{"id":"W4411274741","doi":"10.1016/j.patter.2025.101289","title":"Tokenized and continuous embedding compressions of protein sequence and structure","year":2025,"lang":"en","type":"article","venue":"Patterns","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sequence (biology); Embedding; Computational biology; Chemistry; Computer science; Biochemistry; Biology; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002772891,0.00008060509,0.0001145017,0.00002264689,0.00003952231,0.00001165959,0.00006561145,0.00008167442,0.000006098699],"category_scores_gemma":[0.00002763056,0.00006868401,0.00001666042,0.00002696914,0.00005744247,0.00000208473,0.0001246367,0.00005698382,4.64319e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002324078,"about_ca_system_score_gemma":0.00001750249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000346108,"about_ca_topic_score_gemma":0.00002584791,"domain_scores_codex":[0.9995778,0.0000225509,0.0001028105,0.000166744,0.00003867082,0.00009148406],"domain_scores_gemma":[0.9997493,0.000006176844,0.0000442688,0.0001425233,0.000029533,0.00002816598],"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":[0.00002495147,0.000003919259,0.0275108,0.00007322082,0.00002192327,0.000001303957,0.00003436942,0.000005842156,0.9674069,0.0002718575,0.00002063315,0.004624244],"study_design_scores_gemma":[0.001183145,0.0001296089,0.03405913,0.0002423091,0.00003681512,0.00002584566,0.0001272092,0.0009043094,0.9586005,0.002441474,0.002008084,0.0002415781],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930551,0.0006147089,0.005769914,0.0000703298,0.00003495272,0.0001858882,0.0001027585,0.000005287538,0.0001610683],"genre_scores_gemma":[0.9981615,0.00004440197,0.001454134,0.0001067799,0.00002079866,0.000007520001,0.0000333474,0.000004866581,0.0001666395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008806446,"threshold_uncertainty_score":0.2800853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00603868489856507,"score_gpt":0.2703088452270954,"score_spread":0.2642701603285303,"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."}}