{"id":"W4414874842","doi":"10.1101/2025.10.06.680609","title":"A Fully Automated, Data-Driven Approach for Dimensionality Reduction and Clustering in Single-Cell RNA-seq Analysis","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Basic Science","keywords":"Cluster analysis; Principal component analysis; Pipeline (software); Dimensionality reduction; Noise (video); Reliability (semiconductor); Curse of dimensionality; Rand index; Clustering high-dimensional data","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003045486,0.001638051,0.001522631,0.001918268,0.001517912,0.0028001,0.002976955,0.001238285,0.004620314],"category_scores_gemma":[0.006441825,0.001160942,0.002502889,0.001569767,0.000843467,0.001255629,0.00306822,0.002701208,0.006115175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001384982,"about_ca_system_score_gemma":0.003432518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004892235,"about_ca_topic_score_gemma":0.009730181,"domain_scores_codex":[0.9970812,0.0005976892,0.0001969758,0.0009023706,0.001059007,0.000162707],"domain_scores_gemma":[0.9958931,0.001046196,0.0002611327,0.001045539,0.001484781,0.0002691086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007016775,0.0003980262,0.00831768,0.0009887522,0.0005835905,0.000505269,0.0007422052,0.1485781,0.1932317,0.01555827,0.0676336,0.5627612],"study_design_scores_gemma":[0.00007373866,0.00007761527,0.00351001,0.00005167965,0.00004789086,0.0001656031,0.000147546,0.8899809,0.0601992,0.02546534,0.02011308,0.0001674513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007579072,0.0001435712,0.9741161,0.0002722802,0.00008549108,0.000146822,0.001370218,0.01566465,0.0006216315],"genre_scores_gemma":[0.04772821,0.000115158,0.9437078,0.0002799336,0.00005946738,0.0004187883,0.004215313,0.0022426,0.001232766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004892235,"threshold_uncertainty_score":0.01610625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275353656902388,"score_gpt":0.2445770830104641,"score_spread":0.2170417173202253,"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."}}