{"id":"W3159048693","doi":"10.1016/j.ygeno.2021.04.037","title":"ChrNet: A re-trainable chromosome-based 1D convolutional neural network for predicting immune cell types","year":2021,"lang":"en","type":"article","venue":"Genomics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba; Manitoba Medical Service Foundation","keywords":"Convolutional neural network; Biology; Cluster analysis; Computational biology; Cell type; Immune system; Identification (biology); Computer science; Chromosome; Benchmarking; Deep learning; Artificial intelligence; Gene; Cell; 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":[],"consensus_categories":[],"category_scores_codex":[0.000148616,0.0001570169,0.000169864,0.00001462179,0.0001842603,0.00003914177,0.0001493709,0.0001644147,0.00003248663],"category_scores_gemma":[0.00003497429,0.0001758934,0.0001618186,0.00007284835,0.00005512295,0.000003263037,0.00004630898,0.00009619458,0.000004433161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004172426,"about_ca_system_score_gemma":0.0003505522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001745342,"about_ca_topic_score_gemma":0.00006626452,"domain_scores_codex":[0.9989311,0.00003339896,0.000238794,0.0003464508,0.00007258551,0.0003776776],"domain_scores_gemma":[0.9994282,0.00002825608,0.00007950487,0.0002617386,0.000132172,0.00007016664],"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":[0.0001818301,0.00009401329,0.002669992,0.00007528206,0.00005159831,0.000005708111,0.00004669097,0.03741902,0.9574123,0.00005837121,0.001550246,0.0004349561],"study_design_scores_gemma":[0.002995526,0.0004963218,0.001562707,0.00002805317,0.00009583775,0.00002014651,0.0001213845,0.04521869,0.7889545,0.0002662701,0.1596948,0.0005458065],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811901,0.005348254,0.01119285,0.0002237122,0.0007365796,0.0002664705,0.0001342079,0.00002580706,0.0008819805],"genre_scores_gemma":[0.9879673,0.00009659137,0.007720164,0.0005937049,0.001238776,0.00003195807,0.001139156,0.00004416395,0.001168194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1684578,"threshold_uncertainty_score":0.7172723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01285218704210746,"score_gpt":0.2133574656275823,"score_spread":0.2005052785854748,"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."}}