{"doi":"10.1101/2020.11.18.389049","title":"Identification of high confidence human poly(A) RNA isoform scaffolds using nanopore sequencing","abstract":"ABSTRACT Nanopore sequencing devices read individual RNA strands directly. This facilitates identification of exon linkages and nucleotide modifications; however, using conventional methods the 5′ and 3′ ends of poly(A) RNA cannot be identified unambiguously. This is due in part to the architecture of the nanopore/enzyme-motor complex, and in part to RNA degradation in vivo and in vitro that can obscure transcription start and end sites. In this study, we aimed to identify individual full-length human RNA isoform scaffolds among ∼4 million nanopore poly(A)-selected RNA reads. First, to identify RNA strands bearing 5′ m 7 G caps, we exchanged the biological cap for a modified cap attached to a 45-nucleotide oligomer. This oligomer adaptation method improved 5′ end sequencing and ensured correct identification of the 5′ m 7 G capped ends. Second, among these 5′-capped nanopore reads, we screened for ionic current signatures consistent with a 3′ polyadenylation site. Combining these two steps, we identified 294,107 individual high-confidence full-length RNA scaffolds, most of which (257,721) aligned to protein-coding genes. Of these, 4,876 scaffolds indicated unannotated isoforms that were often internal to longer, previously identified RNA isoforms. Orthogonal data confirmed the validity of these high-confidence RNA scaffolds.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2020,"id":123107,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9516,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":565727,"name":"Madalee G. Wulf","orcid":"0000-0002-7601-413X","position":1,"is_corresponding":false},{"id":565728,"name":"Ira Schildkraut","orcid":"0000-0002-1143-6630","position":2,"is_corresponding":false},{"id":565729,"name":"George Tzertzinis","orcid":"0000-0001-8821-8060","position":3,"is_corresponding":false},{"id":565730,"name":"J. A. Buswell","orcid":"0000-0002-0933-2867","position":4,"is_corresponding":false},{"id":109466,"name":"Miten Jain","orcid":"0000-0002-4571-3982","position":5,"is_corresponding":false},{"id":30898,"name":"Hugh E. Olsen","orcid":"0000-0002-7293-8853","position":6,"is_corresponding":false},{"id":16842,"name":"Mark Diekhans","orcid":"0000-0002-0430-0989","position":7,"is_corresponding":false},{"id":121504,"name":"Ivan R Corrêa","orcid":"0000-0002-3169-6878","position":8,"is_corresponding":false},{"id":109464,"name":"Mark Akeson","orcid":"0000-0001-9392-8075","position":9,"is_corresponding":false},{"id":565731,"name":"Laurence Ettwiller","orcid":"0000-0002-3957-6539","position":10,"is_corresponding":false},{"id":565726,"name":"Logan Mulroney","orcid":"0000-0002-0534-0165","position":0,"is_corresponding":true}],"reference_count":45,"raw_metadata":null,"created_at":"2026-07-18T23:14:59.547352Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}