Try Boost
Accelerate your research with up to 20 hours of computing
Contact Us
Nguyen, E. et.al |

Evo-CRISPR: CRISPR System Generation

1
Protein Design
    More
Step 1: Upload your data

FASTA File Upload (Only for score task)

Drag your file(s) or upload
  • Your file can be in the following formats:fasta
    • Please provide a FASTA file with sequences in standard FASTA format. For the generate pipeline, provide a prompt sequence. For the score pipeline, provide sequences to be scored. Each sequence should start with a '>' followed by a sequence identifier on one line, and the amino acid sequence on subsequent lines. IMPORTANT NOTE: Please use if you use the scoring task.
or
Don’t have a file?
Use our demo data to run
Use Demo Data
View example data
Step 2: Set Parameters
generate
1
3
100
1
100
8000
0.100
1.000
1.000
3
4
25
1.000
1.000
Step 3: Complete run profile

Short description:

Evo CRISPR model is a language model specifically designed for generating novel CRISPR-Cas DNA sequences. Evo-CRISPR is a fine-tuned version of the DNA language model Evo, trained on 48,000 CRISPR-Cas ortholog sequences mined from multiple public databases.
Protein-nucleic acid co-design capabilities make this app uniquely sutied for CRISPR system design.

Example use case:

Designing Cas9-like, Cas12-like, Cas13a-like CRISPR-Cas gene editors de novo for targeted therapeutic interventions.

Technology:

Transformer-based deep learning model trained on trillions of nucleotides from diverse genomes, capable of modeling long-range genomic dependencies.

Citation:
Nguyen, E., Poli, M., Durrant, M.G., Thomas, A.W., Kang, B., Sullivan, J., Ng, M.Y., Lewis, A., Patel, A., Lou, A., Ermon, S., Baccus, S.A., Hernandez-Boussard, T., Ré, C., Hsu, P.D., & Hie, B.L. (2024). Sequence modeling and design from molecular to genome scale with Evo. bioRxiv.
Released:
Jul-02-2025
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs