{"id":"W4410794094","doi":"10.21203/rs.3.rs-6683338/v1","title":"A generalized protein design ML model enables generation of functional de novo proteins","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Protein design; Computer science; Computational biology; Transformer; Folding (DSP implementation); Function (biology); Artificial intelligence; Protein structure; Software engineering; Biology; Engineering; Cell biology; Biochemistry; Electrical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001021325,0.0006833907,0.0007485517,0.0003643268,0.0002638001,0.0009192514,0.001306645,0.001385809,0.003611795],"category_scores_gemma":[0.002296096,0.0004707647,0.0008781909,0.0004146803,0.0004977636,0.001007514,0.001139026,0.001284652,0.001554323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004992823,"about_ca_system_score_gemma":0.0007249252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006806614,"about_ca_topic_score_gemma":0.001189168,"domain_scores_codex":[0.9995825,0.0001392839,0.00001925574,0.000100421,0.0001281521,0.00003044835],"domain_scores_gemma":[0.9991665,0.0003825134,0.00005421799,0.0002497057,0.0001081296,0.00003897797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001841539,0.00005348773,0.0004754871,0.0001389686,0.00004250844,0.0001734504,0.00005101095,0.8757741,0.02281166,0.03147563,0.00174842,0.06707114],"study_design_scores_gemma":[0.000008711552,0.00001604976,0.00002867683,0.000002980871,0.000004862323,0.00001646194,0.000001394916,0.9901868,0.002418734,0.006400977,0.0009116474,0.000002650802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0143483,0.00009227385,0.9822822,0.0001412362,0.00002735514,0.00003008761,0.0001639089,0.001608055,0.001306537],"genre_scores_gemma":[0.3818519,0.0002264892,0.6105138,0.0001911705,0.00005668287,0.0002312759,0.0006522152,0.0008310151,0.005445431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003611795,"threshold_uncertainty_score":0.0120827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0922858015632847,"score_gpt":0.3616586391816521,"score_spread":0.2693728376183674,"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."}}