{"id":"W4392103664","doi":"10.1093/bioinformatics/btae067","title":"Phenotype prediction from single-cell RNA-seq data using attention-based neural networks","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Cancer Agency; University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Artificial neural network; Phenotype; Computer science; RNA-Seq; Artificial intelligence; Computational biology; Deep neural networks; Software; Machine learning; Data mining; Pattern recognition (psychology); Biology; Gene; Genetics; Transcriptome; Gene expression","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":[0.0001268865,0.0001945323,0.0001336374,0.00005188507,0.0001039207,0.0001842425,0.0003402422,0.0002090672,0.00002470822],"category_scores_gemma":[0.00002238582,0.0001839257,0.00008772728,0.0001314999,0.00005965835,0.00003359338,0.0001105787,0.000149739,0.00001594402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002935593,"about_ca_system_score_gemma":0.00008669338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007448237,"about_ca_topic_score_gemma":0.00002439838,"domain_scores_codex":[0.9988998,0.00002499884,0.0003881877,0.0002704383,0.0001663393,0.0002502506],"domain_scores_gemma":[0.999149,0.00002470172,0.00007816623,0.0006119483,0.00005127611,0.00008491144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002356991,0.0003441049,0.003540378,0.0004611147,0.0002394693,0.00001351868,0.0002077602,0.06267089,0.8783864,0.00002333186,0.01018307,0.04369424],"study_design_scores_gemma":[0.0004000563,0.0001048373,0.0001158541,0.00005474083,0.00009209283,0.000002908825,0.00004304762,0.9845941,0.007711723,0.000009168758,0.006667504,0.0002039714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4649169,0.001566601,0.5296102,0.00005887956,0.002121815,0.0002066311,0.0006339346,0.0001091511,0.0007759472],"genre_scores_gemma":[0.977026,0.00005408788,0.01575484,0.0003070304,0.0008471074,0.000002800448,0.005870897,0.00004066416,0.00009651508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9219232,"threshold_uncertainty_score":0.7500272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03938044047685513,"score_gpt":0.2431787984064393,"score_spread":0.2037983579295842,"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."}}