{"id":"W4405356247","doi":"10.1093/bioinformatics/btae738","title":"DiffPaSS—high-performance differentiable pairing of protein sequences using soft scores","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity","funders":"H2020 European Research Council; European Commission; Cancer Research UK","keywords":"Python (programming language); Hyperparameter; Computer science; Differentiable function; Pairing; Benchmark (surveying); Artificial intelligence; Similarity (geometry); Machine learning; Theoretical computer science; Graph; Data mining; 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":[0.0002159897,0.0002024521,0.0002030099,0.00008798632,0.00009238211,0.00009670749,0.0002445217,0.0001622042,0.00002066896],"category_scores_gemma":[0.00001719829,0.0001654928,0.00008789519,0.0001568883,0.0001227502,0.00003302262,0.000166675,0.0001230388,0.00001822162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002126012,"about_ca_system_score_gemma":0.0001287943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001911617,"about_ca_topic_score_gemma":0.000004735108,"domain_scores_codex":[0.998793,0.00001241939,0.000548434,0.0001396843,0.0001907762,0.0003156651],"domain_scores_gemma":[0.9993966,0.00001107669,0.0001506655,0.0003145796,0.00005785941,0.00006919234],"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":[0.0002411831,0.0002347698,0.00799331,0.01341234,0.001112368,0.00001079753,0.002382671,0.02764627,0.7602105,0.007680523,0.005297699,0.1737776],"study_design_scores_gemma":[0.0004326488,0.0003983432,0.0007374763,0.0009290671,0.00007153462,0.00003885241,0.0002471402,0.7812956,0.2075457,0.0005494461,0.007164512,0.0005896618],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9595784,0.0009887717,0.0380736,0.00002079184,0.0002511707,0.0002714448,0.00003627697,0.00003700053,0.0007425284],"genre_scores_gemma":[0.9818252,0.0001389838,0.01732518,0.00004431902,0.0001680222,0.00001192178,0.00007627296,0.00002195599,0.0003881733],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7536494,"threshold_uncertainty_score":0.6748601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01334288746656521,"score_gpt":0.2266625405328697,"score_spread":0.2133196530663045,"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."}}