{"id":"W3015713838","doi":"10.1371/journal.pcbi.1007783","title":"Deep reinforcement learning for the control of microbial co-cultures in bioreactors","year":2020,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Innovative Microfluidic and Catalytic Techniques Innovation","field":"Engineering","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"H2020 European Research Council; European Commission; Natural Sciences and Engineering Research Council of Canada; Wellcome Trust","keywords":"Bioreactor; Reinforcement learning; Reinforcement; Biology; Biochemical engineering; Microbiology; Artificial intelligence; Computer science; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001011872,0.0006993258,0.0006521474,0.0002318751,0.0002520831,0.0005207793,0.0008445885,0.000772716,0.0009275334],"category_scores_gemma":[0.002526291,0.0003140299,0.000392002,0.000163052,0.0009178757,0.0004427379,0.0007285852,0.001095833,0.0001244135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009124134,"about_ca_system_score_gemma":0.0009263239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006465342,"about_ca_topic_score_gemma":0.004203813,"domain_scores_codex":[0.9997641,0.00006983792,0.0000127186,0.00005663819,0.00005089104,0.00004578855],"domain_scores_gemma":[0.9989213,0.0007141562,0.000132238,0.00004706435,0.0001297487,0.00005550879],"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":[0.00003129959,0.00002537335,0.0003187739,0.00002441482,0.00001492712,0.00001843602,0.00001459965,0.9896371,0.001626629,0.00111695,0.00009911707,0.007072468],"study_design_scores_gemma":[0.000004024646,0.00001256686,0.00003531494,0.000001403809,0.000001860872,0.000001642143,0.000001148783,0.9991357,0.0003070386,0.0004491929,0.00004881719,0.000001322976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1452561,0.0005533782,0.849831,0.0004623568,0.00008162422,0.00005588404,0.00004444003,0.0006549693,0.003060193],"genre_scores_gemma":[0.9721868,0.00008221127,0.02647114,0.0000780264,0.00001363512,0.00007180743,0.00002680554,0.00002236869,0.00104719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006465342,"threshold_uncertainty_score":0.01285541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01714102203565858,"score_gpt":0.25526875325128,"score_spread":0.2381277312156214,"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."}}