{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000577271,0.0001068223,0.0002389035,0.0001080913,0.00003852903,0.000005187138,0.0001338934,0.0001099381,0.00001334162],"category_scores_gemma":[0.00007391497,0.00008820536,0.00009639912,0.00006429317,0.000065159,0.000001227975,0.00008100388,0.0002465507,3.526488e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001187357,"about_ca_system_score_gemma":0.0002443286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008277783,"about_ca_topic_score_gemma":0.00009756019,"domain_scores_codex":[0.9990594,0.00008806021,0.0004401043,0.0001579176,0.0001242522,0.0001303068],"domain_scores_gemma":[0.9991711,0.00005785772,0.0002877703,0.0001005467,0.0003407312,0.00004198344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003840746,0.001588644,0.439153,0.000007209058,0.000303802,0.00000303884,0.0001591645,0.01079124,0.5446686,0.001003244,0.0001575658,0.001780492],"study_design_scores_gemma":[0.001943092,0.002223394,0.9894063,0.000003733387,0.00001630041,0.00001823088,0.0002326433,0.001431343,0.001629479,0.002297501,0.0007052417,0.00009272111],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928434,0.00007124783,0.006071332,0.0002381323,0.0003620857,0.0001248685,0.00004451984,6.472819e-7,0.0002437277],"genre_scores_gemma":[0.9937514,0.00001431427,0.005797144,0.0001751036,0.0002219165,0.000004039056,0.00002308157,0.000006454355,0.000006544325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5502533,"threshold_uncertainty_score":0.359691,"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."}}