{"id":"W2885580909","doi":"10.1101/395954","title":"Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting","year":2018,"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":"Genome Canada; Toronto Centre for Phenogenomics; University of Toronto","funders":"Canada Research Chairs; Nvidia","keywords":"Inpainting; Artificial intelligence; Convolutional neural network; Feature (linguistics); Microscopy; Computer science; Pattern recognition (psychology); Fluorescence microscope; Proteome; Computer vision; Image (mathematics); Biology; Bioinformatics; Fluorescence; Pathology; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000555278,0.0006419181,0.0005270932,0.0002156514,0.0003335328,0.0003581609,0.000628679,0.000707511,0.0000182302],"category_scores_gemma":[0.0002666127,0.0006708044,0.0003104477,0.0003358045,0.0002198074,0.00001898421,0.0005943725,0.0005779072,0.000009787691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009248286,"about_ca_system_score_gemma":0.0003552295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003576811,"about_ca_topic_score_gemma":0.000004592291,"domain_scores_codex":[0.9969614,0.0001962491,0.0004382889,0.00153497,0.0002515901,0.0006174631],"domain_scores_gemma":[0.9965405,0.00004978143,0.0005822023,0.001553477,0.001090655,0.0001833398],"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":[0.00007958152,0.000190985,0.005225426,0.000393812,0.0001403944,0.0000119664,0.00001277993,0.00008178887,0.9860563,7.899609e-7,0.007804587,0.000001595776],"study_design_scores_gemma":[0.0006413994,0.0003809665,0.00111117,0.0001584072,0.0002807332,3.486334e-8,0.00001965992,0.0001769758,0.9846163,5.876408e-7,0.01182155,0.0007921788],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9637081,0.001311851,0.03261809,0.0001270269,0.0001327852,0.001382305,0.0001144754,0.0003960831,0.000209266],"genre_scores_gemma":[0.9120875,0.0002041192,0.08608848,0.0001616576,0.0006107874,0.0003502434,0.0000206681,0.0002381542,0.0002383981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05347039,"threshold_uncertainty_score":0.9995743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007864029598822538,"score_gpt":0.2322485897655482,"score_spread":0.2243845601667256,"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."}}