Score, embed, and generate DNA sequences with a genomic foundation model.
npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill evo2-pku-yuangroup
Please help me install this Agent Skill. Skill: evo2 Source: https://github.com/PKU-YuanGroup/OpenAI4S/tree/main/skills/evo2 Command: npx skills add https://github.com/PKU-YuanGroup/OpenAI4S --skill evo2-pku-yuangroup
Evo 2 helps solve the challenge of genomic sequence analysis, enabling tasks like scoring DNA sequences, embedding genomic windows, generating DNA sequences, and scoring regulatory or coding regions across species.
Use the evo2 skill to score a DNA sequence: 'evo2 skill run evo2 --sequence "ATCG" * 50'
High-intent search queries and answers about installing and using this skill.
To score DNA sequences for variant effect analysis, you can calculate sequence likelihoods using the evo2 skill. It processes genomic inputs to provide likelihood scores, requiring a GPU for the necessary computational power.
Yes, you can generate DNA sequences using a specific prefix. The genomic sequence generation capability creates subsequent DNA bases based on your provided starting sequence to support genetic research.
Yes, genomic sequence embedding works across different species. The model applies species-wide analysis to embed genomic windows, enabling you to utilize the resulting sequences for downstream classification tasks.
Yes, you need a GPU for genomic window embedding tasks. Access to a GPU is required to provide the processing power necessary for running the long-context genomic foundation model.
The best way to score regulatory and coding regions across species is to use a long-context genomic foundation model. This approach analyzes the specific regions to help you understand genetic differences.
You should use a foundation model for DNA sequence analysis because it enables long-context processing across species. Unlike traditional bioinformatics tools, it handles scoring, embedding, and generation within a single model framework.
ovachieverProvides Python-based bioinformatics tools for analyzing DNA, RNA, and protein sequences.
robotlearning123Retrieve and interpret genetic variant data from the NCBI ClinVar database.
ovachieverRetrieve nucleotide sequences and associated data from ENA via REST APIs.
uv-xiaoImplement the Mamba state-space model architecture with O(n) complexity.
