{"id":"W4318751336","doi":"10.48550/arxiv.2301.12068","title":"Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Tencent; Canadian Institute for Advanced Research; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Microsoft Research","keywords":"Computer science; Encoder; Trajectory; Sequence (biology); Joint probability distribution; Conformational isomerism; Diffusion; Mutual information; Joint (building); Artificial intelligence; Algorithm; Mathematics; Engineering; Physics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008863105,0.001316383,0.001025402,0.0007416314,0.0003500761,0.0006522957,0.001638592,0.001467672,0.002941685],"category_scores_gemma":[0.00349618,0.0006060685,0.0007220464,0.0007010611,0.0007477818,0.001592705,0.001010106,0.002449341,0.002030477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001037502,"about_ca_system_score_gemma":0.001771628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005433665,"about_ca_topic_score_gemma":0.008153098,"domain_scores_codex":[0.9996724,0.000063702,0.00001865187,0.0001171617,0.00008261706,0.00004548103],"domain_scores_gemma":[0.9986889,0.0006240659,0.00009698675,0.0002186289,0.0002769335,0.00009448967],"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":[0.0003858036,0.0002752734,0.003310448,0.0003055729,0.000110869,0.000245784,0.0001455005,0.5003259,0.030291,0.01591778,0.0153646,0.4333215],"study_design_scores_gemma":[0.000008024323,0.00002007423,0.0001010168,0.000004688158,0.000004921725,0.00002617242,0.000005941406,0.9923372,0.004262115,0.002637118,0.0005884257,0.000004336781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04670964,0.0007354458,0.941597,0.0005356333,0.000111346,0.00007536641,0.0004999269,0.008062574,0.001672989],"genre_scores_gemma":[0.5321144,0.0009161197,0.4498955,0.0008586985,0.0001234989,0.0002645815,0.004871885,0.0008473943,0.01010783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005433665,"threshold_uncertainty_score":0.01080412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05094002654711007,"score_gpt":0.2090181692533215,"score_spread":0.1580781427062114,"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."}}