding regions is a major topic of research in the field of gene prediction. A number of digital signal processing (DSP) based approaches, which exploit 3-base periodicity to detect coding regions, have been proposed. According to these previously published approaches, we summarize that an effective method or filter for identifying protein coding regions should fulfill three important properties, including the independence of the window length, an effective and adaptive frequency response, a fixed basic frequency of 1∕3f. However, most of published approaches cannot simultaneously satisfy these three points, which causes that their identification accuracy is still limited. In this paper, we propose an adaptive signal processing method, called sinusoidal-assisted variational mode decomposition (SAVMD) for identifying coding regions. The adaptability of SAVMD reflects in two aspects including: (i) The proposed method analyzes numerical sequences without needing any window information; (ii) The spectrum of period-3 component can be automatically fitted by SAVMD in Fourier domain. From this, our proposed method outperforms other DSP-based methods in terms of identification accuracy, which is verified by the experimental results on five benchmark datasets. When processing the dataset where most sequences contain undetermined nucleotides (UDT), SAVMD shows more superior performance than the model-dependent method AUGUSTUS as well as other model-independent methods. In addition, we conduct a comparative analysis on different numerical conversions of DNA sequences using SAVMD. Several applicable methods for SAVMD, which are selected from this experimentation, can provide a reference to the applications of other time–frequency decomposition methods in the field of gene prediction.

DSP techniques for protein coding region identification based on background noise and nonlinear phase delay reduction from period-3 spectrum using zero phased anti-notch filter and Savitzky-Golay (S-G) filter

Short time discrete Fourier transform (STDFT) and anti-notch filters (ANF) are perhaps the most common DSP tools that uses the period-3 feature of protein coding sequences to discriminate between protein-coding regions and noncoding regions. However, the performance of these techniques is still limited due to the background noise present in their period-3 spectrum. The drawback with existing de-noising techniques is that it also distorts the period-3 feature besides noise suppression. In this article, the Savitzky-Golay (SG) filter is used to suppress the background noise from period-3 spectrum. A zero phased anti-notch filter (ZANF) is also used to overcome the effect of nonlinear phase delay from the period-3 spectrum of ANF. It is obtained that the combined use of ZANF and SG filters increases the prediction accuracy of conventional ANF by around 19% -26%.

DSP techniques for protein coding region identification based on background noise and nonlinear phase delay reduction from period-3 spectrum using zero phased anti-notch filter and Savitzky-Golay (S-G) filter

Short time discrete Fourier transform (STDFT) and anti-notch filters (ANF) are perhaps the most common DSP tools that uses the period-3 feature of protein coding sequences to discriminate between protein-coding regions and noncoding regions. However, the performance of these techniques is still limited due to the background noise present in their period-3 spectrum. The drawback with existing de-noising techniques is that it also distorts the period-3 feature besides noise suppression. In this article, the Savitzky-Golay (SG) filter is used to suppress the background noise from period-3 spectrum. A zero phased anti-notch filter (ZANF) is also used to overcome the effect of nonlinear phase delay from the period-3 spectrum of ANF. It is obtained that the combined use of ZANF and SG filters increases the prediction accuracy of conventional ANF by around 19% -26%.

A tri-nucleotide mapping scheme based on residual volume of amino acids for short length exon prediction using sliding window DFT method

One of the great challenges in the field of bioinformatics is how to locate the accurate protein-coding regions in a given DNA sequence. The accurate identification of the protein-coding region is useful in many applications. For instance; it helps in characterizing new proteins, drug designing, and also in revealing the evolutionary background of a particular organism. DSP based techniques are quite popular in the protein-coding region identification. The first essential step of the DSP based exon prediction technique is to convert the base sequences into the numerical sequence. The choice of the numerical mapping scheme affects how well the characteristic feature of the DNA sequence is reflected in the numerical domain which helps in finding the accurate location of exons. In the last two decades, numbers of mapping schemes have been successfully used for exon prediction. However, locating the short length exon is still a difficult task. In this paper, we have proposed a tri-nucleotide mapping scheme that exploits the residual volume property of amino acid to encode the given DNA sequence. It is obtained that the proposed tri-nucleotide mapping scheme provides better results than other mapping schemes in case of short length exon detection.

