{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008427459,0.001525773,0.001514995,0.0008473211,0.0004099018,0.0007460845,0.002912801,0.001585259,0.002071197],"category_scores_gemma":[0.001598075,0.0006980943,0.001095373,0.0007393587,0.0005484913,0.001311346,0.001148623,0.00210585,0.0006299708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001598541,"about_ca_system_score_gemma":0.002246601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02157183,"about_ca_topic_score_gemma":0.03087806,"domain_scores_codex":[0.999668,0.00005677832,0.00001506532,0.0001167024,0.00008314255,0.00006038847],"domain_scores_gemma":[0.9995337,0.0002018106,0.00004971055,0.00004357636,0.0001205189,0.0000508246],"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":[0.0003408851,0.0003534219,0.00412784,0.0002423854,0.0002951474,0.0002360794,0.00006082044,0.6989371,0.006248291,0.005229627,0.0154126,0.2685157],"study_design_scores_gemma":[0.00001057831,0.00002074285,0.0001230521,0.000004577994,0.000007979041,0.0000121858,0.000002016013,0.9976405,0.0005648859,0.001208645,0.0004004896,0.000004398266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08910874,0.004787091,0.8872855,0.001062101,0.0002276666,0.0001940182,0.002202381,0.01164901,0.003483586],"genre_scores_gemma":[0.6587011,0.002182937,0.3156389,0.001598566,0.0002392945,0.000497146,0.00919159,0.0004949045,0.01145561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02157183,"threshold_uncertainty_score":0.04289252,"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."}}