{"id":"W4413777087","doi":"10.7554/elife.106557.3","title":"Unsupervised pipeline for the identification of cortical excitatory and inhibitory neurons in high-density multielectrode arrays with ground-truth validation","year":2025,"lang":"en","type":"article","venue":"eLife","topic":"Neuroscience and Neural Engineering","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research","keywords":"Pipeline (software); Excitatory postsynaptic potential; Inhibitory postsynaptic potential; Neuroscience; Multielectrode array; Identification (biology); Ground truth; Biology; Computer science; Computational biology; Chemistry; Artificial intelligence; Microelectrode","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":[],"consensus_categories":[],"category_scores_codex":[0.0002474852,0.0000902074,0.0001149936,0.0001046558,0.0001301106,0.00003360446,0.0001320651,0.00002748154,6.811345e-7],"category_scores_gemma":[0.0008888939,0.00006674072,0.00002127025,0.0003693796,0.0001429205,0.0001752624,0.00003065627,0.0001419034,6.841851e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001753018,"about_ca_system_score_gemma":0.00003804261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000185013,"about_ca_topic_score_gemma":0.000008489871,"domain_scores_codex":[0.9990309,0.00006327931,0.0002586174,0.000297431,0.0001876493,0.0001621186],"domain_scores_gemma":[0.9989808,0.000702473,0.00006276213,0.0001870664,0.00003779653,0.00002912007],"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":[0.00006396561,0.00003652311,0.0005326582,0.00002428439,7.780912e-7,0.000001482613,0.00006386452,0.0005504003,0.9960175,0.0022544,0.00002900125,0.0004250983],"study_design_scores_gemma":[0.0004605246,0.00004931525,0.04390724,0.0000161011,0.00001188136,0.000002731229,0.0000340884,0.03842036,0.9169058,0.00008431835,0.00004341788,0.00006420825],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777865,0.00002154514,0.02119261,0.0003354489,0.0002880798,0.0003278598,0.000004733373,0.00003277528,0.00001037841],"genre_scores_gemma":[0.99939,0.00005763445,0.0000533698,0.0003640708,0.00002813443,0.00003298059,0.000001198368,0.000008279455,0.00006430048],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07911173,"threshold_uncertainty_score":0.2721608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01948993463507645,"score_gpt":0.2563638021901065,"score_spread":0.23687386755503,"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."}}