A new numerical approach for DNA representation using modified Gabor wavelet transform for the identification of protein coding regions

The fundamental step in genomic signal processing applications is to assign mathematical descriptor to nucleotides {A, T, G, C} of DNA molecule for discrete representation. The discrete representation should replicate biological information of gene when analyzed with digital signal processing tools. In this aspect, a novel binary representation of DNA sequence by combining structural and chemical information of original DNA sequence has been proposed for the identification of protein coding regions of eukaryotes. The identification model comprises two stages, mainly, numerical encoding in first stage, and analysis of biological behavior through digital signal processing algorithms in second stage. In the first stage, a new numerical encoding method based on Walsh codes of order-4 is proposed to obtain 1-D binary discrete sequence. In the second stage, the modified Gabor wavelet transform (MGWT) is employed on the discretized DNA sequence for spectrum analysis. The optimal gene numerical encoding and multiresolution approach of MGWT has readily identified the structures of coding regions of unknown gene sequences. The proposed model is validated by analyzing prediction efficiency in terms of statistical metrics such as sensitivity, specificity, accuracy on both sequence and data base level. Furthermore, the results are compared by plotting receiver operating curves (ROC) for all classification thresholds for the state-of-art encoding methods. Area under curve (AUC) value of 0.86 at sequence level and 0.84 at database level is achieved. Performance metrics indicate that the proposed encoding method exhibits relatively better performance than other numerical encoding methods.

Walsh code based numerical mapping method for the identification of protein coding regions in eukaryotes

The protein coding regions play a significant role for gene applications in genomic signal processing. Unlike prokaryotes, the coding regions in eukaryotes are arranged in a random manner. Owing to unequal lengths and low volume density of coding regions, the identification of coding regions makes cumbersome. In this work, a new numerical mapping method based on Walsh codes is proposed to detect the coding regions in eukaryotes. The Walsh code for each nucleotide is obtained using the statistical features of a DNA sequence. The proposed method uses static type of mapping to convert a string of DNA nucleotides into a numerical sequence. The numerical sequence is given as an input to the digital signal processing based spectrum identification tool to detect the existence of quasi-periodic components within the coding region. The advantage of our method is that it is simple to design and easy to represent. The performance of the proposed method has been tested on four benchmark databases and a random set of sequences collected from the National Center for Biological Information (NCBI) database. Furthermore, it has been compared with other state-of-the-art spectrum based numerical mapping methods for statistical features such as sensitivity, specificity and accuracy. The proposed method is efficient as it attains 94 % accuracy, 85 % sensitivity and 96 % specificity when tested on the benchmark C. Elegans gene sequence.

A novel numerical mapping method based on entropy for digitizing DNA sequences

Recently, digital signal processing has been widely applied in the study of genomics. One of the genomic studies is identification of protein-coding regions. Where is a protein coded? How much is encoded? Where are growth and development regulated? The answer to these questions is possible by DNA sequences that can be classified as the exon and intron. In signal processing application, numerical signals are used due to symbolic signal nature of DNA sequence; yet, it must be converted from symbolic sequence to numeric sequence prior the analysis in data preprocessing. The bases in a DNA sequence are represented with four letters A, G, C and T. Each letter corresponds to a numeric value. In the literature, several numerical mapping techniques exist. In this paper, a novel numerical mapping approach has been proposed for converting string to numerical values. Each codon is mapped by improved fractional derivative of Shannon equation in this approach. For exon regions prediction, three methods have been used. These methods are singular value decomposition (SVD), discrete Fourier transform (DFT) and short-time Fourier transform (STFT). The performance of the proposed mapping technique has been evaluated based on the above-mentioned three classification methods. The proposed novel technique has showed more success in the identification of protein-coding regions as compared to the predominant existing mapping techniques SVD, DFT and STFT methods.

Transductive learning as an alternative to translation initiation site identification

