{"id":"W4307277103","doi":"10.21203/rs.3.rs-2063113/v1","title":"STIFMap employs a convolutional neural network to reveal spatial mechanical heterogeneity and tension-dependent activation of an epithelial to mesenchymal transition within human breast cancers","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Cellular Mechanics and Interactions","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of California, San Francisco; Canadian Institutes of Health Research; Mark Foundation For Cancer Research; National Institutes of Health; Huntsman Cancer Institute","keywords":"Epithelial–mesenchymal transition; Mesenchymal stem cell; Convolutional neural network; Transition (genetics); Cancer research; Computational biology; Neuroscience; Computer science; Cell biology; Chemistry; Biology; Artificial intelligence; Biochemistry; Gene","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000351214,0.0004995295,0.0002126374,0.0006540605,0.0001677354,0.0003405282,0.0004779065,0.0006403591,0.0009905362],"category_scores_gemma":[0.0009012767,0.0002596301,0.0003330079,0.0003602051,0.0003141201,0.0003602629,0.0004489361,0.0004560009,0.0002518026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004831313,"about_ca_system_score_gemma":0.0004911958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006332215,"about_ca_topic_score_gemma":0.007632773,"domain_scores_codex":[0.9999179,0.0000115073,0.000002700722,0.00002549514,0.00002451834,0.00001781247],"domain_scores_gemma":[0.9998544,0.00005793073,0.00002136419,0.00002498232,0.00002740544,0.00001386278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004032921,0.000201232,0.01022997,0.0001540146,0.0001375638,0.0004984029,0.0001272119,0.5816286,0.1868273,0.003785682,0.003175242,0.2128315],"study_design_scores_gemma":[0.00000203276,0.00001637863,0.002045014,0.00000188343,0.000003853496,0.0000351619,0.000005779605,0.9908726,0.006313318,0.0004898571,0.0002103222,0.000003931235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6085816,0.0004359724,0.3841754,0.0004412982,0.0000679537,0.00005235779,0.0009170453,0.003201548,0.002126788],"genre_scores_gemma":[0.9220333,0.0001595333,0.07484458,0.00005741913,0.00001911839,0.00003875762,0.0006701437,0.0000856956,0.002091477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006332215,"threshold_uncertainty_score":0.01259071,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03868946074944938,"score_gpt":0.3602409828163839,"score_spread":0.3215515220669345,"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."}}