{"id":"W4398201885","doi":"10.1016/j.foodchem.2024.139747","title":"Feature fusion-based food protein subcellular prediction for drug composition","year":2024,"lang":"en","type":"article","venue":"Food Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lockheed Martin (Canada)","funders":"AlMaarefa University","keywords":"Composition (language); Feature (linguistics); Fusion; Computational biology; Pseudo amino acid composition; Artificial intelligence; Chemistry; Computer science; Pattern recognition (psychology); Subcellular localization; Biology; Biochemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0001386212,0.0001915072,0.0001105746,0.00002227817,0.0001078084,0.00007262742,0.0001617269,0.0002570772,0.00002963151],"category_scores_gemma":[0.00004513242,0.0001880062,0.0001461884,0.00008240352,0.00003967585,0.000005151519,0.00004957874,0.0002184733,0.000005483303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003190444,"about_ca_system_score_gemma":0.00009967828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.694307e-7,"about_ca_topic_score_gemma":9.833717e-7,"domain_scores_codex":[0.9991369,0.00001485272,0.0001688774,0.0003039756,0.0001592049,0.000216234],"domain_scores_gemma":[0.9994661,0.00001511502,0.00006337854,0.0003097685,0.00007200579,0.00007366321],"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":[0.00006715299,0.00003711501,0.00004423912,0.0009548903,0.00006599572,9.195331e-7,0.00003112643,0.0003043915,0.9859254,0.00003630258,0.01212307,0.0004093847],"study_design_scores_gemma":[0.0004075618,0.0003461729,0.000008494275,0.0001286917,0.00003056743,0.00001208885,0.00002251469,0.01482918,0.8902308,0.00006838398,0.09373064,0.000184916],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9743478,0.001411153,0.01942831,0.001153632,0.0002435615,0.0006378994,0.0005906897,0.0001910256,0.001995887],"genre_scores_gemma":[0.9903023,0.000005298649,0.003285981,0.00008656683,0.0005728066,0.0001544539,0.003797069,0.00003993501,0.001755619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09569462,"threshold_uncertainty_score":0.7666669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004313596785096773,"score_gpt":0.2119328778676029,"score_spread":0.2076192810825062,"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."}}