Optimizing Pharmaceutical Innovation Through AI: A Pathway to Expedited Drug Discovery and Development

The cost of developing a new drug can reach $2.5 billion and take over a decade. Companies like Bayer, Roche, and Pfizer are using artificial intelligence (AI) tools to speed up the process and reduce costs by predicting drug properties and analyzing large datasets for new compounds. AI is then used to predict the desired drug properties, absorption, bioactivity, and toxicity.^1,2

Clinical trials are using AI to handle large and complex volumes of categorized and uncategorized data in multi-center clinical trials to develop oncology, cardiovascular, and neurologic compounds and to integrate molecular and imaging data.^2-4 This technology can improve the efficiency of patient recruitment, protocol design, patient monitoring, data analysis, new target discovery, and overall chances that trials will yield valuable data. AI can also detect minute anomalies reducing false negatives in clinical trials, which is especially beneficial with drugs like targeted oncologic agents.^2-4

Clinical Trial Design

AI can be utilized to decrease the number of trial participants, enhance diversity in studies, reduce population variability, and shorten the overall duration of clinical trials. This is primarily achieved through patient recruitment and dataset analysis. Processes involve fair patient selection and access, refinement of biomarkers, and large-scale analytics to support trial-matching search engines. AI automates eligibility analysis and matching, streamlining the overall process, optimizing clinical trial design, and refining the recruitment procedure to align with trial criteria.^2,3 Algorithms have enabled predictions regarding environmental and genetic attributes, allowing for efficacy, toxicity, and survival rate predictions, contributing to more efficient recruiting, data analysis, and monitoring.

Algorithms have enabled predictions regarding environmental and genetic attributes, allowing for efficacy, toxicity, and survival rate predictions, contributing to more efficient recruiting, data analysis, and monitoring. Image Credit: © Toowongsa - stock.adobe.com

AI in Drug Discovery

AI can be used in drug design, chemical synthesis, drug screening, polypharmacology, and drug repurpose. It can accelerate drug target validation and optimize structure design.^3-5 AI has helped overcome these challenges by optimizing the time required to design study criteria specific to the target population, select subjects, enroll study participants, and control subgroups for proper data analysis. AI has enabled researchers to enhance protocol design, understand disease sequelae, and reduce the time and burden of developing a study.¹

AI can be used during clinical trials to aid in new target discovery and toxicity prediction.2 It accelerates identification of new molecular targets such as genes or proteins. AI can analyze large pharmacokinetic and pharmacodynamic datasets and develop algorithms to investigate new molecules with significant treatment potential.²

Many pharmaceutical and biotech companies increasingly use AI in the early stages of drug discovery to identify suitable target locations for novel compounds. Many researchers have also streamlined the process of identifying target locations and understanding their relationship with disease progression by consolidating and validating information from scientific publications, literature, and other credible sources.⁵

AI has been used in cancer treatment to identify how cancer cells become resistant to oncolytic agents so drug use can be adjusted, tumor neoantigens and efficacy of therapy can be identifies, and tolerance and adverse effects to cancer agents can be predicted, which can all lead to supporting effective treatment decisions.^3,6-9 Some examples of AI tools used in drug discovery include DeepConv-DTI, DeepAffinity, DeepChem, DeepTox, DeepNeuralNet QSAR, and Chemputer.^3,5

Notable examples of drugs discovered with the help of AI include:

1. DSP-1181 (Exscientia and Sumitomo Dainippon Pharma): A serotonin 5-HT1a receptor agonist entering phase 1 clinical trials in Japan.¹¹
2. A selective serotonin reuptake inhibitor (SSRI, Exscientia): Developed for treating obsessive-compulsive disorder, the drug took just 12 months to get to phase 1.¹²
3. USP1 inhibitor (Insilico Medicine): Investigators used the generative AI drug design platform Pharma.AI to develop a USP1 inhibitor for solid tumors, which received FDA approval for clinical trials.¹³
4. A2 receptor antagonist (Evotec and Exscientia): Investigators discovered an A2 receptor antagonist anticancer molecule in just 8 months, showcasing the efficiency of AI in drug discovery.¹²

Additionally, biotech companies using AI have over 150 small-molecule drugs in discovery and 15 in clinical trials, reshaping the pharmaceutical industry with AI accelerating drug development.¹⁵

Monitoring and Data Analysis

Clinical trial participants often use wearable medical technologies, and AI can analyze data from these devices allowing researchers to identify issues sooner, including missed visits, outliers, and variances.² AI can identify intricate patterns in medical data providing researchers quantitative evaluations of these data, including medical image analysis, test data, medication safety data analysis, or other data-driven assessment.³ ­­­­­­­­­­­­­­­­­­­­In addition, in the regulatory approval process, data from trials can be reviewed quicker, shortening the time in the approval process.

