{"id":"W4391947037","doi":"10.1101/2024.02.16.580694","title":"Phylochemical mapping of natural products onto the plant tree of life using text mining and large language models.","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Chemical synthesis and alkaloids","field":"Chemistry","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"College of Science and Engineering, University of Minnesota; University of Minnesota; National Science Foundation","keywords":"Workflow; Phylogenetic tree; Biology; Phylogenetics; Computer science; Tree (set theory); Computational biology; Evolutionary biology; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002434938,0.001330375,0.0006114717,0.01043839,0.0009029803,0.002253233,0.001037226,0.000865941,0.002715068],"category_scores_gemma":[0.008611732,0.000334392,0.002052103,0.004768626,0.0005431204,0.00208307,0.001616689,0.001360606,0.002656421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009558184,"about_ca_system_score_gemma":0.001883314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003063417,"about_ca_topic_score_gemma":0.006015399,"domain_scores_codex":[0.9984658,0.0004051541,0.0002120032,0.0005524265,0.0002918839,0.00007288299],"domain_scores_gemma":[0.992673,0.004701362,0.00100435,0.0004127771,0.0009409562,0.0002674925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00105183,0.0004224576,0.03920828,0.02025828,0.001555057,0.00421299,0.004091595,0.01314313,0.2051232,0.01914094,0.1016577,0.5901346],"study_design_scores_gemma":[0.0002022621,0.0007011769,0.06864315,0.002990231,0.001877555,0.003437088,0.004270494,0.2393517,0.08768716,0.08289553,0.5075498,0.0003939372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1458776,0.02220419,0.3582665,0.005725265,0.0006746711,0.001540125,0.4154227,0.03249848,0.01779046],"genre_scores_gemma":[0.2136832,0.004986017,0.4882104,0.0007765776,0.0002143146,0.001258095,0.2868599,0.001281076,0.002730534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01043839,"threshold_uncertainty_score":0.01287735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01906387126023676,"score_gpt":0.2104193421159132,"score_spread":0.1913554708556764,"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."}}