Can AI Identify Novel Therapeutic Targets?

By Rasit Dinc

Introduction

The traditional journey of drug discovery is a long, expensive, and often-unsuccessful one. It can take over a decade and billions of dollars to bring a new drug to market, with a failure rate of over 90% [1]. A significant portion of these failures can be attributed to the initial stages of the process: identifying and validating a therapeutic target. However, a new paradigm is emerging, one that is powered by artificial intelligence (AI) and promises to revolutionize how we discover and develop new medicines. But the question remains: can AI truly identify novel therapeutic targets?

The Power of AI in Target Identification

AI is not just a single technology but a collection of powerful tools and techniques that can be applied to various stages of drug discovery. When it comes to target identification, AI excels at analyzing vast and complex biological datasets that are beyond the scope of human analysis. This includes genomics, proteomics, and metabolomics data, collectively known as multi-omics data.

By integrating and analyzing this multi-omics data, AI algorithms can identify novel patterns and correlations that may point to new therapeutic targets. For instance, AI can uncover previously unknown oncogenic vulnerabilities or key pathways involved in a disease, providing a starting point for drug development [1].

One of the most significant breakthroughs in this area is the development of AI models like DeepMind's AlphaFold [1]. AlphaFold can predict the 3D structure of proteins with unprecedented accuracy, a task that has been a major bottleneck in drug discovery for decades. Knowing the structure of a protein is crucial for understanding its function and for designing drugs that can interact with it. This technology is accelerating the assessment of a protein's "druggability" and enabling structure-based drug design on a massive scale.

Furthermore, AI is transforming the process of virtual screening and de novo drug design. Instead of physically screening millions of compounds in a lab, AI can simulate these experiments in a computer, saving time and resources. AI can also design entirely new molecules with optimized properties for a specific target, a process known as de novo drug design [1].

A Landmark Study

A recent study published in Biomarker Research provides a comprehensive overview of how AI can be integrated into the drug discovery and development process [1]. The authors highlight the transformative potential of AI in identifying novel therapeutic targets, particularly in the field of oncology. They discuss how AI-driven approaches can overcome the limitations of traditional methods and accelerate the development of new cancer therapies.

"Through multiomics data analysis and network-based approaches, AI can help to identify novel oncogenic vulnerabilities and key therapeutic targets." [1]

This study underscores the importance of a multidisciplinary approach, where biologists, chemists, and data scientists collaborate to leverage the full potential of AI. It also emphasizes the need for high-quality data to train and validate AI models, as the old adage "garbage in, garbage out" holds true in the age of AI.

Challenges and the Road Ahead

Despite the immense promise of AI, there are still challenges to overcome. One of the main concerns is the potential for bias in AI models. If an AI model is trained on a dataset that is not representative of the broader population, it may produce biased results. Therefore, it is crucial to ensure that the data used to train AI models is diverse and inclusive.

Another challenge is the "black box" nature of some AI models. It can be difficult to understand how these models arrive at their conclusions, which can be a problem in a highly regulated field like drug discovery. However, researchers are actively working on developing more interpretable AI models to address this issue.

Finally, there are ethical and regulatory considerations that need to be addressed. As AI becomes more integrated into the drug discovery process, it is essential to have clear guidelines and regulations in place to ensure that these technologies are used responsibly and ethically.

Conclusion

So, can AI identify novel therapeutic targets? The answer is a resounding yes. AI is already making a significant impact on the field of drug discovery, and its role is only set to grow in the coming years. By harnessing the power of AI, we can accelerate the discovery of new medicines, reduce the cost of drug development, and ultimately bring new hope to patients around the world. The road ahead may have its challenges, but the transformative potential of AI in identifying novel therapeutic targets is undeniable.

References

[1] Ocana, A., Pandiella, A., Privat, C., Bravo, I., Luengo-Oroz, M., Amir, E., & Gyorffy, B. (2025). Integrating artificial intelligence in drug discovery and early drug development: a transformative approach. Biomarker Research, 13(1), 45. https://doi.org/10.1186/s40364-025-00758-2