{"id":"W4387346479","doi":"10.1145/3584371.3613007","title":"AcrTransAct: Pre-trained Protein Transformer Models for the Detection of Type I Anti-CRISPR Activities","year":2023,"lang":"en","type":"article","venue":"","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CRISPR; Computational biology; Transformer; Computer science; Convolutional neural network; Palindrome; Artificial intelligence; Biology; Gene; Genetics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003587168,0.001101098,0.0004562757,0.0003839803,0.000163484,0.0003571146,0.001318912,0.0008782638,0.001408392],"category_scores_gemma":[0.0007842264,0.0002948053,0.0004912494,0.0002304746,0.0002969911,0.000557022,0.0004255234,0.001224817,0.0005238049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00092045,"about_ca_system_score_gemma":0.0007765357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006238763,"about_ca_topic_score_gemma":0.009187944,"domain_scores_codex":[0.999891,0.00001326822,0.00000474384,0.00004274276,0.00002581075,0.00002231373],"domain_scores_gemma":[0.999805,0.0000830167,0.00002826929,0.00001476604,0.00004963564,0.00001932238],"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":[0.0005770298,0.0003830892,0.009630274,0.0001973929,0.0001753218,0.00020562,0.00003724641,0.8085793,0.03197936,0.002590262,0.00861233,0.1370327],"study_design_scores_gemma":[0.000005676442,0.00002477916,0.0002822383,0.000002086689,0.000005782738,0.000014024,0.00000171468,0.9964544,0.002708522,0.0002814256,0.0002162748,0.000003143996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5271757,0.002102449,0.4475048,0.0009177558,0.00021813,0.0002195795,0.003582391,0.01101718,0.007261937],"genre_scores_gemma":[0.9299594,0.0003502521,0.05835517,0.0004127092,0.00003917035,0.0001689514,0.003878065,0.0001546641,0.006681778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006238763,"threshold_uncertainty_score":0.01240492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01250984658637825,"score_gpt":0.2892972792580063,"score_spread":0.276787432671628,"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."}}