{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02364192,0.002076504,0.001389164,0.002281555,0.003194761,0.01046648,0.004399114,0.001962498,0.01263394],"category_scores_gemma":[0.09729416,0.001237042,0.002223342,0.001730793,0.005410427,0.01571653,0.01813282,0.0075112,0.009910839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001861487,"about_ca_system_score_gemma":0.00573791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002198256,"about_ca_topic_score_gemma":0.001828167,"domain_scores_codex":[0.9629629,0.02446214,0.001630093,0.004320147,0.005617936,0.001006842],"domain_scores_gemma":[0.9234532,0.05505462,0.001627498,0.01308529,0.005538908,0.00124052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001138377,0.0004160201,0.003239574,0.001881293,0.0002756562,0.001400412,0.01974784,0.01633845,0.02861924,0.422152,0.1005649,0.4042262],"study_design_scores_gemma":[0.000142142,0.00009993369,0.000488278,0.0005131282,0.0001041518,0.0004496864,0.00299305,0.1809233,0.02749295,0.5191147,0.2674991,0.0001795235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007287965,0.0003365811,0.962034,0.006320124,0.0003788351,0.0002772969,0.0007331902,0.01505941,0.007572512],"genre_scores_gemma":[0.1139104,0.0005198219,0.8665039,0.003726616,0.0005424617,0.0009038231,0.002399741,0.005322332,0.006170872],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02364192,"threshold_uncertainty_score":0.1250319,"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."}}