Future Development

Gene therapy is the future of medicine, particularly in oncology and rare disease treatment. Targeting specific genes minimizes errors and time delays in therapy development. AI has played a significant role by analyzing large genetic pools and aiding in developing precise genome editing technologies,¹⁰ leading to life-saving gene therapies for previously incurable diseases. Future expansion includes increased use with clinical, translational, and precision medicine, as well as the handling of very complex biological properties and adverse effects.

REFERENCES

1. Blanco-González A, Cabezón A, Seco-González A, et al. The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies. Pharmaceuticals (Basel). 2023;16(6):891. doi:10.3390/ph16060891

2. Askin S, Burkhalter D, Calado G, El Dakrouni S. Artificial Intelligence Applied to clinical trials: opportunities and challenges. Health Technol (Berl). 2023;13(2):203-213. doi:10.1007/s12553-023-00738-2

3. Cox B, Coustasse A, Gupta M, and Kimble C.Revolutionizing Oncology: Artificial Intelligence's Quantum Leap in Cancer Treatment. Pharmacy Times Oncology Edition.2023;5(6):37-38. Accessed May 22, 2024. https://cdn.sanity.io/files/0vv8moc6/pharmacytimes/faa730b682c692b6cc3ee889760dd0ee517ed873.pdf/PTOE-Oct2023-Issue_NoAds.pdf

4. Berger D. At Last, Artificial Intelligence is Transforming Cancer Drug Discovery and Development. AJMC. 2022;(28):7:SP488. Accessed May 22, 2024. https://www.ajmc.com/view/at-last-artificial-intelligence-is-transforming-cancer-drug-discovery-and-development

5. Deblena P, Sanap G, Shenoy S, et al. Artificial intelligence in drug discovery and development. Drug Discov Today. 2021;26(1):80-93. doi:10.1016/j.drudis.2020.10.010

6. Kolluri S, Lin J, Liu R, Zhang Y, Zhang W. Machine Learning and Artificial Intelligence in Pharmaceutical Research and Development: a Review. AAPS J. 2022;24(1):19. doi:10.1208/s12248-021-00644-3

7. Guosheng L, Wenguo F, luo H, et al. The emerging roles of artificial intelligence in cancer drug development and precision therapy. Biomedicine and Pharmacotherapy. August 2020;128:110255. Accessed May 22, 2024. https://www.sciencedirect.com/science/article/pii/S0753332220304479

8. Yang F, Darsey JA, Ghosh A, Li HY, Yang MQ, Wang S. Artificial Intelligence and Cancer Drug Development. Recent Pat Anticancer Drug Discov. 2022;17(1):2-8. doi:10.2174/1574892816666210728123758

9. Wang L, Song Y, Wang H, et al. Advances of Artificial Intelligence in Anti-Cancer Drug Design: A Review of the Past Decade. Pharmaceuticals (Basel). 2023;16(2):253. doi:10.3390/ph16020253

10. Peiffer-Smadja N, Dellière S, Rodriguez C, Birgand G, Lescure FX, Fourati S, Ruppé E. Machine learning in the clinical microbiology laboratory: has the time come for routine practice? Clin Microbiol Infect. 2020 Oct;26(10):1300-1309. doi:10.1016/j.cmi.2020.02.006

11. Willis T. AI drug discovery: assessing the first AI-designed drug candidates to go into human clinical trials. American Chemical Society. 2024. Accessed April 1, 2024. https://www.cas.org/resources/cas-insights/drug-discovery/ai-designed-drug-candidates

12. Savage N. Tapping into the drug discovery potential of AI. May 27, 2021. Accessed April 1, 2024. https://www.nature.com/articles/d43747-021-00045-7

13. Forbes Technology Council. Generative AI Drugs Are Coming. Forbes. 2024. Accessed April 1, 2024. https://www.forbes.com/sites/forbestechcouncil/2023/09/05/generative-ai-drugs-are-coming/?sh=729230925881

14. Ayers M, Jayatunga M, Goldader J, Meier C. Adopting AI in Drug Discovery. Boston Consulting Group.March 29, 2022. Accessed April 1, 2024. https://www.bcg.com/publications/2022/adopting-ai-in-pharmaceutical-discovery