StackTIS: A stacked generalization approach for effective prediction of translation initiation sites

Tzanis, George; Berberidis, Christos; Vlahavas, Ioannis

doi:10.1016/j.compbiomed.2011.10.009

Cited by 8 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first is to prove the significance of hybrid encoding. In the second experiment, we make a comparison of the proposed method to existing state-of-art methods such as C4+MLP Hatzigeorgiou et al (1996), C4+SVM Shuo and Yi-sheng (2009), Z curve+LDA Zhang et al (1998), kmer+MLP Guigó (1997); Hatzigeorgiou (2002), kmer+SVM Tzanis et al (2012), kmer+BRNN Chao Wei (2020). The goal of the last experiment is to evaluate the time cost of the proposed method.…”

Section: Resultsmentioning

confidence: 99%

“…Many existing computational methods Hatzigeorgiou, Mache and Reczko (1996); Guigó (1997); Zhang, Lin, Yan and Zhang (1998); Hatzigeorgiou (2002); Shuo and Yi-sheng (2009); Tzanis, Berberidis and Vlahavas (2012); Chao Wei (2020) have been proposed for protein coding regions prediction in genomic or transcript sequence during the past decades. They first encode a biological sequence into numerical values and then feed them into a classifier for final prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Resultsmentioning

confidence: 99%

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

show abstract

“…StackTIS is a Stacking ‐based methodology whose objective is the detection of potential translation initiation sites (TISs). The proposed model is based on the combination of three different classifiers, where each classifier learns from data described by different attributes.…”

Section: Stacking Variants and Related Approachesmentioning

confidence: 99%

Generating ensembles of heterogeneous classifiers using Stacked Generalization

Sesmero

Ledezma

Sanchís

2015

WIREs Data Min & Knowl

128

View full text Add to dashboard Cite

Over the last two decades, the machine learning and related communities have conducted numerous studies to improve the performance of a single classifier by combining several classifiers generated from one or more learning algorithms. Bagging and Boosting are the most representative examples of algorithms for generating homogeneous ensembles of classifiers. However, Stacking has become a commonly used technique for generating ensembles of heterogeneous classifiers since Wolpert presented his study entitled Stacked Generalization in 1992. Studies that have addressed the Stacking issue demonstrated that when selecting base learning algorithms for generating classifiers that are members of the ensemble, their learning parameters and the learning algorithm for generating the meta-classifier were critical issues. Most studies on this topic manually select the appropriate combination of base learning algorithms and their learning parameters. However, some other methods use automatic methods to determine good Stacking configurations instead of starting from these strong initial assumptions. In this paper, we describe Stacking and its variants and present several examples of application domains.

show abstract

“…The experimental studies should be performed to clarify this question. Several methods may be used to predict translation starts − StackTIS, 46 MetWAMer, 47 and MetaProdigal. 48 The occurrence of alternative transcripts can be associated with the possibility of translation using alternative reading frames (ARFs) that may lead to the synthesis of completely distinct proteins.…”

Section: Identification Of Functional Amino Acid Signaturesmentioning

confidence: 99%

Tissue-Specific Alternative Splicing Analysis Reveals the Diversity of Chromosome 18 Transcriptome

et al. 2013

View full text Add to dashboard Cite

The Chromosome-centric Human Proteome Project (C-HPP) is aimed to identify the variety of protein products and transcripts of the number of chromosomes. The Russian part of C-HPP is devoted to the study of the human chromosome 18. Using widely accepted Tophat and SpliceGrapher, a tool for accurate splice sites and alternative mRNA isoforms prediction, we performed the extensive mining of the splice variants of chromosome 18 transcripts and encoded protein products in liver, brain, lung, kidney, blood, testis, derma, and skeletal muscles. About 6.1 billion of the reads represented by 450 billion of the bases have been analyzed. The relative frequencies of splice events as well as gene expression profiles in normal tissues are evaluated. Using ExPASy PROSITE, the novel features and possible functional sites of previously unknown splice variants were highlighted. A set of unique proteotypic peptides enabling the identification of novel alternative protein species using mass-spectrometry is constructed. The revealed data will be integrated into the gene-centric knowledgebase of the Russian part of C-HPP available at http://kb18.ru and http://www.splicing.zz.mu/.

show abstract

StackTIS: A stacked generalization approach for effective prediction of translation initiation sites

Cited by 8 publications

References 22 publications

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

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

Generating ensembles of heterogeneous classifiers using Stacked Generalization

Tissue-Specific Alternative Splicing Analysis Reveals the Diversity of Chromosome 18 Transcriptome

Contact Info

Product

Resources

About

StackTIS: A stacked generalization approach for effective prediction of translation initiation sites

Cited by 8 publications

References 22 publications

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

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

Generating ensembles of heterogeneous classifiers using Stacked Generalization

Tissue-Specific Alternative Splicing Analysis Reveals the Diversity of Chromosome 18 Transcriptome

Contact Info

Product

Resources

About

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

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