{"id":"W4220796118","doi":"10.1002/jssc.202200183","title":"Ultrahigh‐speed, ultrahigh‐resolution preparative separation of protein biopharmaceuticals using membrane chromatography","year":2022,"lang":"en","type":"article","venue":"Journal of Separation Science","topic":"Protein purification and stability","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Chromatography; Resolution (logic); Chemistry; Membrane; Column chromatography; Fractionation; Chromatography column; Computer science; Artificial intelligence","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":[0.002110797,0.0001222011,0.0001983814,0.000258595,0.0003849379,0.00004476127,0.0003937814,0.00005335956,0.0001065958],"category_scores_gemma":[0.0002006433,0.0001141908,0.0001315576,0.0009033439,0.0004576933,0.00008129679,0.00006591755,0.0001571222,0.000001574919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008405584,"about_ca_system_score_gemma":0.0006139962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008562485,"about_ca_topic_score_gemma":0.000001975358,"domain_scores_codex":[0.9977384,0.0002619332,0.0007023623,0.0002875673,0.0008143689,0.0001954259],"domain_scores_gemma":[0.9980327,0.00001706162,0.0008494428,0.000258686,0.0007227443,0.0001193484],"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":[0.0002721374,0.0001580456,0.0002993398,0.00001277943,0.00001931415,8.757531e-7,0.0002882718,0.008677747,0.9895436,0.0005467267,0.00003465263,0.000146511],"study_design_scores_gemma":[0.000523474,0.0005490742,0.001309923,0.00001004781,0.00001960715,0.00008357117,0.0002293403,0.005331163,0.9871962,0.0001507772,0.004469615,0.0001272036],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809274,0.0008798017,0.01697314,0.0001584541,0.0001983527,0.0004674474,0.00002662632,0.000006295437,0.0003624629],"genre_scores_gemma":[0.9974433,0.00004266312,0.002273247,0.0000663461,0.00007521631,0.00001279778,0.00001125486,0.000006391317,0.0000687408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01651592,"threshold_uncertainty_score":0.4656565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03461655613687097,"score_gpt":0.3742081459888305,"score_spread":0.3395915898519595,"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."}}