{"id":"W4399666047","doi":"10.1371/journal.pcbi.1011361","title":"Using random forests to uncover the predictive power of distance-varying cell interactions in tumor microenvironments","year":2024,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Australian Cancer Research Foundation; Sylvia and Charles Viertel Charitable Foundation","keywords":"Spatial analysis; Computer science; Predictive power; Random forest; Medicine; Computational biology; Biology; Machine learning; Statistics; Mathematics","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":[0.005211934,0.001196822,0.001277611,0.00180842,0.0005981167,0.0009752905,0.00135421,0.001101507,0.001164709],"category_scores_gemma":[0.008137507,0.0005217073,0.002092162,0.001112437,0.0006526909,0.0006807921,0.000761917,0.001290468,0.0003872045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005781234,"about_ca_system_score_gemma":0.001047755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01125592,"about_ca_topic_score_gemma":0.01015563,"domain_scores_codex":[0.9990005,0.0005371649,0.00003822683,0.000226919,0.00008213102,0.0001149943],"domain_scores_gemma":[0.9942904,0.004751575,0.0003156152,0.0002443446,0.0002525105,0.0001456301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.000339686,0.0001113386,0.02146698,0.0001157034,0.0002980733,0.000208804,0.00006684184,0.9411588,0.002049844,0.002927588,0.002029304,0.02922712],"study_design_scores_gemma":[0.0000154469,0.00001605021,0.0009284036,0.000006749203,0.00001720768,0.00001711234,0.00001311456,0.9953777,0.0002643427,0.003163247,0.0001743901,0.000006329584],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4143862,0.001483388,0.5757072,0.001186408,0.0001400134,0.000111955,0.002741423,0.00305649,0.00118686],"genre_scores_gemma":[0.8961462,0.000244301,0.09852751,0.0002699971,0.0001066512,0.0001551547,0.003695189,0.000157914,0.0006970213],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01125592,"threshold_uncertainty_score":0.02756369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02008696633596184,"score_gpt":0.2696427358771207,"score_spread":0.2495557695411589,"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."}}