{"id":"W1995229312","doi":"10.1142/s0219720005001247","title":"SPIDER: SOFTWARE FOR PROTEIN IDENTIFICATION FROM SEQUENCE TAGS WITH <i>DE NOVO</i> SEQUENCING ERROR","year":2005,"lang":"en","type":"article","venue":"Journal of Bioinformatics and Computational Biology","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":219,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Software; Identification (biology); Sequence (biology); Computational biology; Computer science; Sequence assembly; Protein sequencing; DNA sequencing; Protein methods; Biology; Peptide sequence; Genetics; Programming language; Gene; Transcriptome","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001546866,0.00009342268,0.0001509491,0.00004530614,0.0001039253,0.00003462086,0.0001263552,0.00007651613,0.00001351616],"category_scores_gemma":[0.00005599511,0.00007448206,0.00003814614,0.00005652034,0.00007203313,0.0001943652,0.00002000048,0.0001277519,0.000001414109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009126718,"about_ca_system_score_gemma":0.0001616882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004250966,"about_ca_topic_score_gemma":0.0000022144,"domain_scores_codex":[0.9992181,0.000005251888,0.0004969251,0.0000801169,0.0000789159,0.0001206959],"domain_scores_gemma":[0.9988296,0.00009905844,0.0006289744,0.00007846984,0.0003060081,0.00005785797],"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":[0.0004958736,0.0002445225,0.002711826,0.0004941821,0.0003012584,0.000005732489,0.001975368,0.07340942,0.6475952,0.0464915,0.0004625802,0.2258126],"study_design_scores_gemma":[0.002865173,0.0006378797,0.000241709,0.0004396632,0.0001207791,0.0008416473,0.0008891415,0.4355762,0.2244607,0.313185,0.02002792,0.0007142203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3158525,0.00005926822,0.6832618,0.0005388982,0.000006612708,0.0001059169,0.0001180227,0.00001636245,0.00004061325],"genre_scores_gemma":[0.3827417,0.00001409225,0.616873,0.0001652071,0.00008021114,0.00002490357,0.00007869518,0.000005571759,0.00001654563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4231344,"threshold_uncertainty_score":0.3037291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02106295977740671,"score_gpt":0.2886165250035087,"score_spread":0.267553565226102,"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."}}