{"id":"W4223485171","doi":"10.1101/2022.04.11.487796","title":"Multimodal single cell data integration challenge: results and lessons learned","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Helmholtz Artificial Intelligence Cooperation Unit; Deutsche Forschungsgemeinschaft; Chan Zuckerberg Initiative; Silicon Valley Community Foundation","keywords":"Benchmarking; Modalities; Computer science; Pipeline (software); Data science; Task (project management); Data integration; Artificial intelligence; Big data; Machine learning; Competition (biology); Concatenation (mathematics); Modality (human–computer interaction); Data mining; Biology","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":[0.0006166322,0.0004879948,0.0003822534,0.0001141917,0.0002386529,0.0001763504,0.0009215993,0.0005854301,0.00001890334],"category_scores_gemma":[0.0002441798,0.0005481467,0.00009513262,0.0001367845,0.0001291547,0.00001599581,0.00160591,0.0007508794,0.000006238995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000767468,"about_ca_system_score_gemma":0.0003400327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001356997,"about_ca_topic_score_gemma":0.00003773953,"domain_scores_codex":[0.996998,0.0001964168,0.0004765411,0.001643967,0.0002714577,0.0004136658],"domain_scores_gemma":[0.9970837,0.00002952942,0.0003108249,0.00219968,0.0001846743,0.0001915983],"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":[0.0001998809,0.0003564665,0.0002249084,0.0001351551,0.0000718235,0.0000144982,0.000019292,0.00008479929,0.9982704,0.00004079623,0.0005304205,0.00005158768],"study_design_scores_gemma":[0.002205143,0.0004879901,0.003933767,0.0001366627,0.0001729401,4.093853e-8,0.0000285744,0.002702766,0.9095839,0.000003502214,0.07941312,0.00133163],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9858751,0.004113597,0.003219133,0.001150781,0.001467379,0.0006861279,0.003199034,0.000158463,0.0001303918],"genre_scores_gemma":[0.9923524,0.002264765,0.004420487,0.000129094,0.0005328251,0.00006359931,0.00007437501,0.0001244831,0.0000379837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0886865,"threshold_uncertainty_score":0.999697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05509391982350474,"score_gpt":0.2675372987133045,"score_spread":0.2124433788897997,"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."}}