Use of AI for Drug Discovery and Development

#### GS Paper 3

Syllabus: Application of Technology

Source: TH

Context: AI is transforming drug development by accelerating target discovery and predicting drug-target interactions.

Examples of New Drugs Formulated through AI:

• DSP-1181:For obsessive-compulsive disorder.

• Halicin:For antibiotic resistance

• BMS-986195: A potential treatment for fibrosis.

Role of AI in Drug Development and Discovery:

Aspect | Role

Enhanced Target Discovery | AI, particularly through advanced tools like AlphaFold and RoseTTAFold, revolutionizes target discovery by accurately predicting the three-dimensional structures of proteins, DNA, and RNA. It allows for a more precise understanding of how drugs can interact with these biological targets.

Improved Efficiency | AI models drastically reduce the time required for drug-target interaction studies and increase the accuracy of these predictions E.g., AlphaFold 3 predicted drug-target interactions with a 76% accuracy rate, a substantial improvement over previous methods.

Cost Reduction | By leveraging deep neural networks and generative diffusion-based architectures, AI minimizes the need for expensive and time-consuming laboratory experiments, thus reducing drug development costs.

Versatility in Predictions | Predict interactions involving any combination of protein, DNA, RNA, small molecules, and ions, broadening the scope of drug development research.

Improved Drug Design | AI algorithms predict how a molecule will interact with a target protein, allowing for more targeted drug design with better efficacy and fewer side effects.

Limitations of AI in Drug Development

• Limited Prediction Accuracy: AI tools achieve up to 80% accuracy, but drop significantly for complex interactions like protein-RNA.

• Restricted Application: AI enhances early phases like target discovery but doesn’t affect pre-clinical and clinical trials.

• Model Hallucinations: Diffusion-based AI models can generate incorrect predictions due to inadequate training data.

• Restricted Tool Access: Advanced tools like AlphaFold 3 are not publicly available, limiting verification and broader use.

• Lack of Computing Infrastructure: India lacks extensive computing resources like high-speed GPUs, hindering AI-driven drug development.

• Shortage of Skilled Professionals: There’s a significant gap in skilled AI scientists compared to countries like the U.S. and China, limiting innovation within India.

• Data Quality and Quantity: The diverse and often scarce nature of drug discovery data poses challenges for accurate analysis and modelling by AI systems.

• Cost and Technical Expertise: Implementing AI in drug discovery requires substantial investments in infrastructure and skilled personnel

• Lack of Standardization: The absence of standardized data formats, collection methods, and analysis techniques in drug discovery hinders the effective comparison of studies and datasets

What should be done:

• Data Privacy and Regulatory Compliance: Strict adherence to data protection regulations like HIPAA and GDPR is essential in AI-driven drug discovery to address ethical and legal concerns regarding patient data privacy.

• Investment in R&D: India can boost AI-driven research projects in pharmaceuticals by increasing funding and support. Public-private partnerships can expedite innovation and commercialization.

• Regulatory Framework: Establishing supportive regulations balancing innovation and safety is crucial. Investment in infrastructure like high-performance computing facilities is necessary for AI-driven research.

• Public-Private Partnerships: Collaboration among academia, government, and pharmaceutical firms accelerates AI adoption in the industry.

Case Study:

iOncology AI Project: To develop an AI-powered platform (iOncology AI) to help oncologists select the most effective treatment for cancer patients based on their genetic makeup.

The government programme for the promotion of AI in Healthcare:

• Ayushman Bharat Digital India Mission

• IndiGen Programme (for genome sequencing of Indians)

• Human Genome Project

• Health Stack

• ICMR guideline of use of AI in Healthcare

• AIRAWAT (AI Research, Analytics and Knowledge Assimilation platform): India’s first AI-specific cloud computing infrastructure

Conclusion:

The AI market has witnessed significant growth, from $200 million in 2015 to $700 million in 2018, with projections indicating a surge to $5 billion by 2024. The integration of AI in drug discovery has the potential to revolutionize the pharmaceutical industry and healthcare sector in India and further support India’s position as the ‘Pharmacy of the World’.

Insta Links:

Use of Artificial Intelligence in Medicine

Prelims Links

With reference to agriculture in India, how can the technique of ‘genome sequencing’, often seen in the news, be used in the immediate future?

• Genome sequencing can be used to identify genetic markers for disease resistance and drought tolerance in various crop plants.

• This technique helps in reducing the time required to develop new varieties of crop plants.

• It can be used to decipher the host-pathogen relationships in crops

Select the correct answer using the code given below:

(a) 1 only

(b) 2 and 3 only

(d) 1, 2 and 3

Answer: D