Prediction of Rice Transcription Start Sites Using TransPrise: A Novel Machine Learning Approach

Stepan Pachganov; Khalimat Murtazalieva; Alexei Zarubin; Tatiana Taran; Duane Chartier; Tatiana V Tatarinova

doi:10.1007/978-1-0716-1068-8_17

Prediction of Rice Transcription Start Sites Using TransPrise: A Novel Machine Learning Approach

Methods Mol Biol. 2021:2238:261-274. doi: 10.1007/978-1-0716-1068-8_17.

Authors

Stepan Pachganov¹, Khalimat Murtazalieva², Alexei Zarubin³, Tatiana Taran⁴, Duane Chartier⁵, Tatiana V Tatarinova^{6

7

8

9}

Affiliations

¹ Ugra Research Institute of Information Technologies, Khanty-Mansiysk, Russia.
² Vavilov Institute of General Genetics, Moscow, Russia.
³ Tomsk National Research Medical Center of the Russian Academy of Sciences, Research Institute of Medical Genetics, Tomsk, Russia.
⁴ Odessa National University, Odessa, Ukraine.
⁵ International Center for Art Intelligence, Inc, Los Angeles, CA, USA.
⁶ Vavilov Institute of General Genetics, Moscow, Russia. ttatarinova@laverne.edu.
⁷ Department of Biology, University of La Verne, La Verne, CA, USA. ttatarinova@laverne.edu.
⁸ A.A. Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia. ttatarinova@laverne.edu.
⁹ Siberian Federal University, Krasnoyarsk, Russia. ttatarinova@laverne.edu.

PMID: 33471337
DOI: 10.1007/978-1-0716-1068-8_17

Abstract

As the interest in genetic resequencing increases, so does the need for effective mathematical, computational, and statistical approaches. One of the difficult problems in genome annotation is determination of precise positions of transcription start sites. In this paper, we present TransPrise-an efficient deep learning tool for predicting positions of eukaryotic transcription start sites. TransPrise offers significant improvement over existing promoter-prediction methods. To illustrate this, we compared predictions of TransPrise with the TSSPlant approach for well-annotated genome of Oryza sativa. Using a computer with a graphics processing unit, the run time of TransPrise is 250 min on a genome of 374 Mb long.We provide the full basis for the comparison and encourage users to freely access a set of our computational tools to facilitate and streamline their own analyses. The ready-to-use Docker image with all the necessary packages, models, and code as well as the source code of the TransPrise algorithm are available at http://compubioverne.group/ . The source code is ready to use and to be customized to predict TSS in any eukaryotic organism.

Keywords: Machine learning; Rice; TransPrise; Transcription start site.

MeSH terms

Gene Expression Regulation, Plant*
Genome, Plant*
Machine Learning*
Oryza / genetics*
Plant Proteins / genetics*
Promoter Regions, Genetic
Software*
Transcription Initiation Site*
Transcription, Genetic

Substances

Plant Proteins