Artificial intelligence (AI) is driving transformative change in the rapidly evolving field of drug discovery. Traditionally, developing new drugs has been a lengthy and costly endeavour, often requiring up to a decade and billions of dollars to complete. Now, however, AI is accelerating and enhancing the entire process, from the initial stages of drug design to the refinement of clinical trials. AI-powered algorithms enable large-scale data analysis, predict molecular interactions, and quickly and accurately identify potential drug candidates. This technological advancement not only speeds up drug development but also opens new avenues for intellectual property protection. As pharmaceutical companies and research institutions increasingly adopt AI, the role of AI-driven innovations in securing drug discovery patents has become more prominent.
The Derwent Innovations Index (DII) was used to gather data on patent applications, with a focus on the impact of Artificial Intelligence (AI) in revolutionizing drug discovery and development. A thorough search was performed using a combination of classification codes and keyword strategies to identify relevant patents. AI has had a significant impact on this field, accelerating processes that once took years by efficiently analysing large datasets and making accurate predictions. Around 3,000 patent applications were reviewed, categorized into various topics and subtopics, including global filings and key technologies. The analysis was further enhanced through graphical representations that highlighted the leading technologies based on key Cooperative Patent Classification (CPC) codes.
The Figure 1.1 represents “Year wise Trends” displays the annual count of applications and publications from 1978 to 2024, focusing on the contributions of Artificial Intelligence (AI) in areas such as chemical structure analysis, drug interaction prediction, modelling biological processes, target identification, drug screening, and Clinical Trials Optimization, among others. Both metrics remained relatively low and consistent until around 2014, after which a noticeable upward trend emerged. From 2015 onward, there was a sharp increase in both applications and publications, with a particularly significant surge starting in 2018.
The distribution displayed in “Top Assignee” figure 1.2 highlights a diverse array of business and academic institutions actively involved in securing intellectual property, with a strong presence of artificial intelligence contributions in various drug discovery and healthcare technology sectors. IBM Corp leads with the highest number of assignments, followed by Ping An Insurance, Siemens, and Sun Yat-sen University. Other notable assignees include Seoul National University, Johnson & Johnson, Roche Holding Ltd., PLA Academy of Sciences, Chinese Academy of Sciences, and Koninklijke Philips N.V.
The “Top Application Countries” pie chart in figure 1.3 shows the geographical distribution of patent applications related to artificial intelligence contributions in areas such as chemical structure analysis, drug interaction prediction, biological process modelling, target identification, drug screening, and clinical trial optimization. China (CN) leads with 41% of the applications, followed by the United States (US) at 32%, and India (IN) at 12%. This distribution underscores the substantial innovation in AI-driven drug discovery and healthcare technology in key countries, particularly China and the United States.
The bar chart in Figure 1.4 displays the leading Cooperative Patent Classification (CPC) codes along with their definitions. The data highlights a notable emphasis on AI-driven diagnostics, personalized medicine, data management, drug discovery, and simulation technologies, with significant overlap into healthcare operations and climate adaptation.
Figure 1.5 demonstrates the impact of AI on drug discovery patent applications. Precision medicine leads with over 2,500 applications, highlighting a strong focus on personalized care. Approximately 500 applications related to Target Identification & Drug Screening, Algorithms, and Platforms showcase AI’s role in computational tools and early-stage discovery. AI also has shown impact on Clinical Trials Optimization, with around 500 applications, indicates the increasing interest in enhancing clinical trial efficiency.
Figure 1.6 illustrates the classification of AI-related algorithms, including Artificial Intelligence (AI), machine learning (ML), and deep learning (DL). These algorithms are applied across various domains, such as chemical structure analysis, drug interaction prediction, biological process modelling, target identification, drug screening, and clinical trial optimization.
In conclusion, the incorporation of artificial intelligence into drug discovery is transforming the pharmaceutical industry, speeding up research, and opening new pathways for innovation. From precision medicine and effective drug screening to the optimization of clinical trials, AI-powered technologies are becoming essential. The increase in patent activity underscores the global competition to secure intellectual property in this rapidly progressing field, with leading players and regions at the forefront. As AI evolves, its transformative potential is poised to streamline drug development, improve patient outcomes, and pave the way for future advancements in healthcare.