{"id":"W4384695598","doi":"10.1101/2023.07.16.549209","title":"XA4C: eXplainable representation learning via Autoencoders revealing Critical genes","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Cancer Research; Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Autoencoder; Interpretability; Gene; Computational biology; Artificial intelligence; Representation (politics); Proteogenomics; Identification (biology); Computer science; Gene regulatory network; Deep learning; Machine learning; Biology; Transcriptome; Genetics; Gene expression","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":[0.001489072,0.0009201383,0.0006366935,0.0007716527,0.0003056979,0.0007152604,0.00106012,0.001068881,0.001861618],"category_scores_gemma":[0.003524273,0.000319192,0.0007796955,0.0003886941,0.0007595497,0.0006226267,0.001080148,0.001651248,0.000279481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009053632,"about_ca_system_score_gemma":0.001167223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002874705,"about_ca_topic_score_gemma":0.002373746,"domain_scores_codex":[0.9995812,0.0001077539,0.000017662,0.0001257533,0.0001000423,0.00006757867],"domain_scores_gemma":[0.9983631,0.0009545735,0.0001368946,0.0001714242,0.000299088,0.0000749156],"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":[0.0003150268,0.0001753144,0.009135205,0.0001755727,0.0001886425,0.0002745308,0.0001259406,0.8266433,0.04123812,0.01468711,0.003462515,0.1035787],"study_design_scores_gemma":[0.00000823025,0.00002186832,0.0004403668,0.000004182918,0.000006943154,0.00001091584,0.000005671477,0.9918499,0.003683414,0.003734412,0.0002286546,0.000005484892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.141616,0.0002462049,0.8528113,0.000479927,0.00006816096,0.00009399352,0.000489764,0.002923275,0.001271236],"genre_scores_gemma":[0.7176464,0.0001259297,0.2783386,0.0003274842,0.00003549345,0.0002198489,0.001170007,0.0002481446,0.001888068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002874705,"threshold_uncertainty_score":0.007875085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01869351765031502,"score_gpt":0.2533643475254421,"score_spread":0.2346708298751271,"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."}}