{"id":"W4353065773","doi":"10.1038/s42003-023-04583-x","title":"Learning to predict RNA sequence expressions from whole slide images with applications for search and classification","year":2023,"lang":"en","type":"article","venue":"Communications Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Government of Ontario","keywords":"Artificial intelligence; Sequence (biology); Computer science; Pattern recognition (psychology); RNA; Computational biology; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001485737,0.0000929734,0.0001022798,0.00005657585,0.0004243851,0.00001873832,0.0004038466,0.00007892549,0.000001351215],"category_scores_gemma":[0.00007694664,0.00008284219,0.00002388022,0.0001493882,0.0002181789,0.000001207176,0.0004563159,0.00008286919,0.00001659598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008229799,"about_ca_system_score_gemma":0.00004492678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003289049,"about_ca_topic_score_gemma":0.00005939018,"domain_scores_codex":[0.9992834,0.00008991529,0.0001344567,0.0002920957,0.00002968149,0.0001704204],"domain_scores_gemma":[0.9988262,0.0001466871,0.00003987759,0.0007968963,0.0001262933,0.00006405212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000170133,0.00001586199,0.007517048,0.000004058663,0.00003639673,2.966494e-8,0.0001755955,0.000126821,0.9788905,0.0005202043,0.0004485117,0.01224793],"study_design_scores_gemma":[0.0009108534,0.0009543459,0.1366418,0.00003718237,0.00007565224,0.000004811399,0.003369103,0.003248519,0.07742869,0.002253044,0.7745602,0.0005158514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699503,0.001618875,0.02117839,0.004728117,0.0000298517,0.001013695,0.000673665,0.00003930666,0.0007678418],"genre_scores_gemma":[0.9750766,0.001726695,0.0200781,0.00009626846,0.00005970173,0.001198907,0.001400278,0.00001615492,0.0003473146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9014618,"threshold_uncertainty_score":0.3378206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06754984848920954,"score_gpt":0.3415877077218251,"score_spread":0.2740378592326155,"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."}}