{"id":"W2940793299","doi":"10.1101/617225","title":"Statistical modeling, estimation, and remediation of sample index hopping in multiplexed droplet-based single-cell RNA-seq data","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research; Fondation Brain Canada; Compute Canada; Genome Canada; Alfred P. Sloan Foundation","keywords":"Sample (material); Inference; Computer science; Probabilistic logic; Sample size determination; Index (typography); Range (aeronautics); Data mining; Statistics; Algorithm; Artificial intelligence; Mathematics; Physics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01361722,0.000774438,0.001000505,0.001137502,0.0006959398,0.00138572,0.00269373,0.001343217,0.0007192344],"category_scores_gemma":[0.03551389,0.000766345,0.001206637,0.0009932356,0.001924069,0.00169262,0.001535642,0.00229501,0.0002513585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001495332,"about_ca_system_score_gemma":0.001504069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003695482,"about_ca_topic_score_gemma":0.003931648,"domain_scores_codex":[0.9970681,0.001104805,0.0001563429,0.0008659645,0.0006697972,0.000135125],"domain_scores_gemma":[0.9763282,0.01787514,0.001969907,0.002691563,0.0008967171,0.0002385082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002165719,0.0000926602,0.02537951,0.0002915616,0.0002093925,0.0003115506,0.0004334379,0.8587602,0.03078122,0.03988789,0.001543888,0.04209203],"study_design_scores_gemma":[0.000008843405,0.00002908071,0.002129962,0.00001258065,0.00001480048,0.00007367371,0.00002273546,0.9779134,0.0069012,0.01232274,0.0005411183,0.00002974162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0572365,0.0002066759,0.940639,0.0002563274,0.00002767074,0.00007656643,0.0004075324,0.0009437712,0.0002060326],"genre_scores_gemma":[0.6773347,0.0003000415,0.318548,0.0003403325,0.0000572186,0.0003963266,0.001912223,0.0003498437,0.0007612671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01361722,"threshold_uncertainty_score":0.07201558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850162425513087,"score_gpt":0.2344930699740198,"score_spread":0.2059914457188889,"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."}}