{"id":"W2004998616","doi":"10.1089/cmb.2009.0031","title":"Towards Improved Assessment of Functional Similarity in Large-Scale Screens: A Study on Indel Length","year":2010,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Indel; Sequence alignment; Computer science; Hidden Markov model; Similarity (geometry); Markov chain; Multiple sequence alignment; Sequence (biology); Alignment-free sequence analysis; Computational biology; Algorithm; Structural alignment; Biology; Genetics; Artificial intelligence; Gene; Machine learning; Peptide sequence; Image (mathematics)","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":[0.002793755,0.0006869186,0.001089248,0.001539821,0.0002971579,0.0009171143,0.0007986667,0.0008367056,0.0007057297],"category_scores_gemma":[0.008795622,0.0002952928,0.0005011948,0.0009198814,0.0005024457,0.001254873,0.0008967295,0.0009944708,0.0002855672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004111169,"about_ca_system_score_gemma":0.000384106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005036423,"about_ca_topic_score_gemma":0.0006822405,"domain_scores_codex":[0.9983699,0.0005531937,0.0001140386,0.0003541204,0.000528826,0.0000800635],"domain_scores_gemma":[0.9945852,0.003583893,0.0007147956,0.000509183,0.0004380776,0.0001687935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007776917,0.0004563017,0.02085446,0.0006170624,0.0002059295,0.00040607,0.0001958312,0.05192343,0.7281849,0.003798214,0.0003742549,0.192206],"study_design_scores_gemma":[0.00006154794,0.001332614,0.03149765,0.00005343117,0.0002499794,0.001217441,0.0001438022,0.6234311,0.3344184,0.005734137,0.001733393,0.0001264977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5273446,0.002021216,0.4658544,0.0001813242,0.00002113684,0.0001754616,0.0004218846,0.002689649,0.001290484],"genre_scores_gemma":[0.7329132,0.0006925334,0.26461,0.0001214055,0.00001585281,0.0001142116,0.0005959237,0.0002975839,0.0006393822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002793755,"threshold_uncertainty_score":0.01477498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01758547139780474,"score_gpt":0.3092551470240396,"score_spread":0.2916696756262349,"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."}}