About this Research Topic
From Siri to alphaGo, to self-driving cars, the world is witnessing the rapid progress of artificial intelligence
(AI). While science fiction often portrays AI as robots with human-like characteristics, AI has been explored significantly in various biomedical fields including pharmacology. The Years of 2016 and 2017 have captured a lot of excitements in AI-powered drug discovery. The best-known machine-learning methods based drug discovery application, IBM Watson, suggests new drug treatment by mining massive amounts of textual data (i.e., electronic health records and scientific literature), and then ranking potential new hypotheses. In addition, in the US, Japan and China, government have launched various research programs to apply AI to accelerate drug discovery. For example, a recent paper in Nature Biotechnology by Sarangdhar et al at Cincinnati Children’s Hospital, developed a tool named AERSMine, which automatically mines the FDA Adverse Event Reporting System (FAERS) database through systematic normalization, unification and ontological recognition of drugs, clinical indications and adverse events to enable large clinical cohort identification and studies of differential long-term outcomes between treatment regimens.
Therefore, we would like to dedicate this Research Topic in Frontiers in Pharmacology to have a timely, focused and in-depth exploration of state-of- art AI technologies, from theoretical foundations to translational applications for the broad audience of the journal. Our goal is to investigate in which areas the driverless Tesla in pharmacology is happening today, and what are the challenges and future directions.
We look forward to welcoming both reviews and original research submissions in the following areas
Infrastructure development for artificial intelligence applications in pharmacology
o Pharmacology related ontology and controlled terminology development and refinement
o Semantic harmonization and ontology alignment for pharmaceutical research
o Pharmacology database or knowledge base development
o Data integration, knowledge visualization and representation tools
Machine learning algorithms and predictive models built for pharmacology
o Data mining and text mining methods dedicated for pharmacology
o Natural language processing dedicated for pharmacology
o Information extraction on biomedical, clinical, or other data source dedicated for pharmacology
o Quantitative predictive and simulation models dedicated for pharmacology
Applications in translational pharmacology
o Individual drug response
o Clinical PK/PD predictions
o Drug safety prediction and pharmacovigilance
o Drug repurposing and refinement
o Therapeutic regimen design
o Pharmacogenetics/Pharmacogenomics
o Pharmacology biomarker identification
(AI). While science fiction often portrays AI as robots with human-like characteristics, AI has been explored significantly in various biomedical fields including pharmacology. The Years of 2016 and 2017 have captured a lot of excitements in AI-powered drug discovery. The best-known machine-learning methods based drug discovery application, IBM Watson, suggests new drug treatment by mining massive amounts of textual data (i.e., electronic health records and scientific literature), and then ranking potential new hypotheses. In addition, in the US, Japan and China, government have launched various research programs to apply AI to accelerate drug discovery. For example, a recent paper in Nature Biotechnology by Sarangdhar et al at Cincinnati Children’s Hospital, developed a tool named AERSMine, which automatically mines the FDA Adverse Event Reporting System (FAERS) database through systematic normalization, unification and ontological recognition of drugs, clinical indications and adverse events to enable large clinical cohort identification and studies of differential long-term outcomes between treatment regimens.
Therefore, we would like to dedicate this Research Topic in Frontiers in Pharmacology to have a timely, focused and in-depth exploration of state-of- art AI technologies, from theoretical foundations to translational applications for the broad audience of the journal. Our goal is to investigate in which areas the driverless Tesla in pharmacology is happening today, and what are the challenges and future directions.
We look forward to welcoming both reviews and original research submissions in the following areas
Infrastructure development for artificial intelligence applications in pharmacology
o Pharmacology related ontology and controlled terminology development and refinement
o Semantic harmonization and ontology alignment for pharmaceutical research
o Pharmacology database or knowledge base development
o Data integration, knowledge visualization and representation tools
Machine learning algorithms and predictive models built for pharmacology
o Data mining and text mining methods dedicated for pharmacology
o Natural language processing dedicated for pharmacology
o Information extraction on biomedical, clinical, or other data source dedicated for pharmacology
o Quantitative predictive and simulation models dedicated for pharmacology
Applications in translational pharmacology
o Individual drug response
o Clinical PK/PD predictions
o Drug safety prediction and pharmacovigilance
o Drug repurposing and refinement
o Therapeutic regimen design
o Pharmacogenetics/Pharmacogenomics
o Pharmacology biomarker identification
Keywords: Artificial intelligence, machine learning, predictive model, computational pharmacology, translational medicine
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
