{"doi":"10.1055/a-2810-8972","title":"Artificial Intelligence in Drug Discovery and Development:\n                    Raising Quality per Decision","abstract":"<jats:title>Abstract</jats:title>\n                  <jats:p>Drug research and development continuously encounters prolonged timelines,\n                    escalating costs, and high attrition rates. In this narrative review, we\n                    integrated recent advances in artificial intelligence across target\n                    identification, drug repurposing, de novo molecular design, structural biology,\n                    safety prediction, and artificial intelligence-supported clinical development,\n                    aligning these innovations with evolving global regulatory frameworks.\n                    Predictive and interpretable artificial intelligence could enhance the quality\n                    of decision-making throughout the research and development process when combined\n                    with causal or mechanistic priors, synthesis-aware and physics-informed\n                    molecular design, external validation with clear applicability domains, and\n                    governance systems aligned with multiple regulatory guidelines and qualified\n                    digital endpoint applications. Case studies of artificial intelligence-assisted\n                    discovery and repurposing demonstrate shorter development timelines, improved\n                    compound quality, and higher-level early-phase success, while underscoring\n                    challenges such as overfitting, model generalizability, and dataset bias.\n                    Establishing a context-of-use-based “credibility plan” and adopting\n                    equity-by-design through the inclusion of non-European datasets and subgroup\n                    performance evaluation are essential for achieving generalizable impact.\n                    Artificial intelligence integration with new approach methodologies and adaptive\n                    or covariate-adjusted clinical trials may help reduce development inefficiency\n                    without compromising scientific or ethical rigor.</jats:p>","journal":"Pharmacopsychiatry","year":2026,"id":613104,"datarank":0.10397207708399181,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.0,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":487337,"name":"Hiroyuki Uchida","orcid":"0000-0002-0628-7036","position":1,"is_corresponding":false},{"id":283011,"name":"Taishiro Kishimoto","orcid":"0000-0003-0557-8648","position":2,"is_corresponding":false},{"id":1579223,"name":"Shota Furukawa","orcid":"0009-0002-9343-5259","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Artificial Intelligence in Drug Discovery and Development:\n                    Raising Quality per Decision","abstract":"<jats:title>Abstract</jats:title>\n                  <jats:p>Drug research and development continuously encounters prolonged timelines,\n                    escalating costs, and high attrition rates. In this narrative review, we\n                    integrated recent advances in artificial intelligence across target\n                    identification, drug repurposing, de novo molecular design, structural biology,\n                    safety prediction, and artificial intelligence-supported clinical development,\n                    aligning these innovations with evolving global regulatory frameworks.\n                    Predictive and interpretable artificial intelligence could enhance the quality\n                    of decision-making throughout the research and development process when combined\n                    with causal or mechanistic priors, synthesis-aware and physics-informed\n                    molecular design, external validation with clear applicability domains, and\n                    governance systems aligned with multiple regulatory guidelines and qualified\n                    digital endpoint applications. Case studies of artificial intelligence-assisted\n                    discovery and repurposing demonstrate shorter development timelines, improved\n                    compound quality, and higher-level early-phase success, while underscoring\n                    challenges such as overfitting, model generalizability, and dataset bias.\n                    Establishing a context-of-use-based “credibility plan” and adopting\n                    equity-by-design through the inclusion of non-European datasets and subgroup\n                    performance evaluation are essential for achieving generalizable impact.\n                    Artificial intelligence integration with new approach methodologies and adaptive\n                    or covariate-adjusted clinical trials may help reduce development inefficiency\n                    without compromising scientific or ethical rigor.</jats:p>","is_dataset_classified":null,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"41786310","pmcid":"PMC13288427","openalex_id":"https://openalex.org/W7133723330","authors":[],"funders":[],"total_grants":0,"fwci":8.2322,"citation_percentile":0.96223236,"influential_citations":0,"citation_trend":[{"year":2026,"count":1}],"oa_status":"hybrid","license":"cc-by","oa_locations":[{"url":"http://www.thieme-connect.de/products/ejournals/pdf/10.1055/a-2810-8972.pdf","host_type":"journal"},{"url":"http://www.thieme-connect.de/products/ejournals/pdf/10.1055/a-2810-8972.pdf","host_type":"publisher"},{"url":"https://doi.org/10.1055/a-2810-8972","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/41786310","host_type":"repository"},{"url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13288427/","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC13288427","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC13288427?pdf=render","host_type":"Europe_PMC"}],"fields_of_study":["Computational Drug Discovery Methods","Chemistry and Chemical Engineering","Machine Learning in Materials Science"],"mesh_terms":["Drug Development","Artificial Intelligence","Decision Making","Humans","Drug Discovery"],"keywords":["Repurposing","Quality (philosophy)","Process (computing)","Drug development","Inefficiency","Drug discovery","Corporate governance"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Peace, Justice and strong institutions"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"doi"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-02T06:37:26.060864Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}