{"doi":"10.26434/chemrxiv.14779254","title":"Tautomeric Conflicts in Forty Small-Molecule Databases","abstract":"We have analyzed forty different databases ranging in size from a few thousand to nearly 100 million molecules, comprising a total of over 200 million structures, for their tautomeric conflicts. A tautomeric conflict is defined as an occurrence of two or more structures within a data set identified by the tautomeric rules applied as being tautomers of each other. We tested a total of 119 detailed tautomeric transform rules expressed as SMIRKS, out of which 79 yielded at least one conflict. The databases analyzed spanned a wide variety of types including large aggregating databases, drug collections, and experimentally based structure collections. Almost all databases analyzed showed intra-database tautomeric conflicts. The conflict rates as percentage of the database were typically in the few tenths of a percent range, which for the largest databases amounts to more than 100,000 cases per database.","journal":"ChemRxiv","year":2021,"id":222439,"datarank":0.16622677344185136,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.06225469635785954,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.06225469635785954,"corpus_percentile":32.79956679817436,"corpus_rank":8688,"citation_count":1,"citer_count":1,"citers_with_citation_signal":1,"citers_with_endowment":1,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.8413,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":360813,"name":"Marc C. Nicklaus","orcid":"0000-0002-4775-7030","position":1,"is_corresponding":false},{"id":460745,"name":"Devendra K. Dhaked","orcid":"0000-0001-6349-7649","position":0,"is_corresponding":true}],"reference_count":11,"raw_metadata":null,"created_at":"2026-07-18T23:54:03.549854Z","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":[]}