# arcinstitute/evo2

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/arcinstitute-evo2).**

3,951 stars · 505 forks · Jupyter Notebook · Apache-2.0

## Links

- GitHub: https://github.com/ArcInstitute/evo2
- awesome-repositories: https://awesome-repositories.com/repository/arcinstitute-evo2.md

## Description

evo2 is a genomic large language model and foundation model designed to predict, generate, and analyze genetic information across different species. It functions as a nucleotide sequence modeler and a DNA sequence generator, using transformer-based sequence modeling to process genomic data.

The system provides capabilities for synthetic DNA generation, creating new genetic sequences based on biological prompts or species-specific tags. It also performs nucleotide likelihood prediction to score genomic variants and analyze biological properties within DNA sequences.

The model supports genomic sequence analysis through the extraction of high-dimensional representations from intermediate layers. These embeddings enable specialized classification and downstream analysis of genetic data.

## Tags

### Artificial Intelligence & ML

- [Genomic Sequence Modeling](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-to-sequence-models/genomic-sequence-modeling.md) — Uses transformer-based self-attention mechanisms to predict nucleotide likelihoods and capture long-range dependencies in genomic data.
- [Synthetic DNA Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/dataset-generation/synthetic-data-generators/synthetic-dna-generation.md) — Creates new genetic sequences based on specific prompts or species tags to fill gaps in genomic data.
- [Genomic Foundation Models](https://awesome-repositories.com/f/artificial-intelligence-ml/genomic-foundation-models.md) — Serves as a pre-trained biological model providing high-dimensional sequence embeddings for downstream genomic analysis.
- [Genomic LLMs](https://awesome-repositories.com/f/artificial-intelligence-ml/genomic-llms.md) — Implements a large language model trained on DNA sequences to predict, generate, and analyze genetic information.
- [Genomic Cross-Domain Pretraining](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing/language-model-pretraining/domain-specific-pretraining/genomic-cross-domain-pretraining.md) — Learns general biological patterns from diverse species data to allow a single model to generalize across all domains of life.
- [Genomic Sequences](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation/autoregressive-text-generation/genomic-sequences.md) — Produces new DNA sequences by iteratively predicting the next nucleotide based on biological tokens and species tags.
- [DNA Sequence Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation/dna-sequence-generators.md) — Provides a generative model that produces synthetic genetic sequences based on biological prompts or species tags.
- [Genomic](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-generation/genomic.md) — Produces new genetic sequences based on prompts or species tags to complete missing sequence information. ([source](https://cdn.jsdelivr.net/gh/arcinstitute/evo2@main/README.md))
- [Layer Extractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-intermediate-representations/layer-extractions.md) — Captures high-dimensional representations from intermediate model layers for specialized downstream biological analysis.
- [Genomic Sequence Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/protein-sequence-embeddings/genomic-sequence-embeddings.md) — Captures high-dimensional representations from intermediate model layers for specialized analysis of sequence data. ([source](https://cdn.jsdelivr.net/gh/arcinstitute/evo2@main/README.md))

### Part of an Awesome List

- [Genomic Data Analysis](https://awesome-repositories.com/f/awesome-lists/data/genomic-data-analysis.md) — Extracts high-dimensional embeddings from genetic data to perform specialized biological classification and sequence analysis.

### Data & Databases

- [Genomic Sequence Interpreters](https://awesome-repositories.com/f/data-databases/data-analysis-visualization/analytical-platforms-engines/sequence-analysis/genomic-sequence-interpreters.md) — Predicts nucleotide likelihoods across a sequence to score genomic variants or analyze biological properties. ([source](https://cdn.jsdelivr.net/gh/arcinstitute/evo2@main/README.md))
- [Genomic Tokenization](https://awesome-repositories.com/f/data-databases/data-analysis-visualization/analytical-platforms-engines/sequence-analysis/genomic-sequence-interpreters/genomic-tokenization.md) — Converts raw nucleotide sequences into discrete tokens that the model processes as a structured vocabulary.

### Scientific & Mathematical Computing

- [Genome Modeling and Design](https://awesome-repositories.com/f/scientific-mathematical-computing/genome-modeling-and-design.md) — Uses machine learning to predict and create DNA sequences for research and biological engineering across species.

### User Interface & Experience

- [Nucleotide Likelihood Prediction](https://awesome-repositories.com/f/user-interface-experience/visitor-identification/confidence-scoring/sequence-likelihood-scores/nucleotide-likelihood-prediction.md) — Predicts the probability of specific nucleotides in a sequence to score genomic variants and biological properties.