{"id":"W4283074493","doi":"10.1101/2022.06.17.496550","title":"3D single-cell shape analysis using geometric deep learning","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Stand Up To Cancer; Terry Fox Foundation; Cancer Research UK","keywords":"Deep learning; Interpretability; Autoencoder; Artificial intelligence; Computer science; Cluster analysis; Shape analysis (program analysis); Pattern recognition (psychology); Biological system; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009480885,0.0007538407,0.0009116361,0.001752885,0.0003629656,0.000304451,0.001049277,0.0007057425,0.0005757878],"category_scores_gemma":[0.0003604199,0.0009349748,0.000827908,0.003542673,0.0001196179,0.00001475767,0.002305901,0.001144708,0.00001641023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003587604,"about_ca_system_score_gemma":0.0002827485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009495751,"about_ca_topic_score_gemma":0.000005511487,"domain_scores_codex":[0.9956353,0.0003908837,0.0007591691,0.001870241,0.0006000157,0.0007443663],"domain_scores_gemma":[0.9962311,0.00003983216,0.0008561948,0.002078613,0.0005331432,0.0002610624],"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":[0.00002151174,0.0002512203,0.01686597,0.0001155821,0.001311608,0.0000571742,0.000003835527,0.006983625,0.9742693,0.000001594717,0.000104035,0.00001452384],"study_design_scores_gemma":[0.0003375667,0.0001860549,0.006696745,0.00003189405,0.003323377,3.912734e-8,0.00001020938,0.01800328,0.9506185,2.503142e-7,0.01925613,0.001535964],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9544165,0.005192714,0.03936664,0.00001104394,0.0001503657,0.0004225419,0.00004200202,0.0002943293,0.000103848],"genre_scores_gemma":[0.9784905,0.0007416479,0.01984079,0.0001550344,0.0003784942,0.0001181361,0.00001341589,0.0002133976,0.0000486234],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02407394,"threshold_uncertainty_score":0.9993101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01262520283049172,"score_gpt":0.2326907053152819,"score_spread":0.2200655024847902,"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."}}