{"id":"W4396885250","doi":"10.1016/j.xpro.2024.103066","title":"Protocol to perform integrative analysis of high-dimensional single-cell multimodal data using an interpretable deep learning technique","year":2024,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Computer science; Protocol (science); Leverage (statistics); Preprocessor; Omics; Deep learning; Artificial intelligence; Data pre-processing; Imputation (statistics); Machine learning; Data mining; Computational biology; Bioinformatics; Missing data; Biology; Medicine","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":[0.0004970579,0.0002758413,0.0003852613,0.0002646319,0.0000994108,0.00009228949,0.0005200112,0.0001893867,0.0001301657],"category_scores_gemma":[0.00007256156,0.0002306706,0.0001403756,0.0005478571,0.00008082537,0.00003561655,0.00030985,0.0002727579,0.000003486822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005905312,"about_ca_system_score_gemma":0.0001799556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004450521,"about_ca_topic_score_gemma":0.0002816573,"domain_scores_codex":[0.9981197,0.0001537929,0.0004365719,0.0007617222,0.0002325034,0.0002957128],"domain_scores_gemma":[0.9988354,0.00002260679,0.000104745,0.0007255601,0.0001864294,0.0001252136],"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":[0.0005128171,0.0003838661,0.0008281317,0.0001992143,0.0002961178,0.000005204482,0.0002866303,0.004653292,0.9868376,0.00001593429,0.00003236289,0.005948812],"study_design_scores_gemma":[0.0004843469,0.001867709,0.000107345,0.0002626383,0.0001748951,0.000004077049,0.00009859518,0.2204241,0.7700747,0.00002776496,0.006140775,0.0003330683],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.3556058,0.00001530799,0.1945188,0.00001700485,0.00005839044,0.4491611,0.0002573456,0.00008319194,0.0002831288],"genre_scores_gemma":[0.6261778,2.263846e-7,0.04291715,0.00003784601,0.00009537468,0.3300936,0.0005065227,0.00004940895,0.000122088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.270572,"threshold_uncertainty_score":0.9406475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04415856584133926,"score_gpt":0.3421930555880146,"score_spread":0.2980344897466753,"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."}}