A comparative analysis of soft computing techniques for gene prediction

Deep Splicer: A CNN Model for Splice Site Prediction in Genetic Sequences

Many living organisms have DNA in their cells that is responsible for their biological features. DNA is an organic molecule of two complementary strands of four different nucleotides wound up in a double helix. These nucleotides are adenine (A), thymine (T), guanine (G), and cytosine (C). Genes are DNA sequences containing the information to synthesize proteins. The genes of higher eukaryotic organisms contain coding sequences, known as exons and non-coding sequences, known as introns, which are removed on splice sites after the DNA is transcribed into RNA. Genome annotation is the process of identifying the location of coding regions and determining their function. This process is fundamental for understanding gene structure; however, it is time-consuming and expensive when done by biochemical methods. With technological advances, splice site detection can be done computationally. Although various software tools have been developed to predict splice sites, they need to improve accuracy and reduce false-positive rates. The main goal of this research was to generate Deep Splicer, a deep learning model to identify splice sites in the genomes of humans and other species. This model has good performance metrics and a lower false-positive rate than the currently existing tools. Deep Splicer achieved an accuracy between 93.55% and 99.66% on the genetic sequences of different organisms, while Splice2Deep, another splice site detection tool, had an accuracy between 90.52% and 98.08%. Splice2Deep surpassed Deep Splicer on the accuracy obtained after evaluating C. elegans genomic sequences (97.88% vs. 93.62%) and A. thaliana (95.40% vs. 94.93%); however, Deep Splicer's accuracy was better for H. sapiens (98.94% vs. 97.15%) and D. melanogaster (97.14% vs. 92.30%). The rate of false positives was 0.11% for human genetic sequences and 0.25% for other species' genetic sequences. Another splice prediction tool, Splice Finder, had between 1% and 3% of false positives for human sequences, while other species' sequences had around 4% and 10%.

PhyloPrimer: a taxon-specific oligonucleotide design platform

Many environmental and biomedical biomonitoring and detection studies aim to explore the presence of specific organisms or gene functionalities in microbiome samples. In such cases, when the study hypotheses can be answered with the exploration of a small number of genes, a targeted PCR-approach is appropriate. However, due to the complexity of environmental microbial communities, the design of specific primers is challenging and can lead to non-specific results. We designed PhyloPrimer, the first user-friendly platform to semi-automate the design of taxon-specific oligos (i.e., PCR primers) for a gene of interest. The main strength of PhyloPrimer is the ability to retrieve and align GenBank gene sequences matching the user’s input, and to explore their relationships through an online dynamic tree. PhyloPrimer then designs oligos specific to the gene sequences selected from the tree and uses the tree non-selected sequences to look for and maximize oligo differences between targeted and non-targeted sequences, therefore increasing oligo taxon-specificity (positive/negative consensus approach). Designed oligos are then checked for the presence of secondary structure with the nearest-neighbor (NN) calculation and the presence of off-target matches with in silico PCR tests, also processing oligos with degenerate bases. Whilst the main function of PhyloPrimer is the design of taxon-specific oligos (down to the species level), the software can also be used for designing oligos to target a gene without any taxonomic specificity, for designing oligos from preselected sequences and for checking predesigned oligos. We validated the pipeline on four commercially available microbial mock communities using PhyloPrimer to design genus- and species-specific primers for the detection of Streptococcus species in the mock communities. The software performed well on these mock microbial communities and can be found at https://www.cerealsdb.uk.net/cerealgenomics/phyloprimer.

Splice sites detection using chaos game representation and neural network

A novel method is proposed to detect the acceptor and donor splice sites using chaos game representation and artificial neural network. In order to achieve high accuracy, inputs to the neural network, or feature vector, shall reflect the true nature of the DNA segments. Therefore it is important to have one-to-one numerical representation, i.e. a feature vector should be able to represent the original data. Chaos game representation (CGR) is an iterative mapping technique that assigns each nucleotide in a DNA sequence to a respective position on the plane in a one-to-one manner. Using CGR, a DNA sequence can be mapped to a numerical sequence that reflects the true nature of the original sequence. In this research, we propose to use CGR as feature input to a neural network to detect splice sites on the NN269 dataset. Computational experiments indicate that this approach gives good accuracy while being simpler than other methods in the literature, with only one neural network component. The code and data for our method can be accessed from this link: https://github.com/thoang3/portfolio/tree/SpliceSites_ANN_CGR.

Prediction of DNA sequences using adaptative neuro-fuzzy inference system

Accurate prediction and detection of the DNA regions or their underlying structural patterns are constant difficulties for researchers. Feature extraction and functional classification of genomic sequences is an interesting area of research. Many computational techniques have already been applied including the artificial neural network (ANN), nonlinear model, spectrogram and statistical techniques. In this paper, some features are extracted from the wavelet coefficient and second set of features are extracted from the frequency of transition of nucleotides. These two features sets are examined. The purpose was to investigate the abilities of these parameters to predict critical segment in the DNA sequence. The neuro-fuzzy system was used for prediction. The performance of the neuro-fuzzy system was evaluated in terms of training performance and prediction accuracies. Two genomic sequences of the classes: prokaryotic and eukaryotic were used, as an example, (Escherichia coli) and (Caenorhabditis elegans) sequences were selected.

