{"doi":"10.1101/2023.08.02.551637","title":"Compound models and Pearson residuals for single-cell RNA-seq data without UMIs","abstract":"Recent work employed Pearson residuals from Poisson or negative binomial models to normalize UMI data. To extend this approach to non-UMI data, we model the additional amplification step with a compound distribution: we assume that sequenced RNA molecules follow a negative binomial distribution, and are then replicated following an amplification distribution. We show how this model leads to compound Pearson residuals, which yield meaningful gene selection and embeddings of Smart-seq2 datasets. Further, we suggest that amplification distributions across several sequencing protocols can be described by a broken power law. The resulting compound model captures previously unexplained overdispersion and zero-inflation patterns in non-UMI data.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2023,"id":400328,"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":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9475,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":36049,"name":"Christoph Ziegenhain","orcid":"0000-0003-2208-4877","position":1,"is_corresponding":false},{"id":59057,"name":"Leonard Hartmanis","orcid":"0000-0002-4922-8781","position":2,"is_corresponding":false},{"id":58947,"name":"Philipp Berens","orcid":"0000-0002-0199-4727","position":3,"is_corresponding":false},{"id":58949,"name":"Dmitry Kobak","orcid":"0000-0002-5639-7209","position":4,"is_corresponding":false},{"id":553474,"name":"Jan Lause","orcid":"0000-0003-0946-412X","position":0,"is_corresponding":true}],"reference_count":66,"raw_metadata":null,"created_at":"2026-07-19T01:20:04.010538Z","pmid":"37577688","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":[]}