A Brief Review of Computational Gene Prediction Methods

Wang, Zhuo; Chen, Yazhu; Li, Yixue

doi:10.1016/s1672-0229(04)02028-5

Cited by 87 publications

(53 citation statements)

References 28 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At the moment, nearly 50 complete genomes of eukaryotes are publicly available, and many more are in the pipeline to be sequenced in the next few years (Liolios et al 2006). The proliferation of genome sequencing projects has driven the search for fast ways of sequence-based structural annotation, which involves the identification of genes and the modeling of their correct gene structure (Claverie et al 1997;Mathé et al 2002;Zhang 2002;Wang et al 2004). Although great progress has been achieved in gene prediction, for instance by using comparative approaches (Wasserman et al 2000;Liu et al 2004;Jin et al 2006;Wang and Zhang 2006), one of the more difficult tasks in the annotation of whole genomes remains the accurate identification and delineation of promoters (Fickett and Hatzigeorgiou 1997;Ohler 2000Ohler , 2001Bajic et al 2004Bajic et al , 2006a.…”

mentioning

confidence: 99%

Generic eukaryotic core promoter prediction using structural features of DNA

Abeel

Saeys²,

Bonnet³

et al. 2007

Genome Res.

192

208

View full text Add to dashboard Cite

Despite many recent efforts, in silico identification of promoter regions is still in its infancy. However, the accurate identification and delineation of promoter regions is important for several reasons, such as improving genome annotation and devising experiments to study and understand transcriptional regulation. Current methods to identify the core region of promoters require large amounts of high-quality training data and often behave like black box models that output predictions that are difficult to interpret. Here, we present a novel approach for predicting promoters in whole-genome sequences by using large-scale structural properties of DNA. Our technique requires no training, is applicable to many eukaryotic genomes, and performs extremely well in comparison with the best available promoter prediction programs. Moreover, it is fast, simple in design, and has no size constraints, and the results are easily interpretable. We compared our approach with 14 current state-of-the-art implementations using human gene and transcription start site data and analyzed the ENCODE region in more detail. We also validated our method on 12 additional eukaryotic genomes, including vertebrates, invertebrates, plants, fungi, and protists.

show abstract

mentioning

confidence: 99%

Generic eukaryotic core promoter prediction using structural features of DNA

Abeel

Saeys²,

Bonnet³

et al. 2007

Genome Res.

192

208

View full text Add to dashboard Cite

show abstract

“…The proposed methods performed well in a good number of cases. The accuracy measures for evaluating the different methods used in this paper are exon-intron discrimination factor D [23], sensitivity (S N ), specificity (S P ), miss rate (M R ), wrong rate (W R ) [3,15] and approximate correlation [28]. The discriminating factor is defined as Lowest of exon peaks Highest peak in noncoding regions D …”

Section: Resultsmentioning

confidence: 99%

“…For the last few decades, the major task of DNA and protein analysis, has been on string matching, either with a goal of obtaining a precise solution, e.g., with dynamic programming, or more commonly a fast solution, e.g., with heuristic techniques such as BLAST and several versions of FASTA [3]. But any of the string matching methodologies could not lead to satisfactory results.…”

Section: Introductionmentioning

confidence: 99%

A reduced computational load protein coding predictor using equivalent amino acid sequence of DNA string with period-3 based time and frequency domain analysis

Meher¹,

Dash²,

Meher³

et al. 2011

AJMB

View full text Add to dashboard Cite

Development of efficient gene prediction algorithms is one of the fundamental efforts in gene prediction study in the area of genomics. In genomic signal processing the basic step of the identification of protein coding regions in DNA sequences is based on the period-3 property exhibited by nucleotides in exons. Several approaches based on signal processing tools and numerical representations have been applied to solve this problem, trying to achieve more accurate predictions. This paper presents a new indicator sequence based on amino acid sequence, called as aminoacid indicator sequence, derived from DNA string that uses the existing signal processing based timedomain and frequency domain methods to predict these regions within the billions long DNA sequence of eukaryotic cells which reduces the computational load by one-third. It is known that each triplet of bases, called as codon, instructs the cell machinery to synthesize an amino acid. The codon sequence therefore uniquely identifies an amino acid sequence which defines a protein. Thus the protein coding region is attributed by the codons in amino acid sequence. This property is used for detection of period-3 regions using amino acid sequence. Physico-chemical properties of amino acids are used for numerical representation. Various accuracy measures such as exonic peaks, discriminating factor, sensitivity, specificity, miss rate, wrong rate and approximate correlation are used to demonstrate the efficacy of the proposed predictor. The proposed method is validated on various organisms using the standard dataset HMR195, Burset and Guigo and KEGG. The simulation result shows that the proposed method is an effective approach for protein coding prediction.

show abstract

“…There are several methods that have been applied for detecting coding regions in a genome, among which the most used are those based on sequence comparison and ab initio methods (Wang et al, 2004). Homology gene finding methods are based in given a DNA sequence identifying its homologous sequences in other genomes stored in databases.…”

Section: Introductionmentioning

confidence: 99%

Hidden Markov models for gene sequence classification

Mesa¹,

Basterrech²,

Guerberoff³

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

The article presents an application of Hidden Markov Models (HMMs) for pattern recognition on genome sequences. We apply HMM for identifying genes encoding the Variant Surface Glycoprotein (VSG) in the genomes of Trypanosoma brucei (T. brucei) and other African trypanosomes. These are parasitic protozoa causative agents of sleeping sickness and several diseases in domestic and wild animals. These parasites have a peculiar strategy to evade the host's immune system that consists in periodically changing their predominant cellular surface protein (VSG). The motivation for using patterns recognition methods to identify these genes, instead of traditional homology based ones, is that the levels of sequence identity (amino acid and DNA sequence) amongst these genes is often below of what is considered reliable in these methods. Among pattern recognition approaches, HMM are particularly suitable to tackle this problem because they can handle more naturally the determination of gene edges. We evaluate the performance of the model using different number of states in the Markov model, as well as several performance metrics. The model is applied using public genomic data. Our empirical results show that the VSG genes on T. brucei can be safely identified (high sensitivity and low rate of false positives) using HMM.

show abstract

A Brief Review of Computational Gene Prediction Methods

Cited by 87 publications

References 28 publications

Generic eukaryotic core promoter prediction using structural features of DNA

Generic eukaryotic core promoter prediction using structural features of DNA

A reduced computational load protein coding predictor using equivalent amino acid sequence of DNA string with period-3 based time and frequency domain analysis

Hidden Markov models for gene sequence classification

Contact Info

Product

Resources

About