Did you know that the current cost of bringing new drugs to the market is around US$ 2.5 billion? An increase of ~145% from 2003, as per the study on drug costing was published in the Journal of Health Economics by Tufts Center for the Study of Drug Development. During the period, the average time to bring clinical trials has declined along with a decrease in the rate of success fallen by almost half which is just 12%.
Traditional drug discovery methods are based on the target-driven method. This approach works well for certainly druggable targets whose interactions inside the cell are identified in detail and are well-defined structures. However, these traditional methods are limited due to the complex nature of cellular interactions.
Drug development has been an expensive undertaking in spite of continuing efforts across the full spectrum of biotech and pharmaceutical companies to lead in growing research & development costs. The R&D process is marked by considerable technical risks, with expenditures for various research and development projects that fail to result in a marketed product. Pharmaceutical companies differ from the category of businesses of other industries, as research and development in medical platforms involve great risk. The risk can be measured by the fact that only one out of every 10,000 discovered compounds get authorization for marketing.
Increasing drug development costs have been driven majorly due to higher failure rates for drugs tested in human subjects and an increase in out-of-pocket costs for drug development.
Artificial intelligence (AI) has the potential to make changes in drug discovery along with challenges. The issue of future drug discovery focuses on AI for the purposes of drug discovery. AI and machine learning will usher in an era of cheaper, quicker, and more effective drug discovery. The advancement in AI for drug discovery will change the R&D process of BioPharma, and it will make a tremendous impact on the biopharma industry. Machine intelligence has witnessed an upsurge in the application in chemical sciences, particularly in the design of new chemical entities.
Drug companies are pursuing AI on other avenues with adding decision-making ability and the ability to learn to a traditional number-crunching role with a computer in changing work patterns by the research scientist.
Integration of AI in drug discovery has a dramatic impact on Biopharma companies. Most sizeable biopharmaceutical companies believe a solution is at hand. For instance, Pfizer partnered with IBM Watson Health to use the technology for Drug Discovery’s machine learning platform to help immuno-oncology research of Pfizer. Exscientia announced that Sanofi exercised its option to progress an innovative project related to Bispecific Small molecule as a part of its new modality collaboration.
Growth of the AI in Drug Discovery Industry
Astute Analytica predicted that the Artificial Intelligence in the Drug Discovery Market is witnessing a compounded annual growth rate of 42% during 2021-2027. The increasing cost of prescription drugs is a key factor that influences the growth of the global marketplace. Failure in results from increasing investment into treatments and increasing complexity of advanced medicines makes R&D more expensive and opens the opportunity for AI integration in healthcare. The market is majorly driven by the rise of personalized medicine in tests for big data and clinical decision-making in the healthcare industry and the increasing adoption of artificial intelligence in genetics. Also, AI-created healthcare wearables and other real-time monitoring systems are playing a crucial role in the digital monitoring of healthcare.
Application of AI within the Drug Discovery Process
- Synthesizing and aggregating information
- Understanding mechanisms of diseases
- Development of new therapeutic molecules
- Technologies reducing manual work and increasing efficiency.
- Identification of new pathways and targets
- Generating novel drug candidates
Benefits of Applying AI to Drug Discovery
- The application of AI to drug discovery has the potential to revolutionize the current scope and time scale of drug discovery.
- AI is subjective bias and existing knowledge is not a decisive factor for the development process. It does not rely on predetermined targets for drug discovery.
- AI has a higher predictive power to describe important interactions in a drug screen which can result in a reduction of false positives by carefully designing the parameters of the assay in question.
- AI uses the advancement in computing and biology to develop state-of-the-art algorithms for drug discovery.
- AI has the potential to level the playing field in drug development along with a reduction in processing cost and increase in processing power.
- AI can move drug screening from the bench to a virtual lab. Where results can be obtained with promising targets and high speed and can be shortlisted without the demand for manpower hours and extensive experimental input.
AI algorithms have been optimized to do a task. A monitored learning algorithm is designed to find statistical patterns in a training dataset. Applications of AI raise various ethical questions, particularly in the event of an error in the role of each stakeholder. Implementation of AI has a rapid technical advance that comes with regulatory and ethical concerns to leave time to identify the potential drawbacks and risks with high clarity.