{"id":"W2298025969","doi":"10.1049/iet-syb.2014.0050","title":"Protein interaction network constructing based on text mining and reinforcement learning with application to prostate cancer","year":2015,"lang":"en","type":"article","venue":"IET Systems Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Novelis (Canada)","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Interaction network; Node (physics); Computer science; Network topology; Matching (statistics); Artificial intelligence; Construct (python library); Degree distribution; Process (computing); Machine learning; Theoretical computer science; Complex network; Topology (electrical circuits); Mathematics; Computer network; Engineering; Chemistry","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":[0.0002989366,0.0001258033,0.0001399881,0.00003088625,0.00007085883,0.00003017379,0.00005668763,0.0001129174,0.000001183523],"category_scores_gemma":[0.0000197419,0.0001000176,0.00001379701,0.00006528688,0.00003821235,0.000003626225,0.00004260055,0.00008170379,0.000003606439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003213407,"about_ca_system_score_gemma":0.00005890859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008159014,"about_ca_topic_score_gemma":0.00004496953,"domain_scores_codex":[0.9992232,0.00006102857,0.0002192023,0.0002276553,0.00005259845,0.0002162765],"domain_scores_gemma":[0.9994981,0.00001182112,0.0001721621,0.0001442982,0.0000798154,0.00009376146],"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":[0.0008868666,0.00001346284,0.03249148,0.0001035504,0.00007273658,9.303314e-7,0.0005490234,0.8954445,0.03838531,0.0004914835,0.001107862,0.03045281],"study_design_scores_gemma":[0.003648939,0.006555657,0.0003088824,0.0008338401,0.00005857243,0.00008618196,0.005466023,0.7493938,0.004975945,0.00005411572,0.2275329,0.001085198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8895063,0.000310339,0.1059377,0.0001814857,0.0003614963,0.001305328,0.000005441485,0.00002796727,0.0023639],"genre_scores_gemma":[0.9976456,0.000006619257,0.001210067,0.0001959718,0.0003185835,0.0002895207,0.00008068582,0.00001342519,0.0002395352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.226425,"threshold_uncertainty_score":0.40786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009604138591629195,"score_gpt":0.2471417774650317,"score_spread":0.2375376388734025,"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."}}