{"id":"W4386304573","doi":"10.1016/j.chembiol.2023.08.002","title":"Target deconvolution with matrix-augmented pooling strategy reveals cell-specific drug-protein interactions","year":2023,"lang":"en","type":"article","venue":"Cell chemical biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Innovative Medicines Initiative; Kungliga Tekniska Högskolan; National Natural Science Foundation of China; European Commission; McGill University; Innovative Health Initiative; European Federation of Pharmaceutical Industries and Associations; National Institutes of Health; Horizon 2020 Framework Programme; Science, Technology and Innovation Commission of Shenzhen Municipality; Ontario Institute for Cancer Research; National Institute of General Medical Sciences; Diamond Light Source","keywords":"Deconvolution; Computational biology; Pooling; Profiling (computer programming); Drug; Drug discovery; Proteome; Drug target; Chemistry; Computer science; Biology; Bioinformatics; Pharmacology; Algorithm; Artificial intelligence; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003576094,0.0002022939,0.0002385773,0.0001833088,0.0001050679,0.00007277385,0.0005977988,0.00009418274,0.00006920697],"category_scores_gemma":[0.00003120398,0.0001809434,0.00008166748,0.0008081481,0.00009856538,0.0002312852,0.0002988279,0.0002930969,0.0003993017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001184961,"about_ca_system_score_gemma":0.00009094244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001404358,"about_ca_topic_score_gemma":5.452376e-7,"domain_scores_codex":[0.998203,0.000227955,0.000347733,0.0006363856,0.0001421861,0.0004426879],"domain_scores_gemma":[0.9987819,0.0004533248,0.0001484543,0.0003866215,0.0001043213,0.0001254422],"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":[0.00004078399,0.0001031967,0.0001790636,0.00003515277,0.00001670677,0.00001635796,0.0001233676,0.007344372,0.9721492,0.01279991,0.005747231,0.001444666],"study_design_scores_gemma":[0.0009289511,0.0001207895,0.000429249,0.00004676288,0.00001043293,0.00002903307,0.0001083713,0.098312,0.8224794,0.06901862,0.007934731,0.0005816803],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6788674,0.000338783,0.3178486,0.0004607388,0.0002691876,0.0002256573,0.00001401121,0.0002976446,0.001677967],"genre_scores_gemma":[0.9425499,0.00001682177,0.05635006,0.00006914421,0.0001272011,0.00005104296,0.0001276243,0.00001632168,0.0006919067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2636825,"threshold_uncertainty_score":0.7378657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.023119679672083,"score_gpt":0.2984630953558,"score_spread":0.275343415683717,"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."}}