{"id":"W3185631395","doi":"10.1101/2021.07.28.454016","title":"Automated Reconstruction of Whole-Embryo Cell Lineages by Learning from Sparse Annotations","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Medical Research Council; York University; Howard Hughes Medical Institute","keywords":"Terabyte; Computer science; Identification (biology); Embryo; Artificial intelligence; Lineage (genetic); Process (computing); Cell lineage; Deep learning; 3D reconstruction; Computational biology; Biology; Pattern recognition (psychology); Cellular differentiation; Cell biology; Gene; Genetics","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":[0.0002820833,0.000419703,0.0005247941,0.0001648062,0.0001021244,0.0001430028,0.000373735,0.0007005433,0.00005172902],"category_scores_gemma":[0.0002389117,0.0005144955,0.000256029,0.0002871618,0.0001368925,0.00001592768,0.0004462327,0.0005449672,0.00001135931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005627073,"about_ca_system_score_gemma":0.0003515729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001869087,"about_ca_topic_score_gemma":0.000008062694,"domain_scores_codex":[0.9976213,0.0002414199,0.0006264453,0.0009942089,0.0002239128,0.0002927259],"domain_scores_gemma":[0.9972736,0.0000278622,0.0007030584,0.001117088,0.0007515859,0.0001268102],"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":[0.00001155447,0.0001201269,0.003360233,0.00009730986,0.0002186275,0.000009513445,0.000005785931,0.0002842012,0.9930484,6.429187e-7,0.002836426,0.000007228195],"study_design_scores_gemma":[0.0002526261,0.00004981968,0.006077253,0.0001522167,0.0002150381,1.959628e-8,0.00001700321,0.002314512,0.9870402,2.302432e-7,0.003403212,0.0004778327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893298,0.002925333,0.00670895,0.00003596742,0.0001675683,0.0002590899,0.000182952,0.0003648729,0.00002553607],"genre_scores_gemma":[0.9829886,0.001121077,0.01535306,0.00005722343,0.0002122345,0.00006956002,0.00005881557,0.00009938645,0.00004002963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008644109,"threshold_uncertainty_score":0.9997306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007415810058085588,"score_gpt":0.220669851767982,"score_spread":0.2132540417098964,"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."}}