Human bodies are incredibly complex. It may take many years to discover even just one new medicine to successfully treat a disease. Over the past 50 years, drug discovery has focused largely on high-throughput screening for known disease-associated targets. This makes drug discovery a long, expensive, and labor-consuming process. However, in combination with accumulating data from chemical, biological, biomedical, and related fields, artificial intelligence can assist researchers in developing new medicines faster, improving the quality of life for millions of people. AI is a technology-based system that utilizes advanced tools and algorithms to mimic human intelligence and handle large volumes of data more efficiently than ever. Based on the input data, AI can form inferences, predictions, evaluations, and analyses for unseen or future data. AI has thus been successfully applied to various aspects of society, particularly in medicine and pharmaceuticals. The application of AI can facilitate the discovery and development of better medicines, as well as early diagnosis and treatment of diseases.
Several studies have demonstrated that AI can be successfully applied to drug discovery, including de-novo drug design, quantitative structure-activity relationship analysis (QSAR), network pharmacology, chemical space visualization, and inverse molecular design based on generative models. In this Research Topic "Artificial Intelligence and Drug Discovery", we expect but are not limited to the following: (1) the development of novel AI algorithms/tools that can accelerate drug discovery; (2) identifying potential structures for future drug development; and (3) identifying the mechanisms of action (MOA) between drugs and targets by using artificial intelligence.
This Research Topic aims to publish significant research including review, min-review, and research articles that highlight new concepts, insights, and findings covering all aspects of the multidisciplinary fields of chemical and drug design.
1. Design, synthesis, and evaluation of novel receptor agonists/antagonists
2. Network pharmacology utilized in the discovery of natural products and drug design
3. Macromolecule (protein, peptide, peptidomimetic, nucleic acid, lipids, carbohydrate) drug design
4. Novel structure-based drug design techniques include molecular modeling, virtual screening, and chemoinformatics
5. Bioinformatics used in proteomics, chemical genomics, and molecular screening technologies for target identification
6. New algorithms of toxicity, pharmacology, ADMET, and drug delivery
7. Quantitative structure-activity relationship (QSAR) studies on toxicology or pharmacokinetic properties of active scaffolds
8. Inverse molecular design/generation by employing generative models including deep learning, genetic algorithms, or related AI technologies
9. Diagnose diseases by analyzing clinical images with the help of artificial intelligence
10. Application of artificial intelligence and clinic test of biomarkers in early disease diagnosis
11. Big data analysis by artificial intelligence on clinical cases for diseases prevention and prognostic judgment
Please note: All the manuscripts submitted to the collection will need to fully comply with the Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here) and that network analysis without any experimental verification is unacceptable
Human bodies are incredibly complex. It may take many years to discover even just one new medicine to successfully treat a disease. Over the past 50 years, drug discovery has focused largely on high-throughput screening for known disease-associated targets. This makes drug discovery a long, expensive, and labor-consuming process. However, in combination with accumulating data from chemical, biological, biomedical, and related fields, artificial intelligence can assist researchers in developing new medicines faster, improving the quality of life for millions of people. AI is a technology-based system that utilizes advanced tools and algorithms to mimic human intelligence and handle large volumes of data more efficiently than ever. Based on the input data, AI can form inferences, predictions, evaluations, and analyses for unseen or future data. AI has thus been successfully applied to various aspects of society, particularly in medicine and pharmaceuticals. The application of AI can facilitate the discovery and development of better medicines, as well as early diagnosis and treatment of diseases.
Several studies have demonstrated that AI can be successfully applied to drug discovery, including de-novo drug design, quantitative structure-activity relationship analysis (QSAR), network pharmacology, chemical space visualization, and inverse molecular design based on generative models. In this Research Topic "Artificial Intelligence and Drug Discovery", we expect but are not limited to the following: (1) the development of novel AI algorithms/tools that can accelerate drug discovery; (2) identifying potential structures for future drug development; and (3) identifying the mechanisms of action (MOA) between drugs and targets by using artificial intelligence.
This Research Topic aims to publish significant research including review, min-review, and research articles that highlight new concepts, insights, and findings covering all aspects of the multidisciplinary fields of chemical and drug design.
1. Design, synthesis, and evaluation of novel receptor agonists/antagonists
2. Network pharmacology utilized in the discovery of natural products and drug design
3. Macromolecule (protein, peptide, peptidomimetic, nucleic acid, lipids, carbohydrate) drug design
4. Novel structure-based drug design techniques include molecular modeling, virtual screening, and chemoinformatics
5. Bioinformatics used in proteomics, chemical genomics, and molecular screening technologies for target identification
6. New algorithms of toxicity, pharmacology, ADMET, and drug delivery
7. Quantitative structure-activity relationship (QSAR) studies on toxicology or pharmacokinetic properties of active scaffolds
8. Inverse molecular design/generation by employing generative models including deep learning, genetic algorithms, or related AI technologies
9. Diagnose diseases by analyzing clinical images with the help of artificial intelligence
10. Application of artificial intelligence and clinic test of biomarkers in early disease diagnosis
11. Big data analysis by artificial intelligence on clinical cases for diseases prevention and prognostic judgment
Please note: All the manuscripts submitted to the collection will need to fully comply with the Four Pillars of Best Practice in Ethnopharmacology (you can freely download the full version here) and that network analysis without any experimental verification is unacceptable