AI in Drug Discovery Cuts Timelines From 5+ Years to Months
Jun 10, 2021 Dr Nadia Tsao
IDTechEx have recently published a new report, "AI in Drug Discovery 2021: Players, Technologies, and Applications", covering the use of artificial intelligence (AI), including machine learning (ML) and deep learning (DL), in the drug discovery process. The industry has received significant attention from investors and key players in the biopharma industry during 2020, and 2021 continues to be a very exciting year for the industry.
The development of pharmaceutical drugs is a long and costly process. Companies in the pharmaceutical and biotechnology industries typically spend more than $1 billion to bring a drug to market, in a process that often lasts 10 - 15 years. Moreover, the drug development process is very risky - up to 90% of drugs being developed do not reach commercialization. A technology that can contribute significantly to addressing any of these 3 pain points has the potential to quickly grow into a multibillion-dollar industry. AI has been successfully applied to speed up virtual screening, de novo drug discovery, and can be utilized to optimize compounds to have drug-like properties. Processes that typically take several years can be reduced to a matter of months.
Architectures and Algorithms
IDTechEx's latest report, "AI in Drug Discovery 2021: Players, Technologies, and Applications", covers AI technologies, including a discussion of architectures and algorithms used in the drug discovery process. Architectures include supervised learning, unsupervised learning, reinforcement learning, algorithms include random forest, convolutional neural networks, autoencoders, recurrent neural networks, long short-term memory networks, generative adversarial networks, and more. Aspects of the drug discovery process discussed include structure-based virtual screening, ligand-based virtual screening, phenotypic virtual screening, de novo drug discovery, lead optimization, and chemical synthesis planning.
Structure-based virtual screening identifies molecules (ligands) that are predicted to bind to a biological structure (target). Structure-based virtual screening is the leading form of AI in drug discovery being funded today. Source: IDTechEx Research
For each segment of the drug discovery process covered in the report, IDTechEx analyzes key players, the capabilities of their software, technology readiness, and the progress of candidates to market. Venture funding and partnerships within virtual hit screening and de novo drug design are also covered within the report.
IDTechEx have identified almost 100 companies involved in AI in drug discovery, including over 80 founded since 2010. Though computers have been used in aiding pharmaceutical R&D for many decades and even AI itself has been applied for more than 10 years, it has only been the past few years in which the field is drastically accelerating. For example, over 80% of total funding raised for AI in drug discovery has been raised in the past 3 years, with 2020 investments, during the height of the COVID-19 pandemic, more than that of 2018 and 2019 combined. Partnerships and similar collaborations with the biopharma industry are also rapidly accelerating.
The next few years bring a turning point in the application of AI in drug discovery. Successful commercialization of therapies, particularly multi-target drugs, identified or designed using AI will cement this technology as a key to the future of the biopharma industry. IDTechEx's new report, "AI in Drug Discovery 2021: Players, Technologies, and Applications" provides a comprehensive overview of the application of AI, ML and DL to the drug discovery process, including insights obtained from primary interviews with key players.
For more information on this report, please visit www.IDTechEx.com/AIDisc, or for the full portfolio of Healthcare research available from IDTechEx please visit www.IDTechEx.com/Research/Healthcare.