Hey, hi, everyone. My name is Amit Taneja. Thank you so much for joining me in the conference. I'll be going through accelerating pharmaceutical innovation. Leveraging AI and platform engineering to revolutionize drug development. Some of the table contents is, I'll be going through traditional drug discovery challenges, how AI can play a transformative role in drug discovery, the different AI methodologies in drug discovery process. I'll also be going through a couple of case studies. What are the different benefits of AI in drug discovery, the different challenges and the considerations and how the future outlook for AI in drug discovery looks like, and also the conclusion. let's talk about the traditional drug discovery challenges. one of the major thing is high cost. The average cost to develop a new drug exceeds over 2. 6 billion. The long timelines on average, it takes over 12 years to develop and approve a new drug. Okay. Inefficiency. Traditional methods rely on experimental screening, which is time consuming and costly. Now, using platform engineering, we can a lot of, we can do the automation. We can automate all these workflows. So by automating workflows using platform engineering practices, we can streamline the drug discovery processes, reduce any manual intervention, improve operational efficiency. Automated pipelines ensure data moves seamlessly from one phase to another, saving the time and resources. AI is a transformative role in drug discovery. AI provides faster data analysis, identifying promising drug candidates with higher efficiency. AI powered solutions predict molecular interactions, reducing drug discovery time. AI improves accuracy with models predicting success rates over 80%. Now, we can scale. It's a lot scalable, cloud infrastructure in platform engineering. Platform engineering enables scalable cloud infrastructure that supports AI models in processing large data sets, optimizing the computer sources, and reducing time for molecular analysis. Scalable systems ensure that AI processes grow dynamically with project needs. Eliminating any bottlenecks. Now, different AI methodologies in drug discovery. One of them is deep learning. models like CNNs and RNNs analyze chemical bioactivity data. Virtual screening. AI evaluates large chemical libraries, identifying high potential compounds. Molecular docking. AI simulates molecular interactions, predicting how the drugs can actually will bind to the targets. Generator models. AI creates novel molecules for specific therapeutic purposes. CICD in platform engineering. So you, we can use, CICD principles. Platform engineering will automate the deployment of AI models. Ensuring that every iteration or improvement is quickly tested and integrated. This will speed up the time between model training, testing, deployment, reducing any downtime, and manual intervention. Case study. So AI driven molecular discovery. Essentia and Sumitomo Genepon Pharma, AI created a molecule for immuno oncology, reducing the development time to just eight months. Enter clinical trials faster than traditional timelines. Typically, 4 to 5 years highlights AI's ability to expedite the discovery process, faster time to market with platform engineering. Platform engineering practices play a key role in speeding up the time to market for AI design model by automatic key processes, handling large data sets and integrating various research tools. The entire drug discovery timeline was significantly shortened. Let's talk about the case study number two. AI discovered antibiotic. Helician discovery. AI screened over 6, 000 compounds and identified helician and antibiotic effective against drug desistant bacteria. Helician expedited a novel mechanism of action targeting ATP synthase. Demonstrated AI's ability to find innovative therapeutic solutions. Data oriented architecture in the platform engineering. In the case of helician, Platform engineering provided a data oriented architecture that enabled the AI models to handle, process, and analyze vast data sets. By centralizing the data pipelines, the AI was able to screen compounds more efficiently and accurately. The benefits of AI in drug discovery reduce time, AI dramatically shortens the drug development pipelines, lower costs, fewer trials and error reduce the development expense, higher accuracy, AI predictions significantly increase the chances of success for compounds. Optimizing resources with platform engineering. Platform engineering ensures that resources both computational and financial are optimized. It allows for the automatic scaling of compute power. And storage based on AI model demands, ensuring efficient use of resources without unnecessary cost increases, challenges and considerations, data quality, AI relies on large data sets that must be accurate and comprehensive. Model interoperability, complex AI models can be difficult to understand and interpret. Experimental validation, AI predictions must still undergo rigorous experimental validation. Observer, observability and monitoring and platform engineering. Platform engineering emphasizes observability and monitoring tools that help track data flow and model performance. These tools make it easier to detect issues in AI models, ensuring higher accuracy and quality of data. Used in drug discovery. How the future outlook of AI and drug discovery looks like. Next generation AI tools. Advanced models will further accelerate the drug discovery process. Collaboration. Partnerships between AI experts, chemists, and biologists will drive innovation. Expansion. AI will help develop personalized medicine. And targeted therapies, collaboration platforms with platform engineering. In the future, platform engineering will facilitate better collaboration between interdisciplinary teams by creating integrated environments where data scientists, biologists, chemists can work together on drug discovery. These platforms will streamline communication and data sharing. Conclusion. Artificial intelligence has the potential to revolutionize the pharmaceutical industry by accelerating drug discovery processes, improving accuracy, and significantly reducing cost. As AI driven approaches continue to evolve, they offer new possibilities for identifying potential threats. promising drug candidates, predicting molecular interactions and optimizing drug formulations. However, the success of AI in drug discovery is heavily dependent on robust platform engineering. Thank you so much everyone, for joining the conference and listening to this. Thank you again.