TransPrise: a novel machine learning approach for eukaryotic promoter prediction
DOI:
10.7717/peerj.7990URI (для ссылок/цитирований):
https://peerj.com/articles/7990/https://elib.sfu-kras.ru/handle/2311/142534
Автор:
Stepan, Pachganov
Khalimat, Murtazalieva
Aleksei, Zarubin
Dmitry, Sokolov
Duane R. Chartier
Tatiana, V Tatarinova
Коллективный автор:
Институт фундаментальной биологии и биотехнологии
Bio7
Дата:
2019-11Журнал:
PeerJКвартиль журнала в Scopus:
Q1Квартиль журнала в Web of Science:
Q2Библиографическое описание:
Stepan, Pachganov. TransPrise: a novel machine learning approach for eukaryotic promoter prediction [Текст] / Pachganov Stepan, Murtazalieva Khalimat, Zarubin Aleksei, Sokolov Dmitry, Duane R. Chartier, V Tatarinova Tatiana // PeerJ: Bioinformatics and Genomics. — 2019.Аннотация:
As 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 prediction of positions of eukaryotic transcription start sites. Our pipeline consists of two parts: the binary classifier operates the first, and if a sequence is classified as TSS-containing the regression step follows, where the precise location of TSS is being identified. TransPrise offers significant improvement over existing promoter-prediction methods. To illustrate this, we compared predictions of TransPrise classification and regression models with the TSSPlant approach for the well annotated genome of Oryza sativa. Using a computer equipped with a graphics processing unit, the run time of TransPrise is 250 minutes on a genome of 374 Mb long. The Matthews correlation coefficient value for TransPrise is 0.79, more than two times larger than the 0.31 for TSSPlant classification models. This represents a high level of prediction accuracy. Additionally, the mean absolute error for the regression model is 29.19 nt, allowing for accurate prediction of TSS location. TransPrise was also tested in Homo sapiens, where mean absolute error of the regression model was 47.986 nt. 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 necessary packages, models, 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 customizable to predict TSS in any eukaryotic organism.
Коллекции:
Метаданные:
Показать полную информациюСвязанные материалы
Показаны похожие ресурсы по названию, автору или тематике.
-
U-LEARNING - ПОВСЕМЕСТНОЕ ЭЛЕКТРОННОЕ ОБУЧЕНИЕ В XXI ВЕКЕ: НА ПУТИ К КОННЕКТИВИЗМУ И СМАРТ-ОБРАЗОВАНИЮ
Симонова, А. Л.; Ломаско, П. С.; Simonova, A. (Сибирский федеральный университет, 2016-04-14)В статье описываются современные тенденции изменений в области информационных технологий с позиций их потенциала для реализации моделей электронного и смешанного обучения в высшей школе. Раскрываются направления совершенствования ... -
Eportfolio Technology in Evaluation of Students’ Formal, Non-Formal and Informal Learning, Accreditation of Educational Programs and Development of E-Learning in a Federal University
Безызвестных, Е. А.; Смолянинова, О. Г. (2016-03) -
EPORTFOLIO TECHNOLOGY IN EVALUATION OF STUDENTS' FORMAL, NON-FORMAL AND INFORMAL LEARNING, ACCREDITATION OF EDUCATIONAL PROGRAMS AND DEVELOPMENT OF E-LEARNING IN A FEDERAL UNIVERSITY
Смолянинова, Ольга Георгиевна; Безызвестных, Екатерина Анатольевна (2016-10) -
УПРАВЛЕНИЕ BLENDED LEARNING В УНИВЕРСИТЕТЕ
Андрюшкова, О. В.; Andryushkova, O. V. (Сибирский федеральный университет, 2016-04-14)Аннотация: в докладе рассматривается опыт применения комбинированного обучения в преподавании естественнонаучных и педагогических дисциплин по образовательным программам высшей школы. Показано, что в соответствии с ... -
Organizing Blended Learning for Students on the Basis of Learning Roadmaps
Nadezhda M. Andreeva; Ivan P. Artyukhov; Elena G. Myagkova; Nikolay I. Pak; Zhamilya K. Akkasynova (2018)The relevance of the problem of organizing blended learning for students is related to the sharpening contradiction between the high potential of this educational technology and the poor methodological elaboration of its ...