Foundational biological datasets, like the first Human Cell Atlas, take immense time and capital to create (10 years). However, this initial effort creates tooling and knowledge that allows subsequent, larger-scale projects to be completed exponentially faster and at a fraction of the cost.

The primary bottleneck for creating powerful foundation models in biology is the lack of clean, large-scale experimental data—orders of magnitude less than what's available for LLMs. This creates a major opportunity for "data foundries" that use robotic labs to generate high-quality biological data at scale.

AI is moving beyond simply identifying patterns in existing research papers. It is now able to extrapolate fundamental biological principles, enabling it to understand complex systems from the ground up, like the relationship between atoms, molecules, and proteins.

Building the first large-scale biological datasets, like the Human Cell Atlas, is a decade-long, expensive slog. However, this foundational work creates tools and knowledge that enable subsequent, larger-scale projects to be completed exponentially faster and cheaper, proving a non-linear path to discovery.

Demis Hassabis argues that machine learning is the ideal framework for understanding biological systems. Unlike physics, which is elegantly described by mathematics, biology's messy, data-rich nature with many weak correlations is perfectly suited for ML to model and decipher.

The next frontier in preclinical research involves feeding multi-omics and spatial data from complex 3D cell models into AI algorithms. This synergy will enable a crucial shift from merely observing biological phenomena to accurately predicting therapeutic outcomes and patient responses.

The massive Cell-by-Gene atlas began as a simple annotation tool to solve a workflow bottleneck for labs. Its utility drove widespread adoption, which unintentionally created a community-driven, standardized data format that became a foundational resource for the field.

Biohub applies mechanistic interpretability to its protein language models. By analyzing the model's internal representations—learned from both known and unknown biology—researchers can uncover emergent biological principles. This turns the model from a black box predictor into an engine for scientific discovery itself.

Traditional science failed to create equations for complex biological systems because biology is too "bespoke." AI succeeds by discerning patterns from vast datasets, effectively serving as the "language" for modeling biology, much like mathematics is the language of physics.