{"id":"W4406113948","doi":"10.21203/rs.3.rs-5474597/v1","title":"DOLPHIN Advances Cell Representation Beyond Gene-Level by Integrating Exon-Level Quantification and Junction Reads with Deep Neural Networks","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Exon; Representation (politics); Deep neural networks; Gene; Computational biology; Artificial neural network; Computer science; Artificial intelligence; Biology; Genetics; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007756035,0.000873059,0.0005939413,0.0007214799,0.0003150618,0.001299486,0.001426724,0.001021201,0.003605872],"category_scores_gemma":[0.001805468,0.0004948942,0.0005073052,0.0006141713,0.000484344,0.001296782,0.001830383,0.002232002,0.001594506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007587976,"about_ca_system_score_gemma":0.0008341856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005722119,"about_ca_topic_score_gemma":0.01470525,"domain_scores_codex":[0.9996816,0.00003628442,0.00001081201,0.000131286,0.00009732066,0.00004265913],"domain_scores_gemma":[0.9994969,0.0001665143,0.00004571938,0.000137456,0.0001061455,0.00004716266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003265062,0.0001847179,0.00657996,0.0001969271,0.0002178018,0.000177611,0.0002337814,0.1371862,0.2735614,0.02926246,0.01276173,0.5393108],"study_design_scores_gemma":[0.00001111621,0.0000344764,0.001474163,0.0000151177,0.00002524494,0.0000624552,0.00002742297,0.9229481,0.05200013,0.01821386,0.005166512,0.00002142155],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06446186,0.0002237081,0.9209288,0.0003165697,0.0001395391,0.00003374783,0.00155463,0.008796555,0.003544574],"genre_scores_gemma":[0.3061962,0.0002577648,0.6769375,0.0003862887,0.00007375627,0.00007106837,0.0043466,0.001919309,0.009811473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005722119,"threshold_uncertainty_score":0.01206285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0408877096230132,"score_gpt":0.3733141391779702,"score_spread":0.332426429554957,"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."}}