Identification of long non-coding transcripts with feature selection: a comparative study

Ventola, Giovanna Maria; Noviello, Teresa Maria Rosaria; D’Aniello, Salvatore; Ceccarelli, Michele; Cerulo, Luigi

doi:10.1186/s12859-017-1594-z

Cited by 22 publications

(13 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each ChIP-seq sample is described by a comprehensive set of 245 quantitative features (QC-metrics), including LM, EM and GM. To remove uninformative features before training the machine learning models, we applied a feature selection procedure similar to [33] on each set of QC-metrics separately. After standardizing each QC quantitative feature (subtracting mean and dividing by standard deviation) for EM, GM and LM separately, we applied hierarchical clustering ("complete linkage") based on the distance measure !…”

Section: Feature Correlation and Principal Component Analysismentioning

confidence: 99%

A ChIC solution for ChIP-seq quality assessment

Livi

Tagliaferri

Pal

et al. 2020

Preprint

View full text Add to dashboard Cite

Despite the widespread adoption of the ChIP-seq technique, there is still no consensus on quality assessment procedures. Quantitative metrics previously proposed in literature are not always effective in discriminating the success or failure of an experiment, thus hampering objectivity and reproducibility of quality control. Here we introduce ChIC, a new framework for ChIP-seq data quality assessment that overcomes the limitations of previous solutions.ChIC is the first method for ChIP-seq quality control directly considering the enrichment profile shape, thus achieving good performances on ChIP targets yielding sharp and broad peaks alike. We integrate a comprehensive set of quality control metrics into one single score reliably summarizing the sample quality. The ChIC score is based on a machine learning classifier trained on a compendium with thousands of ChIP-seq profiles, which can also be used as a reference for easier evaluation of new datasets. ChIC is implemented as a user-friendly R/Bioconductor package. RESULTS Standard QC-metrics are biased by the shape of ChIP-seq enrichment profileWe analysed a large set of ChIP-seq experiments with paired input control, for a total of 3936 samples from large public databases (Table 1), including the ENCODE project [23] and Roadmap Epigenomics Consortium (Roadmap) [24], to build a reference compendium of QC-metrics, including previously proposed and novel metrics (Fig. 1a).Previously proposed QC quantitative metrics for ChIP-seq do not explicitly take into account the shape of the enrichment profile, yet this is affecting the QC score values. For example, some of the QC-metrics proposed by the ENCODE consortium are more effective on ChIP targets yielding narrow peak profiles, such as TFs, because they are designed for ChIP-seq enrichment profiles with sequencing reads localized in small regions. This is the case for all the metrics based on strand-shift analyses [3,4,7,10,11]. Strand-shift analyses, such as the "cross-correlation" analysis (Supplementary Figure S1a; methods), aim to detect the clustering of reads in a ChIP-seq sample without relying on peak calling. The strand-shift profile is calculated using the position of reads on positive vs negative strand and shifting them towards each other. At each progressive shift the correlation [3,4] between the position of reads on the two strands is calculated. In other variants of this analysis, other measures like the Jaccard Index [7] or the Hamming distance [15] have been proposed instead to quantify the clustering of reads on positive and negative strands. Then, multiple QC-metrics for the strength of the ChIP enrichment can be derived from the resulting crosscorrelation profile, for example the normalized or relative strand coefficient (NSC and RSC, respectively) or the quality control tag (QC tag) [3,4,11]. We refer to this set of metrics, along with others described by Landt et al. [3], as ENCODE Metrics (EM) (see methods).Notably, the relative strand coefficient (RSC) is proportional to the level of clusterin...

show abstract

Section: Feature Correlation and Principal Component Analysismentioning

confidence: 99%

A ChIC solution for ChIP-seq quality assessment

Livi

Tagliaferri

Pal

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Long non-coding RNAs (lncRNAs) are gaining attention because of critical biological functions suggested by recent studies (for a review see (Mercer, Dinger & Mattick, 2009)). Some of the ML applications found included the detection of cancer-related lncRNA (Zhang et al, 2018), the discrimination of circular RNAs from other lncRNAs (Chen et al, 2018), and selection of the most informative features of lncRNA (Ventola et al, 2017). Other applications in the RNA field address the identification and clustering of RNA structure motifs (Smith et al, 2017),…”