BackgroundThe correct protein coding region identification is an important and latent problem in the molecular biology field. This problem becomes a challenge due to the lack of deep knowledge about the biological systems and unfamiliarity of conservative characteristics in the messenger RNA (mRNA). Therefore, it is fundamental to research for computational methods aiming to help the patterns discovery for identification of the Translation Initiation Sites (TIS). In the field of Bioinformatics, machine learning methods have been widely applied based on the inductive inference, as Inductive Support Vector Machine (ISVM). On the other hand, not so much attention has been given to transductive inference-based machine learning methods such as Transductive Support Vector Machine (TSVM). The transductive inference performs well for problems in which the amount of unlabeled sequences is considerably greater than the labeled ones. Similarly, the problem of predicting the TIS may take advantage of transductive methods due to the fact that the amount of new sequences grows rapidly with the progress of Genome Project that allows the study of new organisms. Consequently, this work aims to investigate the transductive learning towards TIS identification and compare the results with those obtained in inductive method.ResultsThe transductive inference presents better results both in F-measure and in sensitivity in comparison with the inductive method for predicting the TIS. Additionally, it presents the least failure rate for identifying the TIS, presenting a smaller number of False Negatives (FN) than the ISVM. The ISVM and TSVM methods were validated with the molecules from the most representative organisms contained in the RefSeq database: Rattus norvegicus, Mus musculus, Homo sapiens, Drosophila melanogaster and Arabidopsis thaliana. The transductive method presented F-measure and sensitivity higher than 90% and also higher than the results obtained with ISVM. The ISVM and TSVM approaches were implemented in the TransduTIS tool, TransduTIS-I and TransduTIS-T respectively, available in a web interface. These approaches were compared with the TISHunter, TIS Miner, NetStart tools, presenting satisfactory results.ConclusionsIn relation to precision, the results are similar for the ISVM and TSVM classifiers. However, the results show that the application of TSVM approach ensured an improvement, specially for F-measure and sensitivity. Moreover, it was possible to identify a potential for the application of TSVM, which is for organisms in the initial study phase with few identified sequences in the databases.

Identification of protein coding regions in RNA transcripts.

Massive parallel sequencing of RNA transcripts by next-generation technology (RNA-Seq) generates critically important data for eukaryotic gene discovery. Gene finding in transcripts can be done by statistical (alignment-free) as well as by alignment-based methods. We describe a new tool, GeneMarkS-T, for ab initio identification of protein-coding regions in RNA transcripts. The algorithm parameters are estimated by unsupervised training which makes unnecessary manually curated preparation of training sets. We demonstrate that (i) the unsupervised training is robust with respect to the presence of transcripts assembly errors and (ii) the accuracy of GeneMarkS-T in identifying protein-coding regions and, particularly, in predicting translation initiation sites in modelled as well as in assembled transcripts compares favourably to other existing methods.

Improved Identification of Protein Coding Region using Wavelet Transform

Identification of protein coding regions is an important topic in genomic examination. The various coding DNA modelindependent methods are used where there is an existence of specific pattern of nucleotides. These methods presume the window length required for an examination of a DNA region. The DNA model depending coding methods catches more specific features of coding DNA. The model independent methods capture universal features of coding region. We introduce a method which is independent from the window length. Therefore objective of this paper is to improve the reorganization of protein coding region using wavelet transform with improved thresholding algorithms. This novel transform is adapt to examine periodic signal components and presents the advantage of being independent of the window length. Wavelet transform has a noisy signal, for this an improved wavelet transform threshold method has been used to improve the effects of denoising. The eukaryote data sets are used to analogize the results of proposed method with other previous methods. Finally the output obtained illustrates that the proposed method gives the better results with respect to identification accuracy. This method avoids sources of errors and makes a tool for detailed probe of the nucleotide occurrence. General Terms Numerical mapping, Thresholding, spectra of coding region, pattern recognition

Computational Study and Performance Evaluation of Different Genomic Signal Processing Methods for Identification of Protein Coding Regions (Exon Regions) of DNA Sequence

developments in the area of genomic signal processing (GSP) reveal that this approach has important role in the analysis of genomic sequence, structure and function as well as the gene regulation of different organisms. In this paper we analyze different genomic signal processing methods used for identification of exon coding regions in DNA sequence. The gene sequences of interest are mapped to electron ion interaction potential (EIIP) values of nucleotides and these transformed numerical gene sequences are processed through different signal processing techniques like discrete Fourier transform (DFT), auto regressive (AR) and adaptive auto regressive (AAR) methods. The performance evaluation in terms of computational time is estimated and analyzed. By applying the EIIP mapped sequence to these DFT, AR and AAR methods, the effective computational time is abruptly reduced in AAR method compared to the DFT and AR methods. We tested five sequences of c-elegans) (AF099922), (FO080874.2), (FO081434)), fruitfly (NM_170135) & homosapien (BDNF (NG_011794)).

Identification of Protein Coding Regions in the Eukaryotic DNA Sequences Based on Marple Algorithm and Wavelet Packets Transform

The identification of protein coding regions (exons) plays a critical role in eukaryotic gene structure prediction. Many techniques have been introduced for discriminating between the exons and the introns in the eukaryotic DNA sequences, such as the discrete Fourier transform (DFT) based techniques, but these DFT-based methods rapidly lose their effectiveness in the case of short DNA sequences. In this paper, a novel integrated algorithm based on autoregressive spectrum analysis and wavelet packets transform is presented to improve the efficiency and accuracy of the coding regions identification. The experimental results show that the new algorithm outperforms the conventional DFT-based approaches in improving the prediction accuracy of protein coding regions distinctly by testing GENSCAN65, HMR195, and BG570 benchmark datasets.

