Raphael Townshend
Raphael Townshend is the Founder and Chief Executive Officer at Atomic AI, a biotechnology company using artificial intelligence to enable the next generation of RNA drug discovery. Prior to founding Atomic AI, Raphael completed his PhD at Stanford University, where he wrote his thesis on Geometric Learning of Biomolecular Structure and taught in Stanford’s machine learning and computational biology programs. He has been recognized in Forbes 30 Under 30, and his work has been featured on the cover of Science, recognized by a Best Paper award at NeurIPS, and published in other top venues such as Nature, Cell, and ICLR. During his PhD program, Raphael also held positions at DeepMind and Google on their artificial intelligence and software engineering teams and founded the inaugural workshop on machine learning and structural biology.
Atomic AI
AI x RNA: Foundation Models for Rational Drug Design
-
Atomic AI operates at the convergence of artificial intelligence and RNA drug discovery — two revolutionary fields with significant potential, yet not without challenges. In developing an RNA foundation model for rational drug design, Atomic pioneered novel approaches to generate, process, and model RNA data (structure, function, and interactions) from first principles. This talk will reveal their methodological journey, critical insights gained, and identify persistent gaps in the broader field that currently constrain AI's capacity to transform drug discovery.
Bigger Data vs. Better Models – Finding the Right Scale for Bio-AI
-
In AI development, there’s a trade-off between scale and sophistication. This session asks whether biological AI should follow the “bigger is better” mantra or focus on smarter, domain-specific architectures. One camp argues that a simple model fed with colossal datasets will outperform a clever model with limited data – echoing the view that more data beats complex algorithms. Others point out that biology’s complexity (from multi-step pathways to 3D genome organization) demands AI with built-in knowledge or special architectures to learn effectively from smaller, high-quality datasets. Through case studies in drug discovery and genomics, we will discuss if success lies in scaling up simple neural networks on big data or in engineering biologically informed AI models that excel with less data. What are the ROI trade-offs for researchers and investors in each approach?