The advances in Artificial intelligence (AI) have successfully propagated into the many areas such as computer vision, speech recognition and natural language processing. AI is now rapidly propagating into the areas requiring substantial domain expertise such as biology, chemistry promising to speeding up, improving the success rates, and lower the cost of drug discovery and drug development.
This new trend resulted in a wave of academic publications in the field of AI-powered drug discovery, a plethora of startups developing new strategies and pursuing the innovative business models to transform the pharmaceutical research and development. The pharmaceutical industry is also strengthening its internal capabilities in this area by centralizing the previously segregated data sources, hiring data scientists and investing in infrastructure.
The applications of AI in drug discovery are very broad and can be classified into several areas:
1. Knowledge discovery and hypothesis generation
2. Target identification
3. Compound generation
4. Virtual screening
5. ADME/Tox
6. Predicting the outcomes of clinical trials and clinical trials enrollment
7. Personalized medicine
8. Real-world evidence analysis and actuarial pharmacology
The advent of artificial intelligence in the pharmaceutical industry is expected to enable the countries that did not previously engage in early-stage drug discovery and innovative medicine to leapfrog years of pharma R&D and contribute to the global push for better health. With 1.4 billion people and the government push for innovative medicines, China is expected to become the major force in the pharmaceutical industry. The authors hope that the trade wars do not impact this important field. Cancer, Alzheimer's and other diseases do not discriminate by nation. Until there is a clear set of cures, a trade war in biotechnology R&D is equivalent to a war on all people. Advances in biomedicine require massive international collaborations, diversity and data sharing initiatives.
The Research Topic covers new AI algorithms and (or) applications in a wide range of areas such as drug target identification, systems biology, pharmacogenomics, network pharmacology, chemical property prediction, synthesis planning, molecular design and generation, protein-ligand interaction, drug-target interaction network, drug-related knowledge graphs, big data analysis for drug information, and image recognition. This Research Topic will highlight the most recent advances and perspectives of on all kinds of artificial intelligence technologies used in drug design.
In this Research Topic the authors welcome Perspective and Policy papers proposing the paths for development of innovative medicines using AI and accelerating pharma R&D in the developed and developing countries.
Articles based solely on in silico techniques should be submitted through the sections Pharmacogenetics and Pharmacogenomics or Translational Pharmacology.
Topic editor Alex Zhavoronkov is the founder of Insilico Medicine, a company specializing in AI research. He is also a professor at the Buck Institute for Research on Aging. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
The advances in Artificial intelligence (AI) have successfully propagated into the many areas such as computer vision, speech recognition and natural language processing. AI is now rapidly propagating into the areas requiring substantial domain expertise such as biology, chemistry promising to speeding up, improving the success rates, and lower the cost of drug discovery and drug development.
This new trend resulted in a wave of academic publications in the field of AI-powered drug discovery, a plethora of startups developing new strategies and pursuing the innovative business models to transform the pharmaceutical research and development. The pharmaceutical industry is also strengthening its internal capabilities in this area by centralizing the previously segregated data sources, hiring data scientists and investing in infrastructure.
The applications of AI in drug discovery are very broad and can be classified into several areas:
1. Knowledge discovery and hypothesis generation
2. Target identification
3. Compound generation
4. Virtual screening
5. ADME/Tox
6. Predicting the outcomes of clinical trials and clinical trials enrollment
7. Personalized medicine
8. Real-world evidence analysis and actuarial pharmacology
The advent of artificial intelligence in the pharmaceutical industry is expected to enable the countries that did not previously engage in early-stage drug discovery and innovative medicine to leapfrog years of pharma R&D and contribute to the global push for better health. With 1.4 billion people and the government push for innovative medicines, China is expected to become the major force in the pharmaceutical industry. The authors hope that the trade wars do not impact this important field. Cancer, Alzheimer's and other diseases do not discriminate by nation. Until there is a clear set of cures, a trade war in biotechnology R&D is equivalent to a war on all people. Advances in biomedicine require massive international collaborations, diversity and data sharing initiatives.
The Research Topic covers new AI algorithms and (or) applications in a wide range of areas such as drug target identification, systems biology, pharmacogenomics, network pharmacology, chemical property prediction, synthesis planning, molecular design and generation, protein-ligand interaction, drug-target interaction network, drug-related knowledge graphs, big data analysis for drug information, and image recognition. This Research Topic will highlight the most recent advances and perspectives of on all kinds of artificial intelligence technologies used in drug design.
In this Research Topic the authors welcome Perspective and Policy papers proposing the paths for development of innovative medicines using AI and accelerating pharma R&D in the developed and developing countries.
Articles based solely on in silico techniques should be submitted through the sections Pharmacogenetics and Pharmacogenomics or Translational Pharmacology.
Topic editor Alex Zhavoronkov is the founder of Insilico Medicine, a company specializing in AI research. He is also a professor at the Buck Institute for Research on Aging. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
![Predicted stratification variables for TMZ in glioblastoma include age, RPA class, and chemotherapeutic (Chemo) and radiotherapeutic (RT) patient status. For each stratified patient class a confusion matrix indicates the number (N) and percentage (P) of treated patients from the test set for which the CT predicts treatment response correctly (responders to predicted treatment response and non-responders to predicted non-response) with respect to the labeled SG value. E.g. the CT model predicts the class of patients aged 52 to 61 years and >63 years not receiving concomitant or adjuvant chemotherapy to respond to the treatment with a true positive (TP) probability of 58%. For this class, with patients aged < 63 years 82% are correctly predicted (true negative [TN]) not to respond.](https://www.frontiersin.org/_rtmag/_next/image?url=https%3A%2F%2Fwww.frontiersin.org%2Ffiles%2FArticles%2F472222%2Ffphar-10-01665-HTML%2Fimage_m%2Ffphar-10-01665-g002.jpg&w=3840&q=75)
