{"id":"W4417122478","doi":"10.1021/acs.jcim.5c02196","title":"AcidProNet: Acidophilic Protein Classification via DCGAN-GP-Based Data Augmentation and Parameter-Shared Mixture-of-Experts Transformer","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; Hainan Provincial Department of Science and Technology; Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Scalability; Identification (biology); Embedding; Key (lock); Transformer; Stability (learning theory); Generative grammar; Exploit","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":[0.0002965049,0.00009956773,0.0001441444,0.00009962465,0.00003544181,0.00004478299,0.0001468353,0.000127869,0.000003459726],"category_scores_gemma":[0.0001869022,0.00008473183,0.00003573149,0.00006544619,0.00004047082,0.0001146591,0.00003470195,0.0001242592,2.379831e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001260913,"about_ca_system_score_gemma":0.00007382494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002919238,"about_ca_topic_score_gemma":4.657879e-7,"domain_scores_codex":[0.9990273,0.00001960014,0.0006415337,0.00007523462,0.0001475694,0.00008879334],"domain_scores_gemma":[0.9992666,0.00001485698,0.0003274611,0.0001682965,0.0001711118,0.00005164418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000301543,0.00003531222,0.0001533995,0.0003142027,0.00005139795,1.089162e-7,0.00037036,0.001999436,0.955146,0.00005161945,0.0001965191,0.04138016],"study_design_scores_gemma":[0.001016555,0.00008661788,0.0000443855,0.0001106112,0.00003269441,0.000012247,0.0001474833,0.7608306,0.2361595,0.0001124095,0.001350358,0.00009657247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6070506,0.0001573695,0.3921114,0.000377105,0.00002949767,0.0001410253,0.00001067113,0.000003541417,0.0001188357],"genre_scores_gemma":[0.9812667,0.00005914504,0.0179853,0.0003158365,0.0000259966,0.000004593202,0.0003328513,0.000004040688,0.000005479917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7588311,"threshold_uncertainty_score":0.3455264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02609890357100594,"score_gpt":0.3021179786139657,"score_spread":0.2760190750429598,"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."}}