{"id":"W3196971188","doi":"10.1038/s41467-021-25534-2","title":"Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; McGill University","funders":"Canada First Research Excellence Fund; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Scalability; Computer science; Set (abstract data type); Computational biology; Artificial intelligence; Key (lock); Encoder; Machine learning; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007118162,0.0007507316,0.0005050544,0.0005203816,0.0001731468,0.0006547231,0.0005824843,0.0007071937,0.0007441878],"category_scores_gemma":[0.002247262,0.0002801298,0.0007555233,0.0006035005,0.00043807,0.0009500264,0.0008182856,0.001297794,0.000506832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003759307,"about_ca_system_score_gemma":0.000549934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001389285,"about_ca_topic_score_gemma":0.002340738,"domain_scores_codex":[0.9997864,0.00004573733,0.000009013794,0.0001032023,0.00002681755,0.00002881224],"domain_scores_gemma":[0.9992956,0.0004152913,0.00007251989,0.00009899692,0.00008371184,0.00003385772],"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":[0.0005348842,0.0002576961,0.02004515,0.0004118743,0.0003068826,0.0003394993,0.0003681364,0.5904483,0.1529976,0.009730389,0.005561671,0.2189979],"study_design_scores_gemma":[0.000008966957,0.00003971456,0.002368231,0.00000925218,0.00002385942,0.00004152163,0.00004437436,0.9772481,0.009751542,0.009595874,0.0008545321,0.00001403256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2249155,0.0007853433,0.7685772,0.0003962671,0.0000753927,0.00005519711,0.002673981,0.001686482,0.00083468],"genre_scores_gemma":[0.8223085,0.0007253217,0.1667709,0.0001947613,0.00009115414,0.0001736373,0.007285773,0.0001888372,0.002261079],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001389285,"threshold_uncertainty_score":0.003764451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02218157552290001,"score_gpt":0.2547764356119345,"score_spread":0.2325948600890345,"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."}}