{"id":"W2134563544","doi":"10.1109/csb.2004.1332434","title":"SPIDER: software for protein identification from sequence tags with de novo sequencing error","year":2004,"lang":"en","type":"article","venue":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Software; Identification (biology); Sequence (biology); Computer science; Computational biology; Protein sequencing; DNA sequencing; Sequence assembly; Peptide sequence; Biology; Genetics; Programming language; DNA; Gene; Transcriptome","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":[0.0003929963,0.0006028618,0.00057123,0.0002152801,0.0006004092,0.0006033154,0.0007156718,0.0003808161,0.00004030722],"category_scores_gemma":[0.0001750104,0.0005872151,0.0001316377,0.0005585771,0.0002311394,0.001116765,0.00005536058,0.0004623245,0.00006974686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001516228,"about_ca_system_score_gemma":0.001473023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002632054,"about_ca_topic_score_gemma":0.00002638099,"domain_scores_codex":[0.996388,0.000007550624,0.00143119,0.0006615795,0.0007390354,0.00077263],"domain_scores_gemma":[0.9959291,0.00007501566,0.00132868,0.0003608832,0.001999194,0.0003071423],"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":[0.000341305,0.0006240064,0.001543005,0.005684847,0.0004731579,0.00001784665,0.005310812,0.7151078,0.1658207,0.0994555,0.001930192,0.003690794],"study_design_scores_gemma":[0.00654508,0.0004650761,0.0001266928,0.005879856,0.0003146405,0.0006206707,0.0042498,0.5761903,0.2191181,0.1781784,0.004721899,0.003589453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1109267,0.0001677286,0.883888,0.0001988186,0.00008158712,0.0021153,0.0008897309,0.000693427,0.001038732],"genre_scores_gemma":[0.5757914,0.000007499173,0.4211148,0.00009013346,0.0002122873,0.001664692,0.0006309094,0.00006907307,0.0004191812],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4648647,"threshold_uncertainty_score":0.9996579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03549132856981759,"score_gpt":0.2753646704719921,"score_spread":0.2398733419021745,"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."}}