{"id":"W4200434821","doi":"10.1101/2021.12.04.471198","title":"Modeling the trajectory of SARS-CoV-2 spike protein evolution in continuous latent space using a neural network and Gaussian process","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Spike (software development); Genome evolution; Computational biology; Reverse vaccinology; Computer science; ENCODE; Viral evolution; In silico; Biology; Sequence (biology); Genome; Artificial intelligence; Genetics; Gene","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":[0.0007689126,0.000436819,0.000346911,0.0004008557,0.000263985,0.0005406974,0.0006383132,0.0008840882,0.001170969],"category_scores_gemma":[0.001862909,0.0003478349,0.0006524471,0.0002948953,0.0007786396,0.0006269045,0.000549993,0.001110373,0.000159777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001223485,"about_ca_system_score_gemma":0.0008933789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02945959,"about_ca_topic_score_gemma":0.01675454,"domain_scores_codex":[0.9998353,0.00005156241,0.000006897598,0.00004778945,0.00002517441,0.00003334171],"domain_scores_gemma":[0.9992988,0.0004898268,0.0000758604,0.00002452187,0.00007248748,0.00003854359],"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":[0.00002780413,0.00001204344,0.00170723,0.000005649565,0.000009650498,0.00002181387,0.00001269499,0.9948738,0.0003978474,0.001022721,0.00007263174,0.001836106],"study_design_scores_gemma":[8.06598e-7,0.000002204707,0.00007120138,4.381677e-7,5.795375e-7,9.276788e-7,7.751216e-7,0.9996691,0.00004299498,0.0002000208,0.00001014442,7.055147e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6630393,0.0002455817,0.3335778,0.0006926483,0.00004394127,0.00002890626,0.0003104129,0.0005208969,0.001540461],"genre_scores_gemma":[0.9846134,0.00006472554,0.01351727,0.00005261351,0.000009417909,0.00002494259,0.0001796819,0.00002054165,0.001517395],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02945959,"threshold_uncertainty_score":0.05857623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02086886025261638,"score_gpt":0.2327689140927971,"score_spread":0.2119000538401807,"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."}}