{"doi":"10.1101/gr.275394.121","title":"Domain-adaptive neural networks improve cross-species prediction of transcription factor binding","abstract":"The intrinsic DNA sequence preferences and cell type-specific cooperative partners of transcription factors (TFs) are typically highly conserved. Hence, despite the rapid evolutionary turnover of individual TF binding sites, predictive sequence models of cell type-specific genomic occupancy of a TF in one species should generalize to closely matched cell types in a related species. To assess the viability of cross-species TF binding prediction, we train neural networks to discriminate ChIP-seq peak locations from genomic background and evaluate their performance within and across species. Cross-species predictive performance is consistently worse than within-species performance, which we show is caused in part by species-specific repeats. To account for this domain shift, we use an augmented network architecture to automatically discourage learning of training species-specific sequence features. This domain adaptation approach corrects for prediction errors on species-specific repeats and improves overall cross-species model performance. Our results show that cross-species TF binding prediction is feasible when models account for domain shifts driven by species-specific repeats.","journal":"Genome Research","year":2022,"id":296411,"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":45,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9483,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":809242,"name":"Divyanshi Srivastava","orcid":"0000-0002-6580-6166","position":1,"is_corresponding":false},{"id":85500,"name":"Avanti Shrikumar","orcid":"0000-0002-6443-4671","position":2,"is_corresponding":false},{"id":225120,"name":"Akshay Balsubramani","orcid":"0000-0003-1545-9837","position":3,"is_corresponding":false},{"id":19594,"name":"Ross C. Hardison","orcid":"0000-0003-4084-7516","position":4,"is_corresponding":false},{"id":360,"name":"Anshul Kundaje","orcid":"0000-0003-3084-2287","position":5,"is_corresponding":false},{"id":4943,"name":"Shaun Mahony","orcid":"0000-0002-2641-1807","position":6,"is_corresponding":false},{"id":268109,"name":"Kelly Cochran","orcid":"0000-0001-5481-2344","position":0,"is_corresponding":true}],"reference_count":53,"raw_metadata":null,"created_at":"2026-07-19T00:31:16.555318Z","pmid":"35042722","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":[]}