{"doi":"10.1093/nar/gkaf092","title":"Probabilistic and machine-learning methods for predicting local rates of transcription elongation from nascent RNA sequencing data","abstract":"Rates of transcription elongation vary within and across eukaryotic gene bodies. Here, we introduce new methods for predicting elongation rates from nascent RNA sequencing data. First, we devise a probabilistic model that predicts nucleotide-specific elongation rates as a generalized linear function of nearby genomic and epigenomic features. We validate this model with simulations and apply it to public PRO-seq (Precision Run-On Sequencing) and epigenomic data for four cell types, finding that reductions in local elongation rate are associated with cytosine nucleotides, DNA methylation, splice sites, RNA stem-loops, CTCF (CCCTC-binding factor) binding sites, and several histone marks, including H3K36me3 and H4K20me1. By contrast, increases in local elongation rate are associated with thymines, A+T-rich and low-complexity sequences, and H3K79me2 marks. We then introduce a convolutional neural network that improves our local rate predictions. Our analysis is the first to permit genome-wide predictions of relative nucleotide-specific elongation rates.","journal":"Nucleic Acids Research","year":2025,"id":538817,"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":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9497,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":72222,"name":"Yixin Zhao","orcid":"0000-0002-7856-2818","position":1,"is_corresponding":false},{"id":1081060,"name":"R. P. Hassett","orcid":"0000-0001-5133-9387","position":2,"is_corresponding":false},{"id":775740,"name":"Shushan Toneyan","orcid":"0000-0002-1365-3241","position":3,"is_corresponding":false},{"id":298873,"name":"Peter K. Koo","orcid":"0000-0001-8722-0038","position":4,"is_corresponding":false},{"id":237917,"name":"Adam Siepel","orcid":"0000-0002-3557-7219","position":5,"is_corresponding":false},{"id":993613,"name":"Lingjie Liu","orcid":"0000-0002-5765-1213","position":0,"is_corresponding":true}],"reference_count":56,"raw_metadata":null,"created_at":"2026-07-19T02:52:25.799399Z","pmid":"39964478","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":[]}