Citation

Sokolov A, Mazur A, Zhigalova N, Prokhortchouk A, Gruzdeva N, et al. (2019) SVMOneClAS: Pipeline for Efficient Splicing Events Calling. J Genet Genome Res 5:044. doi.org/10.23937/2378-3648/1410044

Copyright

© 2019 Sokolov A, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

RESEARCH ARTICLE | OPEN ACCESSDOI: 10.23937/2378-3648/1410044

SVMOneClAS: Pipeline for Efficient Splicing Events Calling

Sokolov A1*, Mazur A1, Zhigalova N1, Prokhortchouk A1, Gruzdeva N2 and Prokhortchouk E1,2

1Center "Bioengineering", Russia, 117312, Moscow, Prospekt 60-Letiya Oktyabrya, 7/1., Russia

2National Research Center "Kurchatov Institute", Russia, 123182, Moscow, pl. Kurchatova, 1. Russia

Abstract

Splicing is a part of mRNA maturation process when exons of pre-mRNA transcript are joined in multiple ways. In case of alternative splicing, some exons may be excluded from the final mRNA, and the resulting ensemble of mRNAs creates different protein isoforms, allowing multiple proteins to be coded by a single gene. To detect new events of alternative splicing in human blood cells, we used RNA-seq technology. A pipeline based on Python "Scikit-Learn" library was developed for efficient splicing events calling. We found 8728 potential candidates, 20 of which were selected for RT-PCR and 8 were finally confirmed as novel events in 7 genes (MPPE1, CTDP1, ENOSF1, SEH1L, TXNL4A, C18orf1, and ME2). SVMOneClAS are freely available from the https://github.com/alsokolov-dev/SVMOneClAS