Powerful AI models for biology exist, but the industry lacks a breakthrough user interface—a "ChatGPT for science"—that makes them accessible, trustworthy, and integrated into wet lab scientists' workflows. This adoption and translation problem is the biggest hurdle, not the raw capability of the AI models themselves.

Similar to how an LLM uses a 'chain of thought' to reason, Genesis's model 'thinks' by iteratively refining an in-memory representation of a crystal structure. This process is guided by physics-based principles, significantly improving the final prediction's accuracy.

Training a language model to predict the next amino acid in a sequence forces it to learn the protein's 3D structure. To make accurate predictions, the model must understand an amino acid's physical microenvironment, effectively deriving 3D spatial relationships from 1D sequence data alone. This demonstrates emergent capabilities of LLMs in biology.

Unlike text-based LLMs where simply increasing parameter count works, Verge Labs found the biggest AI performance gains in biology come from scaling data modalities—adding new types of data like proteomics and imaging. Fusing different data sources is more critical than just making the model bigger.

By providing a genomic model with a sequence of examples showing progressively higher fitness scores (e.g., better RNA aptamers), the model learns the optimization trajectory. It can then continue this "thought process" to generate novel, even higher-performing sequences.

Early efforts like the Human Cell Atlas were criticized as mere data collection ("stamp collecting"). However, the rise of LLMs provided the key to unlock this data's value, transforming vast, unstructured biological datasets into systems that generate scientific insights and move biology from discovery to engineering.

A major misconception is that general-purpose Large Language Models (LLMs) can be readily applied to complex biological problems. Biological data, like RNA sequencing, constitutes a unique language that requires custom-built foundation models, not simply fine-tuning of existing LLMs.

Since DNA is the source code for RNA and proteins, a foundation model pre-trained on DNA can learn underlying biological principles that transfer across modalities. This allows a single model to tackle tasks that previously required specialized protein or RNA models.

Most diseases are linked to variants in non-coding DNA, which makes up 98% of the genome and is notoriously hard to analyze. New long-context AI models excel at detecting these long-range interactions, significantly outperforming older methods.