{"id":"W4285508781","doi":"10.1101/2021.01.22.427860","title":"Evaluation of deep convolutional neural networks for in situ hybridization gene expression image representation","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Hospital for Sick Children; Centre for Addiction and Mental Health","funders":"Natural Sciences and Engineering Research Council of Canada; Centre for Addiction and Mental Health Foundation; Centre for Addiction and Mental Health; Nvidia","keywords":"Discriminative model; Artificial intelligence; Gene expression; Computer science; Pattern recognition (psychology); Convolutional neural network; In situ hybridization; Computational biology; Identification (biology); Expression (computer science); Gene; Machine learning; Biology; Genetics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009602001,0.0002730873,0.0003136354,0.0001119173,0.00006586786,0.00006575052,0.0002092414,0.000439235,0.00001029163],"category_scores_gemma":[0.0004267145,0.0003265392,0.0001586993,0.0001845641,0.00006889972,0.00001880158,0.0001468151,0.0002039648,3.37999e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001184712,"about_ca_system_score_gemma":0.0003803163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002614425,"about_ca_topic_score_gemma":0.00002352964,"domain_scores_codex":[0.9977497,0.0003057106,0.0005273911,0.0007414959,0.000416869,0.0002588486],"domain_scores_gemma":[0.9973707,0.00002696289,0.0003618619,0.0005758462,0.001590523,0.00007417506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000968061,0.0001380544,0.005441074,0.00009922784,0.00005381467,0.000001909819,0.000006810329,0.03333421,0.9607772,0.000007285317,0.00002927313,0.00001437437],"study_design_scores_gemma":[0.001071711,0.00004684553,0.03126728,0.00008711019,0.0001223421,1.886773e-8,0.00000435878,0.1111513,0.8559545,0.00000170895,0.0000159632,0.0002768827],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8216301,0.001714401,0.1751338,0.00002175997,0.0006737569,0.0007436493,0.00006092336,0.00001856265,0.000003065451],"genre_scores_gemma":[0.989239,0.0001918403,0.00971292,0.00004077479,0.0004432576,0.0002512033,0.00006092973,0.00005936571,7.420678e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1676089,"threshold_uncertainty_score":0.9999186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02292291994981664,"score_gpt":0.2556320178812655,"score_spread":0.2327090979314488,"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."}}