{"id":"W3189217046","doi":"10.1101/2021.08.04.453579","title":"A comparison of data integration methods for single-cell RNA sequencing of cancer samples","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University Health Network; University of Toronto; SickKids Foundation; Hospital for Sick Children; Princess Margaret Cancer Centre","funders":"","keywords":"Tumour heterogeneity; Computational biology; Data integration; Computer science; Stromal cell; Cancer; Biology; Data mining; Cancer research; Genetics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006723108,0.0003803692,0.0007554458,0.0001034432,0.00006160942,0.0000621603,0.0008013696,0.0005598902,0.00001020202],"category_scores_gemma":[0.0003329723,0.0004102589,0.0002030554,0.0001837111,0.0001269435,0.00001525155,0.000494491,0.0002846133,1.80399e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009175995,"about_ca_system_score_gemma":0.0009380073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003914812,"about_ca_topic_score_gemma":0.00007330727,"domain_scores_codex":[0.9976293,0.000189941,0.0007970755,0.0009176594,0.0001722371,0.0002937402],"domain_scores_gemma":[0.9967147,0.00008055881,0.0007448142,0.001547962,0.0008149393,0.00009701925],"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":[0.00008012306,0.0002407698,0.003016651,0.0009616819,0.0001969823,6.122088e-7,0.00002935227,0.000211217,0.9950392,0.00002196481,0.00005838146,0.0001430406],"study_design_scores_gemma":[0.000436328,0.000146017,0.0006094202,0.0004103126,0.0002503232,5.64776e-9,0.00003022364,0.003236487,0.9932287,9.105884e-7,0.001259357,0.0003919088],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6864387,0.007847574,0.3036491,0.00002164163,0.0006580923,0.0004594226,0.0008967405,0.00002278747,0.000005920044],"genre_scores_gemma":[0.7675486,0.0003905467,0.2316453,0.00003238994,0.0002214094,0.00006185432,0.00002857631,0.0000694656,0.000001944876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08110985,"threshold_uncertainty_score":0.999835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1062657001524413,"score_gpt":0.3527888210694112,"score_spread":0.2465231209169699,"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."}}