Computational Approaches for Gene Prediction: A Comparative Survey

Al-Turaiki, Israa; Mathkour, Hassan; Touir, Ameur; Hammami, Saleh

doi:10.1007/978-3-642-25453-6_2

Cited by 7 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies, which have evaluated prokaryotic CDS predictors generally only compared a small number of tools, focussing on algorithm design, and did not go into depth when reporting prediction accuracy with few other informative metrics used (Al-Turaiki et al, 2011;Mathe ´et al, 2002). A more recent study, BEACON (Kalkatawi et al, 2015), considered a small range of metrics including genes 'denoted as identical, similar, unique with overlap or unique without overlap' to either a reference annotation or from the output of three pipelines (PGAP, AAMG and RAST).…”

Section: Introductionmentioning

confidence: 99%

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

et al. 2021

View full text Add to dashboard Cite

Motivation The biases in CoDing Sequence (CDS) prediction tools, which have been based on historic genomic annotations from model organisms, impact our understanding of novel genomes and metagenomes. This hinders the discovery of new genomic information as it results in predictions being biased towards existing knowledge. To date, users have lacked a systematic and replicable approach to identify the strengths and weaknesses of any CoDing Sequence (CDS) prediction tool and allow them to choose the right tool for their analysis. Results We present an evaluation framework (ORForise) based on a comprehensive set of 12 primary and 60 secondary metrics that facilitate the assessment of the performance of CDS prediction tools. This makes it possible to identify which performs better for specific use-cases. We use this to assess 15 ab initio and model-based tools representing those most widely used (historically and currently) to generate the knowledge in genomic databases. We find that the performance of any tool is dependent on the genome being analysed, and no individual tool ranked as the most accurate across all genomes or metrics analysed. Even the top-ranked tools produced conflicting gene collections which could not be resolved by aggregation. The ORForise evaluation framework provides users with a replicable, data-led approach to make informed tool choices for novel genome annotations and for refining historical annotations. Availability https://github.com/NickJD/ORForise Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Introductionmentioning

confidence: 99%

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For more work on gene prediction using supervised learning, see the survey by Al-Turaiki et al . [19]. However, one major drawback of these supervised algorithms is that they typically require large amounts of labeled data to train a classifier.…”

Section: Related Workmentioning

confidence: 99%

A Study of Domain Adaptation Classifiers Derived From Logistic Regression for the Task of Splice Site Prediction

Herndon

Caragea

2016

IEEE Trans.on Nanobioscience

View full text Add to dashboard Cite

Supervised classifiers are highly dependent on abundant labeled training data. Alternatives for addressing the lack of labeled data include: labeling data (but this is costly and time consuming); training classifiers with abundant data from another domain (however, the classification accuracy usually decreases as the distance between domains increases); or complementing the limited labeled data with abundant unlabeled data from the same domain and learning semi-supervised classifiers (but the unlabeled data can mislead the classifier). A better alternative is to use both the abundant labeled data from a source domain, the limited labeled data and optionally the unlabeled data from the target domain to train classifiers in a domain adaptation setting. We propose two such classifiers, based on logistic regression, and evaluate them for the task of splice site prediction – a difficult and essential step in gene prediction. Our classifiers achieved high accuracy, with highest areas under the precision-recall curve between 50.83% and 82.61%.

show abstract

“…The prediction of protein coding regions in genomic or transcript sequences is a very important but overlooked subtask for genome annotation. Many well-known gene prediction tools (e.g., GenScan Burge and Karlin (1997), Augustus Stanke, Steinkamp, Waack and Morgenstern (2004)) are integrated models, in which the task of identifying gene structure is first divided into subtasks such as the prediction of functional sites and coding regions, and then these subtasks are integrated in a structured learning framework for the prediction of gene structure Al-Turaiki, Mathkour, Touir and Hammami (2011). Moreover, coding features is also very important for computational methods to discriminate mRNAs from long non-coding RNAs Li, Zhang and Zhou (2014); Tong and Liu (2019).…”

Section: Introductionmentioning

confidence: 99%

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★

Wei

Zhang

Yuan

2020

Preprint

View full text Add to dashboard Cite

Protein coding regions prediction is a very important but overlooked subtask for tasks such as prediction of complete gene structure, coding/noncoding RNA. Many machine learning methods have been proposed for this problem, they first encode a biological sequence into numerical values and then feed them into a classifier for final prediction. However, encoding schemes directly influence the classifier capability to capture coding features and how to choose a proper encoding scheme remains uncertain. Recently, we proposed a protein coding region prediction method in transcript sequences based on a bidirectional recurrent neural network with non-overlapping kmer, and achieved considerable improvement over existing methods, but there is still much room to improve the performance. In fact, kmer features that count the occurrence frequency of trinucleotides only reflect the local sequence order information between the most contiguous nucleotides, which loses almost all the global sequence order information. In viewing of the point, we here present a deep learning framework with hybrid encoding for protein coding regions prediction in biological sequences, which effectively exploiting global sequence order information, non-overlapping kmer features and statistical dependencies among coding labels. Evaluated on genomic and transcript sequences, our proposed method significantly outperforms existing state-of-the-art methods.

show abstract

Computational Approaches for Gene Prediction: A Comparative Survey

Cited by 7 publications

References 32 publications

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

A Study of Domain Adaptation Classifiers Derived From Logistic Regression for the Task of Splice Site Prediction

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★

Contact Info

Product

Resources

About

Computational Approaches for Gene Prediction: A Comparative Survey

Cited by 7 publications

References 32 publications

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

No one tool to rule them all: prokaryotic gene prediction tool annotations are highly dependent on the organism of study

A Study of Domain Adaptation Classifiers Derived From Logistic Regression for the Task of Splice Site Prediction

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding★,★★

Contact Info

Product

Resources

About

Enhancing the prediction of protein coding regions in biological sequence via a deep learning framework with hybrid encoding^★,★★