Consideration of non-canonical splice sites improves gene prediction on the Arabidopsis thaliana Niederzenz-1 genome sequence

Objective

The Arabidopsis thaliana Niederzenz-1 genome sequence was recently published with an ab initio gene prediction. In depth analysis of the predicted gene set revealed some errors involving genes with non-canonical splice sites in their introns. Since non-canonical splice sites are difficult to predict ab initio, we checked for options to improve the annotation by transferring annotation information from the recently released Columbia-0 reference genome sequence annotation Araport11.

Results

Incorporation of hints generated from Araport11 enabled the precise prediction of non-canonical splice sites. Manual inspection of RNA-Seq read mapping and RT-PCR were applied to validate the structural annotations of non-canonical splice sites. Predictions of untranslated regions were also updated by harnessing the potential of Araport11’s information, which was generated by using high coverage RNA-Seq data. The improved gene set of the Nd-1 genome assembly (GeneSet_Nd-1_v1.1) was evaluated via comparison to the initial gene prediction (GeneSet_Nd-1_v1.0) as well as against Araport11 for the Col-0 reference genome sequence. GeneSet_Nd-1_v1.1 contains previously missed non-canonical splice sites in 1256 genes. Reciprocal best hits for 24,527 (89.4%) of all nuclear Col-0 genes against the GeneSet_Nd-1_v1.1 indicate a high gene prediction quality.

Electronic supplementary material

The online version of this article (10.1186/s13104-017-2985-y) contains supplementary material, which is available to authorized users.

An optimized approach for annotation of large eukaryotic genomic sequences using genetic algorithm

BACKGROUND

Detection of important functional and/or structural elements and identification of their positions in a large eukaryotic genomic sequence are an active research area. Gene is an important functional and structural unit of DNA. The computation of gene prediction is, therefore, very essential for detailed genome annotation.

RESULTS

In this paper, we propose a new gene prediction technique based on Genetic Algorithm (GA) to determine the optimal positions of exons of a gene in a chromosome or genome. The correct identification of the coding and non-coding regions is difficult and computationally demanding. The proposed genetic-based method, named Gene Prediction with Genetic Algorithm (GPGA), reduces this problem by searching only one exon at a time instead of all exons along with its introns. This representation carries a significant advantage in that it breaks the entire gene-finding problem into a number of smaller sub-problems, thereby reducing the computational complexity. We tested the performance of the GPGA with existing benchmark datasets and compared the results with well-known and relevant techniques. The comparison shows the better or comparable performance of the proposed method. We also used GPGA for annotating the human chromosome 21 (HS21) using cross-species comparisons with the mouse orthologs.

CONCLUSION

It was noted that the GPGA predicted true genes with better accuracy than other well-known approaches.

Physico-chemical fingerprinting of RNA genes

We advance here a novel concept for characterizing different classes of RNA genes on the basis of physico-chemical properties of DNA sequences. As knowledge-based approaches could yield unsatisfactory outcomes due to limitations of training on available experimental data sets, alternative approaches that utilize properties intrinsic to DNA are needed to supplement training based methods and to eventually provide molecular insights into genome organization. Based on a comprehensive series of molecular dynamics simulations of Ascona B-DNA consortium, we extracted hydrogen bonding, stacking and solvation energies of all combinations of DNA sequences at the dinucleotide level and calculated these properties for different types of RNA genes. Considering ∼7.3 million mRNA, 255 524 tRNA, 40 649 rRNA (different subunits) and 5250 miRNA, 3747 snRNA, gene sequences from 9282 complete genome chromosomes of all prokaryotes and eukaryotes available at NCBI, we observed that physico-chemical properties of different functional units on genomic DNA differ in their signatures.

Seqping: gene prediction pipeline for plant genomes using self-training gene models and transcriptomic data

BACKGROUND

Gene prediction is one of the most important steps in the genome annotation process. A large number of software tools and pipelines developed by various computing techniques are available for gene prediction. However, these systems have yet to accurately predict all or even most of the protein-coding regions. Furthermore, none of the currently available gene-finders has a universal Hidden Markov Model (HMM) that can perform gene prediction for all organisms equally well in an automatic fashion.

RESULTS

We present an automated gene prediction pipeline, Seqping that uses self-training HMM models and transcriptomic data. The pipeline processes the genome and transcriptome sequences of the target species using GlimmerHMM, SNAP, and AUGUSTUS pipelines, followed by MAKER2 program to combine predictions from the three tools in association with the transcriptomic evidence. Seqping generates species-specific HMMs that are able to offer unbiased gene predictions. The pipeline was evaluated using the Oryza sativa and Arabidopsis thaliana genomes. Benchmarking Universal Single-Copy Orthologs (BUSCO) analysis showed that the pipeline was able to identify at least 95% of BUSCO's plantae dataset. Our evaluation shows that Seqping was able to generate better gene predictions compared to three HMM-based programs (MAKER2, GlimmerHMM and AUGUSTUS) using their respective available HMMs. Seqping had the highest accuracy in rice (0.5648 for CDS, 0.4468 for exon, and 0.6695 nucleotide structure) and A. thaliana (0.5808 for CDS, 0.5955 for exon, and 0.8839 nucleotide structure).

