{"id":"W4293475713","doi":"10.1093/bib/bbac352","title":"SADeepcry: a deep learning framework for protein crystallization propensity prediction using self-attention and auto-encoder networks","year":2022,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China","keywords":"Crystallization; Protein crystallization; Benchmark (surveying); Computer science; Sequence (biology); Encoder; Artificial intelligence; Algorithm; Chemistry; Chemical engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007216305,0.0001391839,0.000172509,0.0001136381,0.0006943763,0.0001570761,0.00008877496,0.0001204427,0.00004134063],"category_scores_gemma":[0.0001513769,0.000142853,0.00004047573,0.0002868468,0.00003666154,0.0005809271,0.000136645,0.0003026495,0.000001000989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000169562,"about_ca_system_score_gemma":0.00004260294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004707633,"about_ca_topic_score_gemma":0.000009074964,"domain_scores_codex":[0.9987709,0.00007545485,0.0004316111,0.0001927923,0.000260461,0.0002688074],"domain_scores_gemma":[0.9994006,0.00004053882,0.0003223012,0.0001203707,0.00007517241,0.00004098827],"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":[0.0006820274,0.0002699711,0.01445496,0.001814542,0.00008009505,0.000006672033,0.02107604,0.786944,0.1314782,0.02390469,0.0004899414,0.01879889],"study_design_scores_gemma":[0.0004715534,0.0001859028,0.002074308,0.00008386971,0.00003443996,0.00003673621,0.0005911192,0.9917185,0.0005551231,0.002527198,0.001532226,0.0001889874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3308648,0.00004965921,0.6678874,0.00005725029,0.0002312614,0.0007175529,0.000006993336,0.0001340119,0.00005103719],"genre_scores_gemma":[0.7718639,0.00001268004,0.227464,0.0002873108,0.0001136872,0.0001330671,0.00007436908,0.00002361353,0.00002744671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4409991,"threshold_uncertainty_score":0.5825374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01372385780541861,"score_gpt":0.2227059181185241,"score_spread":0.2089820603131055,"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."}}