{"id":"W2602556590","doi":"10.1371/journal.pone.0174392","title":"ML2Motif—Reliable extraction of discriminative sequence motifs from learning machines","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; National Research Foundation of Korea; Deutsche Forschungsgemeinschaft; National Research Foundation","keywords":"Artificial intelligence; Computer science; Support vector machine; Machine learning; Discriminative model; Pattern recognition (psychology); Computation; Data mining; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000911399,0.000902862,0.0008967876,0.001339717,0.0004215413,0.0008097463,0.001456463,0.001249917,0.002150963],"category_scores_gemma":[0.005377911,0.0004368848,0.0006402242,0.000964572,0.0004630955,0.001600511,0.00169853,0.001414825,0.001569715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004603691,"about_ca_system_score_gemma":0.0008288445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012832,"about_ca_topic_score_gemma":0.002008185,"domain_scores_codex":[0.9992276,0.0001887945,0.00003970621,0.000206748,0.0002589494,0.00007819306],"domain_scores_gemma":[0.9989209,0.000368598,0.0001387991,0.0002802176,0.0002218765,0.00006963316],"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":[0.0004086572,0.0002091689,0.00607718,0.0004375446,0.000131491,0.0003946183,0.0001625077,0.1453062,0.05977116,0.02372259,0.01771777,0.7456612],"study_design_scores_gemma":[0.000013197,0.00004325439,0.0007211994,0.000008920703,0.00000488202,0.0001029876,0.00001886363,0.9758076,0.008755502,0.01120926,0.003302067,0.00001239084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02356928,0.0002775739,0.9710218,0.0001524808,0.0000428917,0.00006480451,0.0004107951,0.003603342,0.0008569959],"genre_scores_gemma":[0.3666755,0.0002489727,0.6243933,0.0002185525,0.0001155054,0.0003097241,0.003891477,0.0006515398,0.003495361],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002150963,"threshold_uncertainty_score":0.007195652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04477034974656711,"score_gpt":0.2942483855799259,"score_spread":0.2494780358333588,"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."}}