CONCLUSIONS

Seqping provides researchers a seamless pipeline to train species-specific HMMs and predict genes in newly sequenced or less-studied genomes. We conclude that the Seqping pipeline predictions are more accurate than gene predictions using the other three approaches with the default or available HMMs.

Well-characterized sequence features of eukaryote genomes and implications for ab initio gene prediction

In silico analysis of DNA sequences is an important area of computational biology in the post-genomic era. Over the past two decades, computational approaches for ab initio prediction of gene structure from genome sequence alone have largely facilitated our understanding on a variety of biological questions. Although the computational prediction of protein-coding genes has already been well-established, we are also facing challenges to robustly find the non-coding RNA genes, such as miRNA and lncRNA. Two main aspects of ab initio gene prediction include the computed values for describing sequence features and used algorithm for training the discriminant function, and by which different combinations are employed into various bioinformatic tools. Herein, we briefly review these well-characterized sequence features in eukaryote genomes and applications to ab initio gene prediction. The main purpose of this article is to provide an overview to beginners who aim to develop the related bioinformatic tools.

A Review of Computational Intelligence Methods for Eukaryotic Promoter Prediction

In past decades, prediction of genes in DNA sequences has attracted the attention of many researchers but due to its complex structure it is extremely intricate to correctly locate its position. A large number of regulatory regions are present in DNA that helps in transcription of a gene. Promoter is one such region and to find its location is a challenging problem. Various computational methods for promoter prediction have been developed over the past few years. This paper reviews these promoter prediction methods. Several difficulties and pitfalls encountered by these methods are also detailed, along with future research directions.

Deciphering the association between gene function and spatial gene-gene interactions in 3D human genome conformation

BACKGROUND

A number of factors have been investigated in the context of gene function prediction and analysis, such as sequence identity, gene expressions, and gene co-evolution. However, three-dimensional (3D) conformation of the genome has not been tapped to analyse gene function, probably largely due to lack of genome conformation data until recently.

METHODS

We construct the genome-wide spatial gene-gene interaction networks for three different human B-cells or cell lines from their chromosomal contact data generated by the Hi-C chromosome conformation capturing technique. The G-SESAME and Fast-SemSim are used to calculate function similarity between interacted / non-interacted genes. The Gene Ontology statistics computed from the gene-gene interaction networks is used for gene function prediction.

RESULTS

We compare the function similarity of gene pairs that do not spatially interact and that have interactions. We find that genes that have strong spatial interactions tend to have highly similar function in terms of biological process, molecular function and cellular component of the Gene Ontology. And even though the level of gene-gene interactions generally have no or weak correlation with either sequential genomic distance or sequence identity between genes, the interacted genes with high function similarity tend to have stronger interactions, somewhat shorter genomic distance and significantly higher sequence identity. And combining genomic distance or sequence identity with spatial gene-gene interaction information informs gene-gene function similarity much better than using either one of them alone, suggesting gene-gene interaction information is largely complementary with genomic distance and sequence identity in the context of gene function analysis. We develop and evaluate a new gene function prediction method based on gene-gene interacting networks, which can predict gene function well for a large number of human genes.

CONCLUSIONS

In this work, we demonstrate that the spatial conformation of the human genome is relevant to gene function similarity and is useful for gene function prediction.

Gene identification programs in bread wheat: a comparison study

Seven ab initio web-based gene prediction programs (i.e., AUGUSTUS, BGF, Fgenesh, Fgenesh+, GeneID, Genemark.hmm, and HMMgene) were assessed to compare their prediction accuracy using protein-coding sequences of bread wheat. At both nucleotide and exon levels, Fgenesh+ was deduced as the superior program and BGF followed by Fgenesh were resided in the next positions, respectively. Conversely, at gene level, Fgenesh with the value of predicting more than 75% of all the genes precisely, concluded as the best ones. It was also found out that programs such as Fgenesh+, BGF, and Fgenesh, because of harboring the highest percentage of correct predictive exons appear to be much more applicable in achieving more trustworthy results, while using both GeneID and HMMgene the percentage of false negatives would be expected to enhance. Regarding initial exon, overall, the frequency of accurate recognition of 3' boundary was significantly higher than that of 5' and the reverse was true if terminal exon is taken into account. Lastly, HMMgene and Genemark.hmm, overall, presented independent tendency against GC content, while the others appear to be slightly more sensitive if GC-poor sequences are employed. Our results, overall, exhibited that to make adequate opportunity in acquiring remarkable results, gene finders still need additional improvements.