Miriam Martínez Navarro - 20 September 2024
AI’s Role in Transforming Drug Discovery: A New Frontier
The Impact of AI on Pipelines, Productivity, and Clinical Success
Growth of AI-Driven Drug Discovery Pipelines
Artificial intelligence (AI) is poised to revolutionize drug discovery. A recent analysis by Boston Consulting Group (BCG) revealed in 2022 that biotech companies leveraging AI have 158 small-molecule drugs in preclinical discovery, with approximately 15 already in clinical trials [1]. The global AI in drug discovery market size was estimated at USD 1.9 billion in 2024, and is expected to expand at a CAGR of 29.7% from 2024 to 2030, to reach USD 9.1 billion by 2030 [2].
The combined pipeline of these AI-focused companies represents around 50% of the preclinical output of "big pharma". While it's still uncertain how many AI-discovered drugs will successfully advance through clinical trials, this growth indicates a promising future for AI-driven innovation [1].
Pipeline Composition and Target Classes
AI-native companies often focus on well-established target classes, aiming to reduce risk by leveraging validated biological pathways or to demonstrate their AI's effectiveness. In contrast, the top 20 pharmaceutical companies dedicate about 50% of their pipelines to emerging targets, signaling their higher risk tolerance [1].
Based on application, the drug optimization and repurposing segment accounted for the highest market share of 53.7% in 2023. Preclinical testing segment is another application of AI in drug development that is growing at the fastest pace [2].
In terms of therapeutic focus, most AI-driven drug discovery efforts concentrate on oncology and central nervous system (CNS) disorders, reflecting the significant unmet needs in these areas and the availability of well-characterized targets [1]. Oncology segment held the largest revenue share of 22.4% in 2023. The infectious disease segment is expected to grow at the fastest CAGR of 32.0% from 2024 to 2030 [2].
AI's value in Drug Discovery
Broader Molecular Diversity
AI is reshaping drug discovery by unlocking novel biological mechanisms and expanding molecular diversity. These newly explored mode of actions lead to the discovery of molecules with improved safety and efficacy profiles [1].
AI can also explore chemical spaces adjacent to classically discovered molecules, identifying new hits for major targets. By generating synthetic data based on real-world datasets, AI compensates for data scarcity by covering a wider range of scenarios than real-world data. This way, it broadens the scope of drug discovery [1].
Enhanced Target Identification and Molecular Insights
AI can deliver value to early drug discovery teams in many different ways. At a biological level, AI can help researchers to identify the right biological targets by facilitating the different stages of the process (see Table 1 for specific discovery contexts) [3].
| AI analysis of | Research purpose |
|---|
| Omics data | Find new genome-wide targets |
| Academic and experimental data (network building) | Reveal new disease pathways and potential mechanisms of action |
| Phenotypic data (images) | Identify new targets and leads |
| Protein structure prediction | Understand protein interactions, function and drugability |
| Protein motion models | Identify new binding sites, protein/drug and polypharmacological interactions |
Table 1: BiologyIn terms of chemistry, AI can be useful for finding and designing molecules for preclinical candidates, that is, in hit confirmation, hit-to-lead and lead optimization processes. Each application brings additional insights to drug discovery teams (check Table 2 for different use cases) [3].
| AI use | Research purpose |
|---|
| Exploring vast array of chemical space and molecular dynamics | Screen for molecule hits |
| Analysis of molecule structure and experimental data | Predict molecule structure/activity relationships |
| Analysis of prospective protein target | Generate lead-like molecules |
| Mining of literature and internal data | Predict optimal synthetic routes |
| Prediction of pharmacokinetic and pharmacodynamics properties | Preselect drug leads |
Preemptively flag leads and candidates
| Predict off-target effects
|
Table 2: ChemistryImproved Clinical Success Rates
One of the most exciting prospects of AI in drug discovery is its potential to increase clinical success rates. Recent analyses of the clinical pipelines of AI-native Biotech companies show that AI-discovered drugs have an 80-90% success rate in Phase I clinical trials, significantly higher than historic industry averages [4].
In Phase II, the success rate remains around 40%, similar to historical data. Although the sample size is still small, these early results suggest that AI could lead to more efficient drug development [4].
Greater Productivity
One of the most tangible benefits of AI in drug discovery is its potential to boost productivity. AI has demonstrated its ability to accelerate timelines by streamlining target identification, hit optimization, and molecule design processes. For instance, AI enables rapid target validation and reduces the number of iterations needed during lead optimization [1].
Although it's challenging to quantify the cost reductions from AI-driven drug discovery, several companies have reported lower R&D expenses, suggesting that broad implementation of AI could lead to significant savings in the future [1].
Conclusion
AI is ushering in a new era in drug discovery, with the potential to revolutionize how we identify, validate, and develop new drugs. While still early, AI-driven approaches are already showing promising results in preclinical and early clinical stages. As AI continues to evolve, we can expect more efficient drug discovery processes, improved clinical outcomes, and potentially transformative new treatments for patients.
REFERENCES
[1] Jayatunga MKP, Xie W, Ruder L, Schulze U, Meier C. AI in small-molecule drug discovery: a coming wave? Nat Rev Drug Discov. 2022 Mar;21(3):175-176. doi: 10.1038/d41573-022-00025-1.
[2] Artificial Intelligence In Drug Discovery Market Size, Share & Trends Analysis Report By Therapeutic Space (Oncology, Neurodegenerative Diseases), By Application, By Region, And Segment Forecasts, 2024 - 2030.
[3] Ayers M, Jayatunga MKP, Goldader J, Meier C. Adopting AI in drug discovery Boston Consulting Group (BCG)
[4] Jayatunga MKP, Ayers M, Bruens L, Jayanth D, Meier C. How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons. Drug Discovery Today. 2024 Jun; 29(6). doi.org/10.1016/j.drudis.2024.104009.
By Miriam Martínez Navarro
Miriam is a Human Biologist expert in neuropharmacology. After a master’s degree in Pharmaceutical and Biotech Industry, she obtained her PhD in Biomedicine from Pompeu Fabra University (Barcelona). During her doctorate, she focused her research on the behavioral analysis of animal models for neurophenotypical characterization. Since then, she has been working in the healthcare marketing and publicity sector, where she has contributed to developing marketing campaigns for several pharmaceutical brands. In 2021, she joined ZeClinics with a branding and marketing strategy focus.