As pharmaceutical R&D pivots toward faster, data-driven outcomes, artificial intelligence is rewriting the rules of drug discovery and repurposing. Narayanan Venkatasubramanian, CEO and Co-Founder, Peptris, shares how AI is accelerating target identification, transforming rare disease pipelines, and enabling strategic collaborations. From optimizing clinical timelines to expanding global market access, he unpacks how next-gen platforms are reshaping drug development while preparing for evolving regulatory frameworks—pushing Indian innovation toward a globally competitive edge.
How is artificial intelligence transforming traditional drug discovery processes, and what efficiencies does it introduce?
Artificial intelligence (AI) is revolutionizing traditional drug discovery by automating and optimizing several stages of the process, significantly reducing time and costs. AI enables:
· Target Identification: AI analyzes large datasets, including genomics and proteomics, to identify novel drug targets with higher precision than traditional methods
· Molecular Simulations: High-fidelity simulations reduce the need for extensive physical compound testing, saving time and resources
Ultra Large Library Screening: Screen billions of virtual compounds to pick a small set of potential molecules to be tested in the lab – reducing time and cost significantly
· De Novo Drug Design: AI generates novel molecular structures with optimized properties ensuring a novel and broader IP space
· Predictive Analytics: AI predicts drug properties like toxicity and efficacy, streamlining lead optimization
These advancements cut development timelines by up to 50% and reduce costs by automating labor-intensive tasks, enabling faster identification of viable candidates
What are the current trends and challenges in drug repurposing, and how do they impact the speed and cost of bringing therapies to market?
Trends:
· The cost and time to develop drugs make it unviable for large pharma companies to develop novel drugs of rare diseases where the patient numbers are small compared to some of the diseases like diabetes. Repurposing opportunities are the quickest and best option that can expedite regulatory approval and bring a therapy to patients quickly. Repurposing reduces development costs (averaging $300 million vs. $2.5 billion for new drugs) according to industry reports. We expect this to reduce further with AI.
· Further, AI-driven in silico screening identifies new targets and novel indications for molecules that have cleared Phase I and deemed safe. This approach helps both the innovator and the patient in equal measure as it broadens the IP space for the innovator and reaches the patient faster too.
How do partnerships, such as the one between Peptris Technologies and Revio Therapeutics, influence innovation and commercialization in the pharmaceutical sector?
Strategic partnerships like Peptris-Revio Therapeutics drive innovation by combining complementary strengths. For example:
· Peptris leverages its AI expertise for drug discovery, while Revio focuses on clinical development and commercialisation of PEPR124 (RT001) for Duchenne Muscular Dystrophy
· Partnerships pool resources, share risks, and accelerate market access by enabling companies to focus on their core competencies.
Such collaborations democratize access to advanced technologies and expand global footprints, as seen in Peptris retaining BRICS-market rights while Revio handles other regions.
What regulatory hurdles and considerations arise when developing and approving AI-discovered or repurposed drugs?
Peptris leverages AI to discover novel associations between drugs and targets and validates them in wet labs. There are no regulatory hurdles in the way as it follows the traditional development path once the wet lab validation is completed. Repurposed drugs often require full Phase II/III trials to validate efficacy in new indications. There may also be a need for additional safety data if the route of administration is different compared to the original indication and also if the patient population for the new indication is different e.g. repurposing a drug not used in adult populations for a paediatric disease.
The other new trend is in using AI as a part of the regulatory model and bypassing some of the mandatory animal studies with software predictions and simulations. This is still in the early stages and the regulators are warming up to this.
Key regulatory challenges include:
· Transparency in AI Models: Regulators demand explainable AI systems to ensure algorithmic decisions are reproducible and unbiased.
· Data Privacy: Compliance with data protection laws like HIPAA is critical when using sensitive patient data for AI-driven research
· Regulatory frameworks are evolving to address these issues. For instance, the FDA’s Software Pre-Certification Program aims to streamline approval processes for AI-enabled innovations.
How do AI-driven discoveries and repurposed drugs address unmet needs in rare diseases, and what are the commercial implications?
AI accelerates rare disease drug development by identifying novel targets or repurposing clinically safe molecules for niche indications. This is critical as 95% of rare diseases lack approved treatments.
· Faster Development: Repurposing reduces timelines by bypassing early-stage research; AI further enhances efficiency through predictive modeling.
· Commercial Viability: In developed countries, Orphan drug designations provide incentives like market exclusivity and tax credits, offsetting smaller patient populations
Priority review vouchers: These help fast-track approvals
These approaches not only meet urgent medical needs but also create sustainable business models through focused partnerships with rare disease organisations. We need an equivalent framework in India to help innovators work on some of the rare and unmet conditions specific to our populations.
What is the potential long-term impact of AI and drug repurposing on the global pharmaceutical industry, particularly concerning R&D efficiency and patient outcomes?
AI and drug repurposing are poised to transform the pharmaceutical landscape by:
· Improving R&D Efficiency: Success rates in Phase I trials for AI-discovered drugs are set to improve to 80–90%, compared to 40–65% historically, reducing attrition rates significantly
· Lowering Costs: Automation cuts R&D costs by hundreds of millions per asset while enabling faster delivery of therapies to market.
· Enhancing Patient Outcomes: Personalized medicine becomes more accessible as AI tailors treatments based on individual profiles, improving efficacy and reducing side effects.
In the long term, these innovations will democratise access to advanced therapies globally while reshaping business models toward more agile, cost-effective operations.
