Detect promoter regions in DNA sequences via the Genomic Intelligence promoter-prediction API.
npx skills add https://github.com/ClawBio/ClawBio --skill gi-promoter
Please help me install this Agent Skill. Skill: gi-promoter Source: https://github.com/ClawBio/ClawBio/tree/main/skills/gi-promoter Command: npx skills add https://github.com/ClawBio/ClawBio --skill gi-promoter
Predicting promoter regions in a multi-kilobase DNA sequence normally requires GPU infrastructure, model weight downloads, tokenization, and windowing logic. This Skill replaces that setup with a single CLI call to the hosted Genomic Intelligence G0 transformer (GENA-LM BERT Large), returning per-window promoter probabilities and called regions in under a second.
Run the gi-promoter skill with the --demo flag to predict promoter regions in the bundled TP53 FASTA sequence and write the report to an output directory.
High-intent search queries and answers about installing and using this skill.
Run the gi-promoter CLI with a single-record FASTA file between 300 and 500,000 bp. The sequence is posted to the Genomic Intelligence /v1/tasks/promoter/predict endpoint, which windows it internally and returns per-window promoter probabilities plus called regions.
The default model is a GENA-LM BERT Large transformer with a 2000 bp context window and 1000 bp prediction stride. Shorter-context and DNABERT variants are also published; query GET /v1/tasks/promoter/models for the current list of model ids.
Yes, the skill requires a Genomic Intelligence partner key supplied via the --api-key flag or the GI_API_KEY environment variable. A shared hackathon-tier key ships in the repo's .env.example, and individual keys can be requested from [email protected].
An empty result often indicates wrong strand orientation, because the model is strand-sensitive and scores collapse below threshold on the genomic strand of minus-strand genes. Reverse-complement the sequence to gene-sense before submitting, and check that N-content is not dominating the region.
Sequences must be 300 to 500,000 bp after whitespace stripping, enforced as minLength and maxLength on the request schema. Violations return a 422 validation_failed error, and the skill rejects out-of-bounds input locally before spending an API request.
No, this skill performs remote inference, so submitted sequences traverse the hosted Genomic Intelligence endpoint. Do not submit identifiable patient data without an appropriate data-use agreement; the skill is intended for research and development use only.
pradyumnasagarCompute reverse complements and complements for DNA/RNA sequences with IUPAC ambiguity support.
K-Dense-AIPredict promoters, splice sites, enhancers, chromatin state, and gene expression from DNA sequences via hosted transformer models.
fgarofalo56Run local AI models via a self-hosted OpenAI-compatible API.
LynxLabVNAutomate research paper writing from literature review to conference submission.
