{"id":"W4415554460","doi":"10.1016/j.jhazmat.2025.140166","title":"Machine learning-accelerated determination of immunotoxicities of liquid crystal monomers","year":2025,"lang":"en","type":"article","venue":"Journal of Hazardous Materials","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"State Key Laboratory for Environmental Criteria and Risk Assessment; State Key Laboratory in Marine Pollution; State Administration of Foreign Experts Affairs; National Natural Science Foundation of China; Chinese Academy of Sciences; City University of Hong Kong","keywords":"Binding affinities; Monomer; Docking (animal); Molecular dynamics; Virtual screening; Structural similarity; Cluster analysis; Categorization; Hydrogen bond; Embedding","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":[0.0004925248,0.000106076,0.0003865247,0.0002045614,0.0000245119,0.00002022819,0.000184068,0.00009414813,0.00007497488],"category_scores_gemma":[0.0001650496,0.00009438847,0.0001412352,0.00009186107,0.00007463684,0.00001009931,0.00007207113,0.00005930361,2.98778e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001630969,"about_ca_system_score_gemma":0.00008236871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003292102,"about_ca_topic_score_gemma":0.000003533834,"domain_scores_codex":[0.9988388,0.0001263879,0.0007318394,0.00009162896,0.0001160016,0.00009528769],"domain_scores_gemma":[0.9985989,0.000013906,0.0008193314,0.000154605,0.0003944677,0.00001880471],"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":[0.0006082255,0.00005776288,0.0001563885,0.00006952295,0.0001253391,0.000004018415,0.00003696925,0.0000238453,0.9980888,0.000007991552,0.0001730947,0.0006480014],"study_design_scores_gemma":[0.0003485481,0.0008103481,0.000193426,0.00006521184,0.00007928234,0.0000183807,0.00006411549,0.00001686263,0.9967257,0.00003828751,0.001569471,0.00007040528],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996226,0.0007625677,0.002381194,0.00002625242,0.00006762068,0.00007366702,0.000009484164,0.000004746564,0.000448427],"genre_scores_gemma":[0.9975536,0.0007069899,0.001207085,0.00002316438,0.00004572745,0.000002290355,0.00002576377,0.00001107761,0.0004242946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001396376,"threshold_uncertainty_score":0.384905,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006837560510281795,"score_gpt":0.2621818005341544,"score_spread":0.2553442400238726,"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."}}