The biological foundations of life are built upon an unimaginably vast network of interactions, where molecules, cells, systems, and organisms are constantly colliding. For centuries, scientists and doctors have relied on targeted techniques and isolated observations, developing an understanding of biology through slow, iterative discovery. This approach has applied fractional knowledge to enable life-changing solutions in only a subset of disease states.
Humanity is now entering a new era of scientific discovery, utilizing artificial intelligence to learn and reason about complex biological challenges. AI enables us to organize and perceive the complexity of biological interactions at scales far greater than the human brain is innately capable, frameworks backed by rapidly improving analytical technologies and growing experimental data.
A widely recognized example of AI in biology is AlphaFold, an AI model that predicts protein structures and interactions from statistical regularities in structural and evolutionary data. Proteins, responsible for an immense proportion of biological interactions, can now be systematically explored virtually in hours or days, circumventing conventional methodologies that require weeks, months, or even years of effort. AlphaGenome, another of Google DeepMind’s AI-driven models, allows researchers to quickly and efficiently predict how gene variants contribute to genetic landscapes that drive disease and dysfunction. These disruptive AI approaches are already being applied broadly in areas like cancer, Alzheimer’s disease, and pandemic response.
Importantly, the AI field is presently dominated by modeling approaches that are statistical in nature; these models learn correlations rather than true cause and effect. This distinction is crucial, as statistical models are limited by the context within which they can be applied. This leads to the major overarching question in the field today: how do we capture the cause and effect of every interaction within the nebulous network that we call biology? Contemporary solutions to this question are being explored through hybrid computational frameworks, models that combine our limited structured knowledge about biological systems and how they function with advanced AI.