{"id":"W4410077458","doi":"10.1038/s41467-025-59189-0","title":"GelGenie: an AI-powered framework for gel electrophoresis image analysis","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Genetics; Medical Research Council; Harvard University; Technische Universität München; University at Albany; University of Edinburgh; Wellcome Trust; Tsinghua University; State University of New York; Hansjörg Wyss Institute for Biologically Inspired Engineering, Harvard University; School of Informatics, University of Edinburgh; Bristol-Myers Squibb","keywords":"Computer science; Segmentation; Pixel; Artificial intelligence; Image processing; Biomolecule; Electrophoresis; Image (mathematics); Pattern recognition (psychology); Computer vision; Materials science; Nanotechnology; Chemistry; Chromatography","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":[],"consensus_categories":[],"category_scores_codex":[0.0002419385,0.0001569596,0.0002269469,0.0002794933,0.0002785455,0.0000798435,0.001440918,0.0005293114,0.00001730679],"category_scores_gemma":[0.0004905987,0.0001632591,0.0003647814,0.001105854,0.0001247351,0.000008836037,0.000343386,0.0005162415,0.000002174987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003337269,"about_ca_system_score_gemma":0.00008945318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002480684,"about_ca_topic_score_gemma":0.0008607054,"domain_scores_codex":[0.9989582,0.0001324948,0.0002431917,0.0003703353,0.00008682642,0.0002089266],"domain_scores_gemma":[0.9956409,0.00008935332,0.00009399801,0.003683226,0.0004384994,0.00005400366],"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":[0.00009057891,0.0004317671,0.003305397,0.00001456073,0.002440844,4.741736e-7,0.00004200611,0.00000686046,0.9028944,0.02959671,0.05807206,0.003104294],"study_design_scores_gemma":[0.0003253798,0.0001563095,0.005882079,0.00001474362,0.002656658,0.000001269104,0.00008200059,0.001995281,0.5643452,0.01427386,0.4097901,0.0004771364],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04230908,0.04001071,0.8926584,0.01116647,0.00007155159,0.00122103,0.0001429677,0.0002783203,0.01214147],"genre_scores_gemma":[0.8125538,0.001950505,0.1812556,0.001932189,0.00004325824,0.0001707862,0.00158747,0.00001835808,0.0004880866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7702447,"threshold_uncertainty_score":0.6657513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006376299787003335,"score_gpt":0.3527707894161675,"score_spread":0.3463944896291642,"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."}}