{"id":"W4385567285","doi":"10.1101/2023.08.04.410498","title":"Can a Sparse 2 <sup>9</sup> × 2 <sup>9</sup> Pixel Chaos Game Representation Predict Protein Binding Sites using Fine-Tuned State-of-the-Art Deep Learning Semantic Segmentation Models?","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Representation (politics); Segmentation; Fractal; Field (mathematics); Artificial intelligence; Pixel; Binary number; Natural language processing; Theoretical computer science; Space (punctuation); Pattern recognition (psychology); Algorithm; Mathematics; Arithmetic; Pure 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006875292,0.000719187,0.000717924,0.0004241165,0.0003251068,0.0002305986,0.0006533243,0.0005385454,0.00002014668],"category_scores_gemma":[0.0005124266,0.0007116929,0.0004421389,0.001007519,0.0002151786,0.00007984705,0.0008270774,0.0007264138,0.00002752026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000234386,"about_ca_system_score_gemma":0.0005051533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004373052,"about_ca_topic_score_gemma":0.00004651535,"domain_scores_codex":[0.9956282,0.0004360778,0.001002482,0.001481031,0.0007120849,0.0007401034],"domain_scores_gemma":[0.9968463,0.00004371544,0.001003622,0.001297045,0.0005799832,0.0002294032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005850674,0.00006535908,0.00735572,0.0003109378,0.0003272616,0.00001624976,0.0001067375,0.3109694,0.6807485,0.000007432095,0.00002293967,0.00001095675],"study_design_scores_gemma":[0.0005715756,0.0001109145,0.001581918,0.0005469715,0.0003546989,1.630588e-7,0.00009221549,0.3889781,0.6069331,0.00002487759,0.00007989165,0.0007255957],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9851435,0.0003751852,0.01240363,0.0001556246,0.0001432577,0.001400287,0.0002140601,0.0001608498,0.000003592156],"genre_scores_gemma":[0.9959038,0.0002426709,0.002794275,0.00004928451,0.00031889,0.0003117346,0.00005552459,0.0001931892,0.0001306061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07800864,"threshold_uncertainty_score":0.9995334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02397686718300486,"score_gpt":0.2399267669414027,"score_spread":0.2159498997583978,"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."}}