SENMAP: A Convolutional Neural Network Architecture for Curation of LTR-RT Libraries from Plant Genomes

Orozco-Arias, Simón; Candamil-Cortés, Mariana S.; Valencia-Castrillon, Estiven; Jaimes, Paula A.; Orozco, Nicolás Tobón; Arias-Mendoza, Maradey; Tabares-Soto, Reinel; Guyot, Romain; Isaza, Gustavo

doi:10.1109/ci-ibbi54220.2021.9626130

Cited by 2 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a pipeline to de novo annotate TEs included multiple steps to deal with some specific limitations of raw libraries, in particular the presence of redundant and fragmented consensus (Baril et al 2022). Machine learning approaches have also been implemented to automatically curate particular TE orders in plants (Orozco-Arias et al 2021. Thus, previous attempts at automation were partial and still required substantial time investment by the researcher.…”

Section: Discussionmentioning

confidence: 99%

“…Due to the increasing interest in TE biology, several friendly-user manuals have been recently published (Baril et al, 2022;Goubert et al, 2022;Jamilloux et al, 2016;Platt et al, 2016; J. M. Storer et al, , 2022. Additionally, some specific tools to aid in the manual curation have also been produced (Baril et al, 2022;Goubert et al, 2022;Orozco-Arias, et al, 2021;. Still, manual curation of TE libraries is time-consuming and requires acquiring knowledge on the biology of TEs present in the genomes of interest.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MCHelper automatically curates transposable element libraries across eukaryotic species

Orozco-Arias,

Sierra,

Durbin

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The number of species with high quality genome sequences continues to increase, in part due to scaling up of multiple large scale biodiversity sequencing projects. While the need to annotate genic sequences in these genomes is widely acknowledged, the parallel need to annotate transposable element sequences that have been shown to alter genome architecture, rewire gene regulatory networks, and contribute to the evolution of host traits is becoming ever more evident. However, accurate genome-wide annotation of transposable element sequences is still technically challenging. Several de novo transposable element identification tools are now available, but manual curation of the libraries produced by these tools is needed to generate high quality genome annotations. Manual curation is time-consuming, and thus impractical for large-scale genomic studies, and lacks reproducibility. In this work, we present the Manual Curator Helper tool MCHelper, which automates the TE library curation process. By leveraging MCHelper's fully automated mode with the outputs from two de novo transposable element identification tools, RepeatModeler2 and REPET, in fruit fly, rice, and zebrafish, we show a substantial improvement in the quality of the transposable element libraries and genome annotations. MCHelper libraries are less redundant, with up to 54% reduction in the number of consensus sequences, have up to 11.4% fewer false positive sequences, and also have up to ~45% fewer unclassified/unknown transposable element consensus sequences. Genome-wide transposable element annotations were also improved, including larger unfragmented insertions. MCHelper is a fast, easy to install, and easy to use tool and is available at https://github.com/GonzalezLab/MCHelper.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MCHelper automatically curates transposable element libraries across eukaryotic species

Orozco-Arias,

Sierra,

Durbin

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Genomic object detection: An improved approach for transposable elements detection and classification using convolutional neural networks

Orozco-Arias,

Lopez-Murillo,

Piña

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Analysis of eukaryotic genomes requires the detection and classification of transposable elements (TEs), a crucial but complex and time-consuming task. To improve the performance of tools that accomplish these tasks, Machine Learning approaches (ML) that leverage computer resources, such as GPUs (Graphical Processing Unit) and multiple CPU (Central Processing Unit) cores, have been adopted. However, until now, the use of ML techniques has mostly been limited to classification of TEs. Herein, a detection-classification strategy (named YORO) based on convolutional neural networks is adapted from computer vision (YOLO) to genomics. This approach enables the detection of genomic objects through the prediction of the position, length, and classification in large DNA sequences such as fully sequenced genomes. As a proof of concept, the internal protein-coding domains of LTR-retrotransposons are used to train the proposed neural network. Precision, recall, accuracy, F1-score, execution times and time ratios, as well as several graphical representations were used as metrics to measure performance. These promising results open the door for a new generation of Deep Learning tools for genomics. YORO architecture is available at https://github.com/simonorozcoarias/YORO.

show abstract

SENMAP: A Convolutional Neural Network Architecture for Curation of LTR-RT Libraries from Plant Genomes

Cited by 2 publications

References 33 publications

MCHelper automatically curates transposable element libraries across eukaryotic species

MCHelper automatically curates transposable element libraries across eukaryotic species

Genomic object detection: An improved approach for transposable elements detection and classification using convolutional neural networks

Contact Info

Product

Resources

About