{"status":200,"statusText":"OK","data":{"uci_id":39,"name":"Ecoli","repository_url":"https://archive.ics.uci.edu/dataset/39/ecoli","data_url":"https://archive.ics.uci.edu/static/public/39/data.csv","abstract":"This data contains protein localization sites","area":"Biology","tasks":["Classification"],"characteristics":["Multivariate"],"num_instances":336,"num_features":7,"feature_types":["Real"],"demographics":[],"target_col":["class"],"index_col":["Sequence"],"has_missing_values":"no","missing_values_symbol":null,"year_of_dataset_creation":1996,"last_updated":"Thu Feb 15 2024","dataset_doi":"10.24432/C5388M","creators":["Kenta Nakai"],"intro_paper":{"ID":391,"type":"NATIVE","title":"A Probabilistic Classification System for Predicting the Cellular Localization Sites of Proteins","authors":"P. Horton, K. Nakai","venue":"Intelligent Systems in Molecular Biology","year":1996,"journal":null,"DOI":null,"URL":"https://www.semanticscholar.org/paper/A-Probabilistic-Classification-System-for-the-Sites-Horton-Nakai/623c5e3441a1e08e3da2c68924c85e4b95274652","sha":null,"corpus":null,"arxiv":null,"mag":null,"acl":null,"pmid":null,"pmcid":null},"variables":[{"name":"Sequence","role":"ID","type":"Categorical","demographic":null,"description":"Accession number for the SWISS-PROT database","units":null,"missing_values":"no"},{"name":"mcg","role":"Feature","type":"Continuous","demographic":null,"description":"McGeoch's method for signal sequence recognition","units":null,"missing_values":"no"},{"name":"gvh","role":"Feature","type":"Continuous","demographic":null,"description":"von Heijne's method for signal sequence recognition","units":null,"missing_values":"no"},{"name":"lip","role":"Feature","type":"Binary","demographic":null,"description":"von Heijne's Signal Peptidase II consensus sequence score","units":null,"missing_values":"no"},{"name":"chg","role":"Feature","type":"Binary","demographic":null,"description":"Presence of charge on N-terminus of predicted lipoproteins","units":null,"missing_values":"no"},{"name":"aac","role":"Feature","type":"Continuous","demographic":null,"description":"score of discriminant analysis of the amino acid content of outer membrane and periplasmic proteins","units":null,"missing_values":"no"},{"name":"alm1","role":"Feature","type":"Continuous","demographic":null,"description":"score of the ALOM membrane spanning region prediction program","units":null,"missing_values":"no"},{"name":"alm2","role":"Feature","type":"Continuous","demographic":null,"description":"score of ALOM program after excluding putative cleavable signal regions from the sequence","units":null,"missing_values":"no"},{"name":"class","role":"Target","type":"Categorical","demographic":null,"description":null,"units":null,"missing_values":"no"}],"additional_info":{"summary":"The references below describe a predecessor to this dataset and its development. They also give results (not cross-validated) for classification by a rule-based expert system with that version of the dataset.\r\n\r\nReference: \"Expert Sytem for Predicting Protein Localization Sites in Gram-Negative Bacteria\", Kenta Nakai & Minoru Kanehisa,  PROTEINS: Structure, Function, and Genetics 11:95-110, 1991.\r\n\r\nReference: \"A Knowledge Base for Predicting Protein Localization Sites in Eukaryotic Cells\", Kenta Nakai & Minoru Kanehisa, Genomics 14:897-911, 1992.","purpose":null,"funded_by":null,"instances_represent":null,"recommended_data_splits":null,"sensitive_data":null,"preprocessing_description":null,"variable_info":"  1.  Sequence Name: Accession number for the SWISS-PROT database\r\n  2.  mcg: McGeoch's method for signal sequence recognition.\r\n  3.  gvh: von Heijne's method for signal sequence recognition.\r\n  4.  lip: von Heijne's Signal Peptidase II consensus sequence score. Binary attribute.\r\n  5.  chg: Presence of charge on N-terminus of predicted lipoproteins. Binary attribute.\r\n  6.  aac: score of discriminant analysis of the amino acid content of outer membrane and periplasmic proteins.\r\n  7. alm1: score of the ALOM membrane spanning region prediction program.\r\n  8. alm2: score of ALOM program after excluding putative cleavable signal regions from the sequence.","citation":null}}}