{"id":"W4388006581","doi":"10.1016/j.compbiomed.2023.107621","title":"Drug–target affinity prediction method based on multi-scale information interaction and graph optimization","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Chongqing; Chinese Academy of Sciences; Natural Science Foundation Project of Chongqing, Chongqing Science and Technology Commission; National Natural Science Foundation of China","keywords":"Interpretability; Computer science; Granularity; Data mining; Interaction information; Graph; Benchmark (surveying); Machine learning; Artificial intelligence; Representation (politics); Theoretical computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000359533,0.0007736104,0.001363909,0.002443505,0.0008119441,0.0006102985,0.001263686,0.0008798707,0.002622073],"category_scores_gemma":[0.001194134,0.0003559442,0.001340241,0.001593633,0.0003301351,0.001224893,0.0006356224,0.0007339543,0.0004212318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006458471,"about_ca_system_score_gemma":0.00119351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007966674,"about_ca_topic_score_gemma":0.009303489,"domain_scores_codex":[0.9995999,0.00008413084,0.00002142524,0.0001123023,0.0001442225,0.00003807086],"domain_scores_gemma":[0.999577,0.0002332497,0.000035651,0.00003403585,0.00009439816,0.00002572532],"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":[0.0002883709,0.0004457028,0.004458125,0.0003758395,0.0003441603,0.0003088016,0.00006053901,0.7250175,0.01028766,0.01470437,0.009472866,0.234236],"study_design_scores_gemma":[0.00001126163,0.00001864277,0.0003093279,0.000002220988,0.00002688822,0.00002889029,0.000004277352,0.9967462,0.0004873711,0.002063346,0.0002955447,0.000006039424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09354807,0.001321657,0.8952486,0.0005155485,0.0001266359,0.0002462101,0.0004799466,0.002284905,0.006228472],"genre_scores_gemma":[0.7338141,0.0006866208,0.2589151,0.0002910295,0.0001060659,0.0002987612,0.001341675,0.0002288778,0.004317805],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007966674,"threshold_uncertainty_score":0.01584059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02558420766581722,"score_gpt":0.3555734968437154,"score_spread":0.3299892891778982,"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."}}