Discovery of widespread transcription initiation at microsatellites predictable by sequence-based deep neural network

Grapotte, M, Saraswat, M, Bessière, C, Menichelli, C, Ramilowski, JA, Severin, J, Hayashizaki, Y, Itoh, M, Tagami, M, Murata, M, Kojima-Ishiyama, M, Noma, S, Noguchi, S, Kasukawa, T, Hasegawa, A, Suzuki, H, Nishiyori-Sueki, H, Frith, MC, Abugessaisa, I, Aitken, S, Aken, BL, Alam, I, Alam, T, Alasiri, R, Alhendi, AMN, Alinejad-Rokny, H, Alvarez, MJ, Andersson, R, Arakawa, T, Araki, M, Arbel, T, Archer, J, Archibald, AL, Arner, E, Arner, P, Asai, K, Ashoor, H, Astrom, G, Babina, M, Baillie, JK, Bajic, VB, Bajpai, A, Baker, S, Baldarelli, RM, Balic, A, Bansal, M, Batagov, AO, Batzoglou, S, Beckhouse, AG, Beltrami, AP, Beltrami, CA, Bertin, N, Bhattacharya, S, Bickel, PJ, Blake, JA, Blanchette, M, Bodega, B, Bonetti, A, Bono, H, Bornholdt, J, Bttcher, M, Bougouffa, S, Boyd, M, Breda, J, Brombacher, F, Brown, JB, Bult, CJ, Burroughs, AM, Burt, DW, Busch, A, Caglio, G, Califano, A, Cameron, CJ, Cannistraci, CV, Carbone, A, Carlisle, AJ, Carninci, P, Carter, KW, Cesselli, D, Chang, JC, Chen, JC, Chen, Y, Chierici, M, Christodoulou, J, Ciani, Y, Clark, EL, Coskun, M, Dalby, M, Dalla, E, Daub, CO, Davis, CA, de Hoon, MJL, de Rie, D, Denisenko, E, Deplancke, B, Detmar, M, Deviatiiarov, R, Di Bernardo, D, Diehl, AD, Dieterich, LC (June 2021) Discovery of widespread transcription initiation at microsatellites predictable by sequence-based deep neural network. Nature Communications, 12 (1). ISSN 2041-1723 (In Press)

[img] PDF
2021.Grapotte.transcription_initiation.pdf

Download (3MB)
DOI: 10.1038/s41467-021-23143-7

Abstract

Using the Cap Analysis of Gene Expression (CAGE) technology, the FANTOM5 consortium provided one of the most comprehensive maps of transcription start sites (TSSs) in several species. Strikingly, ~72% of them could not be assigned to a specific gene and initiate at unconventional regions, outside promoters or enhancers. Here, we probe these unassigned TSSs and show that, in all species studied, a significant fraction of CAGE peaks initiate at microsatellites, also called short tandem repeats (STRs). To confirm this transcription, we develop Cap Trap RNA-seq, a technology which combines cap trapping and long read MinION sequencing. We train sequence-based deep learning models able to predict CAGE signal at STRs with high accuracy. These models unveil the importance of STR surrounding sequences not only to distinguish STR classes, but also to predict the level of transcription initiation. Importantly, genetic variants linked to human diseases are preferentially found at STRs with high transcription initiation level, supporting the biological and clinical relevance of transcription initiation at STRs. Together, our results extend the repertoire of non-coding transcription associated with DNA tandem repeats and complexify STR polymorphism.

Item Type: Paper
Subjects: bioinformatics > genomics and proteomics > genetics & nucleic acid processing > DNA, RNA structure, function, modification > transcription
organs, tissues, organelles, cell types and functions > tissues types and functions > neural networks
CSHL Authors:
Communities: CSHL labs > Gingeras lab
SWORD Depositor: CSHL Elements
Depositing User: CSHL Elements
Date: 2 June 2021
Date Deposited: 16 Jun 2021 18:41
Last Modified: 23 Jun 2021 19:33
PMCID: PMC8172540
URI: https://repository.cshl.edu/id/eprint/40212

Actions (login required)

Administrator's edit/view item Administrator's edit/view item
CSHL HomeAbout CSHLResearchEducationNews & FeaturesCampus & Public EventsCareersGiving