# 🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)

## Executive summary

The video details the rapid evolution of Generative Genomics, focusing on how large language models (LLMs) trained on DNA sequences (Genome Language Models or GLMs) have advanced from merely reading DNA to actively designing functional biological sequences. Key models discussed include Hyena DNA, EVO, and the latest iteration, Omni. The core technical leap is Omni's ability to outperform specialized models across diverse tasks, such as predicting disease-causing mutations and understanding non-coding regulatory regions. This capability creates a dual mandate: advancing biological design while simultaneously developing advanced biosecurity tools to detect and counter engineered pathogens, framing the field as an AI arms race.

## Key takeaways

- The Leap from Reading to Writing DNA: Early models like Hyena DNA focused on reading DNA and predicting function using convolutions for long context (up to a million). Generative models like EVO marked the shift to generating sequences, culminating in the ability to generate functional genomes from scratch, a feat previously impossible for humans.
- Omni's Advancement via Alignment: Omni represents a significant step beyond EVO by incorporating extensive mid-training and post-training (alignment). This process makes the pre-trained base model useful for specific scientific tasks, such as identifying causal variants, allowing it to outperform specialized models across a wide range of genomic tasks.
- The Biosecurity Arms Race: The capability to design novel biological sequences necessitates a corresponding defensive capability. The defense must move beyond simple sequence matching and become function-aware, capable of detecting pathogens that look structurally different but maintain the same biological function.
- Mechanistic AI for Biology: Mechanistic approaches involve probing the model's internal representations (embeddings and activations) to distill underlying biological patterns, such as GC content or transcription factor motifs. This allows researchers to understand the 'rules' the model has learned from the raw data.

## Technical details

- Genome Language Models (GLMs): GLMs are LLMs trained on raw DNA sequences, treating the genome as a language. They aim to map function from raw DNA sequences, understanding long-range interactions and grammar rules of life.
- Model Architectures and Training: The field progressed from Hyena DNA (using convolutions for long context) to EVO (first generative model). Omni improves upon this by utilizing mid-training and post-training (alignment) to make the model useful for specific tasks, moving beyond simple next-token prediction.
- Variant and Disease Prediction: Models can predict if a mutation (variant) is likely to cause disease. Omni excels in this by analyzing non-coding and long-range regulatory regions, which are often overlooked by traditional bioinformatic tools.
- Chain of Thought (CoT) in Genomics: CoT is a reasoning paradigm applied to DNA, where the model is shown a sequence of progressively better examples (e.g., RNA aptamers with increasing fitness scores) and asked to continue the trajectory, simulating a step-by-step thought process.
- Context Scaling and Modalities: The goal is to build general biological intelligence by unifying multiple modalities (DNA, RNA, proteins, epigenomics) into single models, leveraging the fact that they all ultimately stem from DNA. The challenge remains scaling context from millions of base pairs to the full human genome (3 billion base pairs).

## Practical implications

- Accelerating scientific discovery by enabling the design of novel molecules (e.g., CRISPR-Cas systems, antimicrobial agents) and functional genomes.
- Improving human health diagnostics by analyzing Variants of Unknown Significance (VUS) and identifying disease causes in complex non-coding regions.
- Strengthening national biosecurity by developing AI-native defense systems capable of detecting engineered or novel pathogens.
- Developing new methods for rare earth mineral extraction by designing highly selective proteins.

## Topics

AI, Genomics, Bioinformatics, Machine Learning, Biosecurity, Synthetic Biology, Omni, EVO, Hyena DNA, ClinVar / TraitGym, ProteinGym, Radical Numerics

Source: https://www.youtube.com/watch?v=B7DdNj_VjcU