{"id":"W2973034691","doi":"10.1038/s41592-019-0529-1","title":"Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":427,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia Hospital; University of British Columbia; BC Cancer Agency; Terry Fox Research Institute; BC Children's Hospital","funders":"Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; University of British Columbia; National Cancer Institute; Cancer Research UK; Government of Canada","keywords":"RNA-Seq; Profiling (computer programming); Computational biology; Single-cell analysis; Tumor microenvironment; RNA; Cell; Biology; Probabilistic logic; Gene expression profiling; Transcriptome; Computer science; Genetics; Gene; Gene expression; Tumor cells; Cancer research; Artificial intelligence","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":[0.001168523,0.0003918507,0.0007780485,0.0004121313,0.0004608298,0.001105096,0.0008016904,0.0007864112,0.001227293],"category_scores_gemma":[0.002176128,0.000573825,0.0005599654,0.0006060255,0.0004939912,0.0006433286,0.0007898603,0.001111993,0.0006052277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006216934,"about_ca_system_score_gemma":0.0007225041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001964077,"about_ca_topic_score_gemma":0.006354568,"domain_scores_codex":[0.9992556,0.0001456374,0.00002604457,0.0002967766,0.000206767,0.00006906164],"domain_scores_gemma":[0.9991331,0.0005177421,0.00008880457,0.0001028154,0.0001138053,0.00004385425],"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":[0.000429168,0.00008582926,0.007787243,0.0002893391,0.0001322689,0.0000812316,0.0002162091,0.08849249,0.8127439,0.009324225,0.001680405,0.07873771],"study_design_scores_gemma":[0.00002625902,0.00005743444,0.009556979,0.00001720702,0.00005259023,0.0001374065,0.00006475696,0.7941534,0.1789388,0.01285673,0.00408172,0.00005673955],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07471938,0.0003298572,0.9216948,0.0001117991,0.00004943319,0.00007413981,0.0009881901,0.0008324828,0.001199866],"genre_scores_gemma":[0.6567783,0.0004491253,0.3374352,0.0002819032,0.00006045051,0.0003194561,0.001998927,0.0005614061,0.002115087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001964077,"threshold_uncertainty_score":0.00617981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01624177429636534,"score_gpt":0.2872486475668399,"score_spread":0.2710068732704746,"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."}}