{"id":"W2994163036","doi":"10.1101/868935","title":"Fast and flexible design of novel proteins using graph neural networks","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"graph theory and CDMA systems","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Compute Canada; Nvidia","keywords":"Artificial neural network; Protein design; Graph; Constraint (computer-aided design); Sequence (biology); Function (biology); Variety (cybernetics); Protein sequencing","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":[0.0003335728,0.0005442545,0.0004000474,0.0004420398,0.0002737334,0.0004175326,0.0006044665,0.0007370766,0.002000768],"category_scores_gemma":[0.0008036438,0.0003255528,0.0003823382,0.0003640283,0.0005244506,0.0005939917,0.0004867585,0.0006411955,0.0003455777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057097,"about_ca_system_score_gemma":0.0006880459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003160127,"about_ca_topic_score_gemma":0.004986141,"domain_scores_codex":[0.9998355,0.00003725796,0.000006663804,0.00004887296,0.00004509517,0.00002667421],"domain_scores_gemma":[0.9997459,0.0001147694,0.00003864614,0.00003041339,0.0000469099,0.00002329759],"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":[0.00007053833,0.00006465286,0.0005008463,0.00006654174,0.00002272706,0.00005658785,0.00003075003,0.8992613,0.02295454,0.01123334,0.001762839,0.06397539],"study_design_scores_gemma":[0.000005371042,0.00001289025,0.00003462044,0.000001896987,0.000002142472,0.000004661647,0.000002878222,0.9957418,0.001770708,0.00194611,0.0004749222,0.000001971862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.15561,0.0003909341,0.8349085,0.0005539527,0.0001153257,0.0001000533,0.0001005647,0.001639975,0.006580733],"genre_scores_gemma":[0.7060995,0.0002109129,0.2880335,0.0002605082,0.0000222629,0.000144653,0.0001958051,0.0001709689,0.00486202],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003160127,"threshold_uncertainty_score":0.007669866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155690015186338,"score_gpt":0.2020136164678765,"score_spread":0.1804567163160131,"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."}}