{"id":"W4400869919","doi":"10.1038/s41592-024-02341-3","title":"Contextual AI models for single-cell protein biology","year":2024,"lang":"en","type":"article","venue":"Nature Methods","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Human Genome Research Institute","keywords":"Pinnacle; Context (archaeology); Cell type; Computational biology; Computer science; Function (biology); Hierarchy; Biology; Embedding; Artificial intelligence; Cell; Cell biology; Genetics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007864709,0.0001755694,0.0002034823,0.00009389988,0.00004020411,0.00005156935,0.0002192603,0.0006909535,0.00001546689],"category_scores_gemma":[0.000244561,0.0001493069,0.0002403093,0.0001419161,0.00006788771,0.000005996962,0.00009590149,0.0003564924,0.000002579678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001843236,"about_ca_system_score_gemma":0.00005837827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000506624,"about_ca_topic_score_gemma":0.000004659546,"domain_scores_codex":[0.9987808,0.000216628,0.0001915665,0.0005213711,0.00005686627,0.0002328079],"domain_scores_gemma":[0.9993159,0.00006988221,0.0000389991,0.0003841118,0.0001422648,0.00004888935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003204285,0.00003701332,0.000001543985,0.00004939342,0.00006219339,0.000002071202,0.00001412009,0.000005127434,0.9437048,0.002313388,0.009456874,0.0443214],"study_design_scores_gemma":[0.0001078624,0.0001965745,1.703444e-7,0.00001047745,0.00003789533,0.00000507297,0.000006348731,0.002008667,0.6960928,0.008351262,0.2930517,0.0001311024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003274945,0.01654898,0.9706985,0.0003058909,0.0001067759,0.000474699,0.0000184764,0.0001028316,0.008468867],"genre_scores_gemma":[0.5223868,0.0000463301,0.4719169,0.0009317624,0.0003628403,0.0001614962,0.0001941946,0.00004527102,0.003954374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5191119,"threshold_uncertainty_score":0.6088557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0202349242454697,"score_gpt":0.3901649368756546,"score_spread":0.3699300126301849,"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."}}