The bottleneck for AI in drug discovery is not the algorithm but the lack of high-quality, large-scale biological data. New platforms are needed to generate this necessary "substrate" for AI models to learn from, challenging the narrative that better models alone are the solution.

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 models trained on descriptive data (e.g., RNA-seq) can classify cell states but fail to predict how to transition a diseased cell to a healthy one. True progress requires generating massive "causal" datasets that show the effects of specific genetic perturbations.

Despite the buzz, a clinical development expert cautions that AI's impact in drug development is limited. The primary bottleneck isn't the algorithms but the lack of sufficient, high-quality human biological data that can be translated into reliable predictions, as animal models often fail to provide it.

The primary obstacle to creating sophisticated AI models of cells isn't the AI itself, but the data. Existing datasets often perturb only one cellular variable at a time, failing to capture the complex interactions that arise from simultaneous changes. New platforms are needed to generate this multi-dimensional data.

While AI excels where large, clean datasets exist (like protein folding), it struggles with modeling slow, progressive diseases like Alzheimer's or obesity. These are organ-level phenomena, and the necessary data doesn't exist yet. In vivo platforms are critical for generating this required foundational data.

The progress of AI in predicting cancer treatment is stalled not by algorithms, but by the data used to train them. Relying solely on static genetic data is insufficient. The critical missing piece is functional, contextual data showing how patient cells actually respond to drugs.

Current AI for protein engineering relies on small public datasets like the PDB (~10,000 structures), causing models to "hallucinate" or default to known examples. This data bottleneck, orders of magnitude smaller than data used for LLMs, hinders the development of novel therapeutics.

The bottleneck for AI in drug development isn't the sophistication of the models but the absence of large-scale, high-quality biological data sets. Without comprehensive data on how drugs interact within complex human systems, even the best AI models cannot make accurate predictions.