Section: Architectures and Algorithms Currently Used For Tes Or Simentioning

confidence: 99%

“…PRISMA flow diagram Publication identifier Year Q1 Q2 Q3 Q4 Reference Publication identifier Year Q1 Q2 Q3 Q4 Reference P1 X X X X (Yu, Yu & Pan, 2017) P19 2013 X X X (Loureiro et al, 2013b) P2 X X X (Schietgat et al, 2018) P20 2014 X X (Ma, Zhang & Wang, 2014) P3 X X X (Arango-López et al, 2017) P21 2010 X X (Dashti & Masoudi-Nejad, 2010) P4 X X X (Loureiro et al, 2013a) P22 2010 X X (Ding, Zhou & Guan, 2010) P5 X X X (Tsafnat et al, 2011) P23 2019 X (Jaiswal & Krishnamachari, 2019) P6 X X X (Zhang et al, 2018) P24 2015 X X X X (Girgis, 2015) P7 X X X (Eraslan et al, 2019) P25 2018 X X X (Nakano et al, 2018a) P8 X X X (Douville et al, 2018) P26 2018 X X X (Zamith Santos et al, 2018) P9 X X (Chen et al, 2018) P27 2009 X (Abrusan et al, 2009) P10 X X X X (Ashlock & Datta, 2012) P28 2019 X X (Su, Gu & Peterson, 2019) P11 X X X (Smith et al, 2017) P29 2017 X X X X (Nakano et al, 2017) P12 X X X X (Kamath, De Jong & Shehu, 2014) P30 2014 X X X (Brayet et al, 2014) P13 X X X (Kim et al, 2016) P31 2013 X (Zamani et al, 2013) P14 X X X (Segal et al, 2018) P32 2019 X (Hubbard et al, 2019) P15 X X X (Rawal & Ramaswamy, 2011) P33 2014 X X (Ryvkin et al, 2014) P16 X X X (Tang et al, 2017) P34 2013 X X X X (Zhang et al, 2013) P17 X X X (Ventola et al, 2017) P35 2019 X X…”

Section: Figurementioning

confidence: 99%

“…TEs have been found in all organisms and comprise the majority of the nuclear DNA content of plant genomes (Orozco-arias et al, 2018), such as in wheat, barley, and maize. In these species, up to 85% of the sequenced DNA is classified into repeated sequences (Choulet et al, 2014), of which TEs represent the most abundant and functionally relevant type (Ventola et al, 2017). Due to the high diversity of TE structures and transposition mechanisms, there are still numerous classification problems and debates on the classification systems (Piégu et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Peer Review #1 of "A systematic review of the application of machine learning in the detection and classification of transposable elements (v0.1)"

2019

View full text Add to dashboard Cite

Background. Transposable elements (TEs) constitute the most common repeated sequences in eukaryotic genomes. Recent studies demonstrated their deep impact on species diversity, adaptation to the environment, and diseases. Although there are many conventional bioinformatics algorithms for detecting and classifying TEs, none have achieved reliable results on different types of TEs. Machine learning (ML) techniques can automatically extract hidden patterns and novel information from labeled or non-labeled data and have been applied to solving several scientific problems. Methodology. We followed the Systematic Literature Review process, applying the six stages of the review protocol from it, but added a previous stage, which aims to detect the need for a review. Then search equations were formulated and executed in several literature databases. Relevant publications were scanned and used to extract evidence to answer research questions. Results. Several ML approaches have already been tested on other bioinformatics problems with promising results, yet there are few algorithms and architectures available in literature focused specifically on TEs, despite representing the majority of the nuclear DNA of many organisms. Only 35 papers were found and categorized as relevant in TE or related fields. Conclusions. ML is a powerful tool that can be used to address many problems. Although ML techniques have been used widely in other biological tasks, their utilization in TE analyses is still limited. Following the Systematic Literature Review process, it was possible to notice that the use of ML for TE analyses (detection and classification) is an open problem, and this new field of research is growing in interest.

show abstract

“…TEs have been found in all organisms and comprise the majority of the nuclear DNA content of plant genomes (Orozco-Arias et al, 2018), such as in wheat, barley and maize. In these species, up to 85% of the sequenced DNA is classified into repeated sequences (Choulet et al, 2014), of which TEs represent the most abundant and functionally relevant type (Ventola et al, 2017). Due to the high diversity of TE structures and transposition mechanisms, there are still numerous classification problems and debates on the classification systems (Piégu et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

A systematic review of the application of machine learning in the detection and classification of transposable elements

Orozco-Arias

Isaza

Guyot

et al. 2019

PeerJ

View full text Add to dashboard Cite

Background Transposable elements (TEs) constitute the most common repeated sequences in eukaryotic genomes. Recent studies demonstrated their deep impact on species diversity, adaptation to the environment and diseases. Although there are many conventional bioinformatics algorithms for detecting and classifying TEs, none have achieved reliable results on different types of TEs. Machine learning (ML) techniques can automatically extract hidden patterns and novel information from labeled or non-labeled data and have been applied to solving several scientific problems. Methodology We followed the Systematic Literature Review (SLR) process, applying the six stages of the review protocol from it, but added a previous stage, which aims to detect the need for a review. Then search equations were formulated and executed in several literature databases. Relevant publications were scanned and used to extract evidence to answer research questions. Results Several ML approaches have already been tested on other bioinformatics problems with promising results, yet there are few algorithms and architectures available in literature focused specifically on TEs, despite representing the majority of the nuclear DNA of many organisms. Only 35 articles were found and categorized as relevant in TE or related fields. Conclusions ML is a powerful tool that can be used to address many problems. Although ML techniques have been used widely in other biological tasks, their utilization in TE analyses is still limited. Following the SLR, it was possible to notice that the use of ML for TE analyses (detection and classification) is an open problem, and this new field of research is growing in interest.

show abstract

Identification of long non-coding transcripts with feature selection: a comparative study

Cited by 22 publications

References 68 publications

A ChIC solution for ChIP-seq quality assessment

A ChIC solution for ChIP-seq quality assessment

Peer Review #1 of "A systematic review of the application of machine learning in the detection and classification of transposable elements (v0.1)"

A systematic review of the application of machine learning in the detection and classification of transposable elements

Contact Info

Product

Resources

About