{"id":"W4311890421","doi":"10.48084/etasr.5230","title":"Classification of Macromolecules Based on Amino Acid Sequences Using Deep Learning","year":2022,"lang":"en","type":"article","venue":"Engineering Technology & Applied Science Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Word2vec; Embedding; Word embedding; Task (project management); Machine learning; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); 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":[0.002144333,0.0001168503,0.0001203444,0.0009772428,0.0005609475,0.0000216888,0.0009769717,0.0001075085,0.00001573896],"category_scores_gemma":[0.0005779847,0.0001244527,0.00002914193,0.001902875,0.0006142085,0.000005345057,0.0005661826,0.0008396702,0.000004147762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001726538,"about_ca_system_score_gemma":0.000227961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004568516,"about_ca_topic_score_gemma":5.89185e-7,"domain_scores_codex":[0.998135,0.00004888879,0.0002113076,0.0003701274,0.0007474701,0.0004871541],"domain_scores_gemma":[0.9992093,0.00003844361,0.00008941894,0.0004874167,0.000122108,0.00005333202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001251032,0.00002019198,0.0009363109,0.0000160632,0.000003604183,0.000001080536,0.00003000417,0.1991641,0.7950245,0.002874878,0.000004147342,0.001912676],"study_design_scores_gemma":[0.0001320353,0.0003088968,0.0005222572,0.000008124502,0.000002162347,0.00001110462,0.000428118,0.5300649,0.4672057,0.00009051675,0.001104562,0.0001216083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9663767,0.00007546297,0.03224988,0.0001641761,0.00005131475,0.0002138346,0.000003979403,0.00008162266,0.000783004],"genre_scores_gemma":[0.9798132,0.000006217098,0.02002646,0.00001174498,0.00001722874,0.00007635143,0.00001370837,0.00001723781,0.0000178721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3309009,"threshold_uncertainty_score":0.5075034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02226822236046992,"score_gpt":0.3170238563315601,"score_spread":0.2947556339710902,"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."}}