At Generate:Biomedicines (“Generate”), we are building something entirely new—a platform that programs biology to generate therapeutics with both intentionality and scale. By combining machine learning, biological engineering, and experimental data, we are redefining how medicines are designed and developed. The models that drive this innovation are built by a team of scientists, machine learning experts, and data specialists, working together to push the boundaries of what’s possible.
Among them are women shaping the future of AI in drug discovery, applying computational methods to problems that traditional approaches could never solve. And yet, women remain underrepresented in AI globally, holding just 22% of roles in the field, according to the World Economic Forum’s Global Gender Gap Report 2024. On this International Day of Women and Girls in Science, we’re sharing the perspectives of three colleagues who are part of this effort. Their experiences highlight the different paths that lead into AI and the impact of bringing diverse expertise together.
Erin Yang, Computational Protein Generation Scientist, didn’t set out to become a scientist, let alone work in AI. “I don’t have a childhood story about loving to tinker or play chess (I still don’t know how to play chess). I didn’t ‘always know’ I wanted to be a scientist,” she admits. Instead, it was a college roommate’s obsession with Grey’s Anatomy that nudged her toward a science class—one where professors quickly recognized and encouraged her curiosity. “In my senior year, I took Computational Chemistry, where I first saw how biology could be modeled on a computer.”
That spark led her down a new path, but it was a breakthrough in protein structure prediction that truly shifted her focus. “It wasn’t until the 2018–2019 CASP competition [a global challenge to predict protein structures] that I saw the potential for deep learning to not only predict but also maybe even design proteins. That made me want to take on even bigger biological challenges with deep learning, so I spent the rest of grad school building expertise in both ML and biology—which led me to Generate.”
For Hoda Akl, Machine Learning Scientist, a single grad-school course opened the door to AI. “What amazed me then was the idea that if you have enough quality data, you can train a model to learn the mapping between inputs and outputs without explicitly knowing the function yourself,” she recalls. “Learning the math behind it made me think, of course it learns!—but I still have moments where I pause and think, wait, this actually works?”
Now, she applies that same sense of wonder to protein design, where the ability to map relationships between sequences and function is essential. “Applying ML to protein design is dope because the problems we tackle have real impact,” she says. “The challenge is in defining what we want the model to learn, how it can understand biological data, and how to bridge the gap between ML’s capabilities and the complexities of biology.”
Tharindi Hapuarachchi, Vice President of Platform Strategy, came to AI from a different angle: using computational models to better understand brain injury. “I have always been fascinated by how the rigid frameworks of mathematics and computer science can be applied to the complex, dynamic systems of biology,” she says. “My PhD research focused on developing computational models of metabolism to predict cerebral health in ICU patients—an experience that deepened my appreciation for the power of AI-driven insights in medicine.”
Now, she focuses on ensuring that AI-driven discoveries at Generate have real-world impact. “At Generate, I drive our platform strategy, shaping the roadmap that advances our mission of harnessing AI to revolutionize drug discovery.”
Each of them credits mentorship as a key part of their success. “I had great mentors in college and grad school who helped me at different stages,” Erin says. “The best mentors were the ones who supported me, empathized with my challenges, and genuinely wanted me to succeed.” Hoda agrees, adding that women in AI and computational sciences often hold back because they don’t see enough people who look like them. “We wait for an invitation, hold back from opportunities, and feel the need to be overqualified before applying,” she says. “This is a self-limiting belief—recognizing and overcoming it is necessary work.”
For Tharindi, sponsorship—not just mentorship—has been critical. “I’ve been fortunate to work alongside and learn from many remarkable individuals,” she says. “Yet, the most impactful support comes from sponsors—those who advocate for you when you’re not in the room, ensuring your voice, work, and potential are recognized even in your absence.”
Though their paths into AI differ, all three women share the same commitment to pushing boundaries, taking risks, and welcoming new ways of thinking. “My path wasn’t linear, and that was probably one of the best decisions I’ve made,” Erin says. “Taking risks, embracing new experiences, all while keeping an abundance mindset helped get me to where I am now.” Hoda echoes that sentiment: “You don’t need permission to pursue the path you want. The field of ML is deeply interdisciplinary, bringing together people from diverse scientific and cultural backgrounds. So put yourself out there.” Tharindi sums it up simply: “If the era of generative AI teaches us anything, let it be this—nothing is impossible.”
On this International Day of Women and Girls in Science, their stories highlight the many ways AI is shaping the future of drug discovery—whether through machine learning-driven protein design, computational modeling, or strategic platform development. Expanding participation in AI and computational sciences isn’t just about representation; it’s about bringing fresh ideas, approaches, and problem-solving strategies that push scientific progress forward. As generative biology continues to evolve, the collective expertise of those working in this space will define what’s possible—and ensure AI’s full potential is realized in medicine.
Above all, we hope more women and girls see themselves in these fields—discovering new frontiers in AI and forging breakthroughs in healthcare.