Genomic sequence processing has been an active area of research for the past two decades and has increasingly attracted the attention of digital signal processing researchers in recent years. A challenging open problem in deoxyribonucleic acid (DNA) sequence analysis is maximizing the prediction accuracy of eukaryotic gene locations and thereby protein coding regions. In this paper, DNA symbolic-to-numeric representations are presented and compared with existing techniques in terms of relative accuracy for the gene and exon prediction problem. Novel signal processing-based gene and exon prediction methods are then evaluated together with existing approaches at a nucleotide level using the Burset/Guigo1996, HMR195, and GENSCAN standard genomic datasets. A new technique for the recognition of acceptor splice sites is then proposed, which combines signal processing-based gene and exon prediction methods with an existing data-driven statistical method. By comparison with the acceptor splice site detection method used in the gene-finding program GENSCAN, the proposed DSP-statistical hybrid technique reveals a consistent reduction in false positives at different levels of sensitivity, averaging a 43% reduction when evaluated on the GENSCAN test set.

Signal Processing in Sequence Analysis: Advances in Eukaryotic Gene Prediction

Data-driven machine learning, especially deep learning technology, is becoming an important tool for handling big data issues in bioinformatics. In machine learning, DNA sequences are often converted to numerical values for data representation and feature learning in various applications. Similar conversion occurs in Genomic Signal Processing (GSP), where genome sequences are transformed into numerical sequences for signal extraction and recognition. This kind of conversion is also called encoding scheme. The diverse encoding schemes can greatly affect the performance of GSP applications and machine learning models. This paper aims to collect, analyze, discuss, and summarize the existing encoding schemes of genome sequence particularly in GSP as well as other genome analysis applications to provide a comprehensive reference for the genomic data representation and feature learning in machine learning.

/pdf/survey-on-encoding-schemes-for-genomic-data-representation-153ny7mzc4.pdf

Survey on encoding schemes for genomic data representation and feature learning—from signal processing to machine learning

Digital Signal Processing (DSP) applications in Bioinformatics have received great attention in recent years, where new effective methods for genomic sequence analysis, such as the detection of coding regions, have been developed. The use of DSP principles to analyze genomic sequences requires defining an adequate representation of the nucleotide bases by numerical values, converting the nucleotide sequences into time series. Once this has been done, all the mathematical tools usually employed in DSP are used in solving tasks such as identification of protein coding DNA regions, identification of reading frames, and others. In this article we present an overview of the most relevant applications of DSP algorithms in the analysis of genomic sequences, showing the main results obtained by using these techniques, analyzing their relative advantages and drawbacks, and providing relevant examples. We finally analyze some perspectives of DSP in Bioinformatics, considering recent research results on algebraic structures of the genetic code, which suggest other new DSP applications in this field, as well as the new field of Genomic Signal Processing.

Digital Signal Processing in the Analysis of Genomic Sequences

Manydigital signal processing techniques have beenusedtoautomatically distinguish theprotein coding regions (exons) fromnon-coding regions (introns) inaDNAsequence. Recently, Auto-regressive (AR) technique hasbeenused forthedetection of3periodicty present inprotein coding regions of genomic sequences. The. sequence length, average spacing between coding regions, andaverage coding region length arethemainfactors thataffect the performance ofanyprediction method Inthis paper, wepropose theuseofSingular Value Decomposition (SVD) methodfor thedetection ofperiod-3 behavior in DNA sequences. Results showthatSVDmethod outperforms theARtechnique.

Detection of period-3 behavior in genomic sequences using singular value decomposition

From DNA to protein: Why genetic code context of nucleotides for DNA signal processing? A review

The major signal in protein coding regions of genomic sequences is f=1/3 periodicity; some methods such as FFT-based methods, autocorrelation, mutual information function, etc, which exploit this phenomenon, rapidly lose effectiveness in the case of small DNA sequences when attempting to detect 3-periodicity The paper proposes an AR technique as an alternative tool for this purpose, due to its improved coding region resolution for small data records Theoretical analysis and experimental results show that the detection resolution for the AR technique is higher than that of Fourier methods for small DNA sequences The sequence length and structure are the main factors that affect performance of any detection method However, AR methods are more robust against variations in these factors Unlike neural net-based methods, no a priori knowledge of the sequences is required Hence, the AR technique appears to be a useful tool for 3-periodicity (including other periodicities), repeat and regulatory regions of unknown genomic sequences, especially small genomic sequence

N. Rao

Papers

Detection of 3-periodicity for small genomic sequences based on AR technique