{"id":"W4388155974","doi":"10.1101/2023.10.29.564479","title":"Simplifying bioinformatics data analysis through conversation","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Python (programming language); Chatbot; Pipeline (software); Data science; World Wide Web; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005751842,0.0004952395,0.0005417038,0.0002272497,0.0001579187,0.000233165,0.001216377,0.0007355955,0.00001630796],"category_scores_gemma":[0.000239985,0.0005498127,0.000253261,0.0006873106,0.0001176987,0.00002838369,0.00119816,0.0004363338,0.00006747309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007183086,"about_ca_system_score_gemma":0.0003955774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001768779,"about_ca_topic_score_gemma":0.00002983791,"domain_scores_codex":[0.9973291,0.0000843597,0.0006568099,0.001102862,0.0003418686,0.0004850579],"domain_scores_gemma":[0.9961069,0.00003084594,0.0004229712,0.002984795,0.0003016524,0.0001528926],"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":[0.00007021773,0.0001488304,0.0254681,0.0006916621,0.003347554,0.00001969653,0.00005378124,0.002547472,0.9648663,0.0001051494,0.002674988,0.000006240042],"study_design_scores_gemma":[0.002158726,0.0002359005,0.06483866,0.0003908751,0.005206653,3.914465e-8,0.00006566902,0.0808455,0.8034676,0.00001441071,0.03887761,0.003898311],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7301155,0.0009259335,0.2623357,0.000337534,0.002324199,0.0008286423,0.002662448,0.0004471027,0.00002291355],"genre_scores_gemma":[0.9786155,0.001004809,0.01916617,0.0003306296,0.0005945305,0.0000411239,0.0001086035,0.0001270741,0.00001161614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2484999,"threshold_uncertainty_score":0.9996954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05226007105566299,"score_gpt":0.2625579742798717,"score_spread":0.2102979032242087,"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."}}