{"id":"W4362585021","doi":"10.1101/2023.03.31.532253","title":"Clinical Phenotype Prediction From Single-cell RNA-seq Data using Attention-Based Neural Networks","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Prevention of Organ Failure; University of British Columbia; Simon Fraser University","funders":"","keywords":"Phenotype; Computational biology; RNA-Seq; Cell; Gene; Cell type; Clinical phenotype; Biology; Artificial intelligence; Computer science; Machine learning; Gene expression; Transcriptome; Genetics","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":[0.0007986135,0.001075048,0.0006818277,0.0008616438,0.0002046618,0.0005492336,0.0007098435,0.0007426933,0.0008426206],"category_scores_gemma":[0.001743686,0.0002555748,0.0007531361,0.0003985619,0.0002695971,0.0003890763,0.000483495,0.0008617312,0.0003308633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005725913,"about_ca_system_score_gemma":0.000498215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006243442,"about_ca_topic_score_gemma":0.007091071,"domain_scores_codex":[0.9997059,0.00006185956,0.00001660659,0.000136038,0.00003693084,0.00004274826],"domain_scores_gemma":[0.9991862,0.0004561703,0.00008789107,0.00005285273,0.0001559032,0.00006094705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001407582,0.0005128813,0.0867357,0.00030222,0.0004697443,0.0007625422,0.0001269459,0.5387462,0.05223583,0.00101248,0.009759759,0.3079282],"study_design_scores_gemma":[0.0000112834,0.00004336827,0.003595332,0.000006395087,0.00002556311,0.00003654852,0.000009158321,0.9923368,0.003085462,0.0006312541,0.0002108454,0.000007925866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6656559,0.002650304,0.3188342,0.001333862,0.0002222866,0.0001853781,0.00364493,0.004480113,0.002992998],"genre_scores_gemma":[0.9576342,0.0002664797,0.03624677,0.000435653,0.00009181851,0.0001156778,0.003558919,0.00005720001,0.001593347],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006243442,"threshold_uncertainty_score":0.01241422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0673354430605662,"score_gpt":0.2677749198109569,"score_spread":0.2004394767503906,"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."}}