A Punctual Algorithm for Small Gene Prediction in DNA Sequences Using a Time-Frequency Approach based on the Z-Curve

Identification of protein-coding regions in Deoxyribonucleic Acid (DNA) sequences because of their 3-base periodicity has been a challenging issue in bioinformatics. Many DSP (Digital Signal Processing) techniques have been applied for identification task and concentrated on assigning numerical values to the symbolic DNA sequence and then applying spectral analysis tools such as the short-time discrete Fourier transform (ST-DFT) to locate periodicity components. In this paper, we investigate the location of exons in DNA strand using Variable Length Window approach based on z-curve. Z-curve is a unique 3-D curve to illustrate DNA's sequence which presents a complete description of DNA's sequence biological behavior. The proposed algorithm has a high accuracy and resolution due to applying Gaussian window with an adjustable length to identify and estimate exonic areas and non-coding regions are totally eliminated. In order to extract period-3 component we used a narrow-band band-pass filter with a central frequency of . The proposed algorithm was applied on some gene sequences existed in GenBank dataset and its results were compared by other existing methods at the nucleotide level. Simulation results show that our algorithm increases the accuracy of exon detection relative to other methods for exon prediction.

A Novel Fast Algorithm for Exon Prediction in Eukaryotic Genes using Linear Predictive Coding Model and Goertzel Algorithm based on the Z-Curve

identification of protein-coding regions in Deoxyribonucleic Acid (DNA) sequences because of their 3- base periodicity has been a challenging issue in bioinformatics. Many DSP (Digital Signal Processing) techniques have been applied for identification task and concentrated on assigning numerical values to the symbolic DNA sequence and then applying spectral analysis tools such as the short-time discrete Fourier transform (ST-DFT) to locate periodicity components. In this paper, first, the symbolic DNA sequences are converted to digital signal using the Z-curve method, which is a unique 3-D plot to illustrate DNA sequence and presents the biological behavior of DNA sequence. Then a novel fast algorithm is proposed to investigate the location of exons in DNA strand based on the combination of Linear Predictive Coding Model (LPCM) and Goertzel algorithm. The proposed algorithm leads to increase the speed of process and therefor reduce the computational complexity. Detection of small size exons in DNA sequences, exactly, is another advantage of our algorithm. The proposed algorithm ability in exon prediction is compared with several existing methods at the nucleotide level using: (i) specificity - sensitivity values; (ii) Receiver Operating Curves (ROC); and (iii) area under ROC curve. Simulation results show that our algorithm increases the accuracy of exon detection relative to other methods for exon prediction. In this paper, we have also developed a useful user friendly package to analyze DNA sequences. Keywordssequence; Protein coding regions; Signal processing; Exon; Linear predictive coding model; Goertzel algorithm.

Fast Algorithmfor Identifying Protein-Coding Regions

Identification of protein-coding regions is a hot research area at present. After using mapping methods to turn symbolic genomic sequences into numeric sequences, we need to do the transform to show the period-3 component of protein-coding regions. In this paper, we find twofast algorithms relying on discrete Fourier transform and the extension of Signal Noise Ratio to compute the period-3 component of protein-coding regions.

Identification of protein coding regions using antinotch filters

A major area of research in genomic sequence analysis is the identification of protein coding regions using the period-3 property. Previously antinotch filter has been used for this purpose. In this paper, three antinotch filters, namely conjugate suppression antinotch filter, antinotch filter followed by moving average filter and harmonic suppression antinotch filter are proposed to improve the identification accuracy. Conjugate suppression antinotch filter suppresses the conjugate frequency component, antinotch filter followed by moving average filter reduces the background noise and harmonic suppression antinotch filter suppresses the harmonic frequency component. Several existing DNA to numerical mapping techniques are compared for GENSCAN test set and based on the result one mapping technique is recommended so that detailed analysis can be performed using various datasets. The computational complexity of the antinotch filters is evaluated in comparison with the ST-DFT method and it is found that the computational load is reduced to a greater extent in antinotch filter. The identification accuracy of the proposed antinotch filter methods is compared with the existing antinotch filter method at the nucleotide level for benchmark datasets. The results show that proposed methods outperform the existing method, giving improved identification of the protein coding regions.