As generative AI evolves, it moves beyond deciphering human language to mastering the intricate languages of biology and chemistry. Consider DNA as a detailed script, a 3-billion-letter sequence that guides our body’s functions and growth. Similarly, proteins, the essential components of life, have their language, including a 20 amino acid alphabet. In chemistry, the molecules even have a unique dialect, like constructing words, sentences, or paragraphs using grammar rules. Molecular grammar dictates how atoms and substructures mix to form molecules or polymers. Just as language grammar defines the structure of sentences, molecular grammar describes the structure of molecules.
As generative AI, reminiscent of large language models (LLMs), show its ability to decode the language of molecules, recent avenues for efficient drug discovery are emerging. Several pharmaceutical firms are increasingly using this technology to drive innovation in drug development. The McKinsey Global Institute (MGI) estimates generative AI could create $60 billion to $110 billion annually in economic value for the pharmaceutical industry. This potential is primarily as a consequence of its ability to boost productivity by speeding up the identification of potential recent drug compounds and accelerating their development and approval processes. This text explores how generative AI is changing the pharmaceutical industry by acting as a catalyst for rapid advancements in drug discovery. Nonetheless, to understand generative AI’s impact, it is important to know the standard drug discovery process and its inherent limitations and challenges.
Challenges of Traditional Drug Discovery
The traditional drug discovery process is a multi-stage endeavor, often time-consuming and resource-intensive. It begins with goal identification, where scientists pinpoint biological targets involved in a disease, reminiscent of proteins or genes. This step leads to focus on validation, which confirms that manipulating the goal can have therapeutic effects. Next, researchers engage in lead compound identification to seek out potential drug candidates that may interact with the goal. Once identified, these lead compounds undergo lead optimization, refining their chemical properties to boost efficacy and minimize unintended effects. Preclinical testing then assesses the security and effectiveness of those compounds in vitro (in test tubes) and in vivo (in animal models). Promising candidates are evaluated in three clinical trial phases to evaluate human safety and efficacy. Finally, successful compounds must gain regulatory approval before being marketed and prescribed.
Despite its thoroughness, the standard drug discovery process has several limitations and challenges. It’s notoriously time-consuming and dear, often taking on a decade and costing billions of dollars, with high failure rates, particularly within the clinical trial phases. The complexity of biological systems further complicates the method, making it difficult to predict how a drug will behave in humans. Furthermore, the extreme screening can only explore a limited fraction of the possible chemical compounds, leaving many potential drugs undiscovered. High attrition rates also hampered the method, where many drug candidates fail during late-stage development, resulting in wasted resources and time. Moreover, each stage of drug discovery requires significant human intervention and expertise, which might decelerate progress.
How Generative AI Changes Drug Discovery
Generative AI addresses these challenges by automating various stages of the drug discovery process. It accelerates goal identification and validation by rapidly analyzing vast amounts of biological data to more precisely discover and validate potential drug targets. Within the lead compound discovery phase, AI algorithms can predict and generate recent chemical structures prone to interact effectively with the goal. The power of generative AI to explore an unlimited variety of leads makes the chemical exploration process highly efficient. Generative AI also enhances lead optimization by simulating and predicting the results of chemical modifications on lead compounds. For example, NVIDIA collaborated with Recursion Pharmaceuticals to explore over 2.8 quadrillion mixtures of small molecules and targets in only every week. This process could have taken roughly 100,000 years to realize the identical results using the standard methods. By automating these processes, generative AI significantly reduces the time and value required to bring a brand new drug to market.
Furthermore, generative AI-driven insights make preclinical testing more accurate by identifying potential issues earlier in the method, which helps lower attrition rates. AI technologies also automate many labor-intensive tasks, enabling researchers to concentrate on higher-level strategic decisions and scaling the drug discovery process.
Case Study: Insilico Medicine’s First Generative AI Drug Discovery
A biotechnology company, Insilico Medicine, has used generative AI to develop the primary drug for idiopathic pulmonary fibrosis (IPF), a rare lung disease characterised by chronic scarring that results in irreversible lung function decline. By applying generative AI to omics and clinical datasets related to tissue fibrosis, Insilico successfully predicted tissue-specific fibrosis targets. Employing this technology, the corporate designed a small molecule inhibitor, INS018_055, which showed potential against fibrosis and inflammation.
In June 2023, Insilico administered the primary dose of INS018_055 to patients in a Phase II clinical trial. This drug’s discovery marked a historic moment because the world’s first anti-fibrotic small molecule inhibitor was discovered and designed using generative AI.
The success of INS018_055 validates the efficiency of generative AI in accelerating drug discovery and highlights its potential to tackle complex diseases.
Hallucination in Generative AI for Drug Discovery
As generative AI advances drug discovery by enabling the creation of novel molecules, it is important to concentrate on a big challenge these models could face. The generative models are vulnerable to a phenomenon referred to as hallucination. Within the context of drug discovery, hallucination refers back to the generation of molecules that appear valid on the surface but lack actual biological relevance or practical utility. This phenomenon presents several dilemmas.
One major issue is chemical instability. Generative models can produce molecules with theoretically favorable properties, but these compounds could also be chemically unstable or vulnerable to degradation. Such “hallucinated” molecules might fail during synthesis or exhibit unexpected behavior in biological systems.
Furthermore, hallucinated molecules often lack biological relevance. They may fit with chemical targets but fail to interact meaningfully with biological targets, making them ineffective as drugs. Even when a molecule appears promising, its synthesis might be prohibitively complex or costly, as hallucination doesn’t account for practical synthetic pathways.
The validation gap further complicates the difficulty. While generative models can propose quite a few candidates, rigorous experimental testing and validation are crucial to substantiate their utility. This step is important to bridge the theoretical potential and practical application gap.
Various strategies might be employed to mitigate hallucinations. Hybrid approaches combining generative AI with physics-based modeling or knowledge-driven methods can assist filter hallucinated molecules. Adversarial training, where models learn to differentiate between natural and hallucinated compounds, can even improve the standard of generated molecules. By involving chemists and biologists within the iterative design process, the effect of hallucination will also be reduced.
By addressing the challenge of hallucination, generative AI can further its promise in accelerating drug discovery, making the method more efficient and effective in developing recent, viable drugs.
The Bottom Line
Generative AI changes the pharmaceutical industry by speeding up drug discovery and reducing costs. While challenges like hallucination remain, combining AI with traditional methods and human expertise helps create more accurate and viable compounds. Insilico Medicine demonstrates that generative AI has the potential to handle complex diseases and convey recent treatments to market more efficiently. The long run of drug discovery is becoming more promising, with generative AI driving innovations.
