Borzoi: AI Skill for Genome-Wide Functional Track Prediction

Product Overview

Borzoi is an AI skill designed for DNA sequence analysis, specifically focused on predicting genome-wide functional tracks such as RNA-seq, CAGE, DNase, and ChIP. This skill supports developers working with AI coding agents like Claude Code, Cursor, and Codex by providing a mechanism to score and evaluate the regulatory effects of DNA variants.

What this skill does

• Predicts functional tracks from DNA sequences using a pre-trained model.
• Allows scoring of regulatory effects on expression and accessibility by analyzing variants.
• Generates predicted coverage tracks for specific genomic loci.
• Assists in prioritizing non-coding variants based on predicted track differences.

Who it is for

This skill is ideal for bioinformatics developers and research teams who need to incorporate DNA sequence analysis into their workflows. Teams using AI coding platforms like Claude Code, Cursor, or Codex will significantly benefit from the automation of functional track predictions.

Use cases

• Evaluating the potential impact of genomic variants in regulatory regions on gene expression.
• Generating coverage predictions for distinct loci to support research and analysis in genomics.
• Prioritizing and studying non-coding DNA variants by observing changes in predicted functional tracks.

Technical details

• Requires Python 3.10 or newer, with a preference for version 3.11.
• Compatible with CUDA 12.1 or newer, requiring at least 24 GB of GPU VRAM for optimal performance.
• Leverages a pre-trained model available on Hugging Face, requiring either pre-cached weights or egress to huggingface.co.
• Outputs predictions in the format of a `(B, T, L)` tensor consisting of tracks, length bins, and batch size that reflect assay and biosample metadata.
• Usage example: Using a DNA input, the Borzoi model will produce binned predictions across 7,611 human tracks, with optional mouse track analysis.

This AI skill allows genomic analysis without making claims about enhancing business outcomes or guaranteeing specific results, focusing solely on its specialized function of genomic track prediction.

Source & Licence

This package is built on open-source work published by aipoch (aipoch/open-science) and distributed under Apache-2.0. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted under the Apache License 2.0, which also includes an express patent grant. Attribution and any NOTICE file must be retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.