{"id":"W4316495494","doi":"10.12688/wellcomeopenres.18681.1","title":"Pf7: an open dataset of Plasmodium falciparum genome variation in 20,000 worldwide samples","year":2023,"lang":"en","type":"preprint","venue":"Wellcome Open Research","topic":"Malaria Research and Control","field":"Medicine","cited_by":148,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Faculty of Tropical Medicine, Mahidol University; Addis Ababa University; National Institutes of Health; Universiteit Antwerpen; National Institute for Medical Research; Ministère de la Santé; Universidad Nacional de Colombia; Bundesministerium für Gesundheit; World Health Organization; University of Ghana; Bill and Melinda Gates Foundation; Mahidol University; University College London; National Center for Advancing Translational Sciences; National Human Genome Research Institute; Wellcome Trust; National Institute of Allergy and Infectious Diseases; Medical Research Council; London School of Hygiene and Tropical Medicine","keywords":"Plasmodium falciparum; Variation (astronomy); Biology; Genome; Computational biology; Structural variation; Genetics; Malaria; Evolutionary biology; Gene; Immunology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001711593,0.001685978,0.001482828,0.00409126,0.0006784351,0.001577595,0.001394589,0.001360528,0.0253778],"category_scores_gemma":[0.00701324,0.0008090687,0.0008966416,0.008466877,0.0004252073,0.000916853,0.001928161,0.001431864,0.02133715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007471136,"about_ca_system_score_gemma":0.002056357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01165312,"about_ca_topic_score_gemma":0.010403,"domain_scores_codex":[0.998396,0.000275985,0.0001786728,0.0005048394,0.0004377957,0.000206834],"domain_scores_gemma":[0.9976349,0.0006916515,0.0004084217,0.0005499208,0.0003907118,0.0003244529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009331374,0.0001018315,0.02447269,0.002336847,0.0005317835,0.0005648796,0.0003359705,0.003539604,0.006657445,0.001804397,0.918777,0.03994441],"study_design_scores_gemma":[0.0008222178,0.0001473197,0.08532767,0.0003669196,0.0002398978,0.0009317712,0.0002565408,0.00263965,0.003545485,0.003926647,0.901674,0.00012187],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00382277,0.0002754505,0.000937634,0.0001155382,0.00002834206,0.00002692675,0.9930842,0.0008799038,0.0008291868],"genre_scores_gemma":[0.003868964,0.000102804,0.001279305,0.00004169775,0.00001421204,0.00007648769,0.9942067,0.0001776273,0.0002322967],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0253778,"threshold_uncertainty_score":0.08489716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2762833932571187,"score_gpt":0.4550705055030257,"score_spread":0.178787112245907,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}