{"id":"W4317425811","doi":"10.1038/s41467-022-35734-z","title":"Annotation of natural product compound families using molecular networking topology and structural similarity fingerprinting","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of New Brunswick","funders":"National Center for Complementary and Integrative Health; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Government of Canada; U.S. Department of Health and Human Services","keywords":"Bottleneck; Annotation; Computer science; Similarity (geometry); Fragmentation (computing); Computational biology; Mass spectrometry; Identification (biology); Data mining; Pattern recognition (psychology); Chemistry; Artificial intelligence; Biology; Chromatography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003939221,0.000481042,0.0003268524,0.004206526,0.0004533789,0.0007976985,0.0003694388,0.0003103562,0.003216449],"category_scores_gemma":[0.001316409,0.0001917424,0.000502956,0.002283972,0.0002115676,0.0009856932,0.0006488418,0.0002826694,0.001354852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004796496,"about_ca_system_score_gemma":0.0004103763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00128602,"about_ca_topic_score_gemma":0.002073341,"domain_scores_codex":[0.9997497,0.0000333554,0.00002202102,0.0001021967,0.00007190467,0.00002078787],"domain_scores_gemma":[0.9990783,0.000219405,0.0003090724,0.0001222346,0.0001918679,0.00007908673],"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":[0.0007764336,0.0001338014,0.06046313,0.001054349,0.0001652033,0.0006050286,0.0003497036,0.01120136,0.7863817,0.003210781,0.004636935,0.1310216],"study_design_scores_gemma":[0.00005880966,0.0005574904,0.2293013,0.0002237333,0.0003504551,0.002140054,0.0005425232,0.2939313,0.3821151,0.01026054,0.0803573,0.0001612916],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6760398,0.001332682,0.2481683,0.0002358563,0.00004897329,0.0003722784,0.04885218,0.01529444,0.009655533],"genre_scores_gemma":[0.6494828,0.0009910156,0.2841603,0.00008357948,0.00003121556,0.0003680012,0.06071927,0.0008646474,0.003299218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004206526,"threshold_uncertainty_score":0.01076007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02166204898805064,"score_gpt":0.3207216103799703,"score_spread":0.2990595613919197,"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."}}