Predicts genome-wide functional tracks from DNA sequences using the Borzoi-CUDA model.
npx skills add https://github.com/guanxiaol/open-science --skill borzoi
Please help me install this Agent Skill. Skill: borzoi Source: https://github.com/guanxiaol/open-science/tree/main/runtime/skills/borzoi Command: npx skills add https://github.com/guanxiaol/open-science --skill borzoi
The borzoi Skill addresses the need for predicting genome-wide functional tracks from DNA sequences, enabling users to score regulatory effects on expression/accessibility, generate coverage tracks for loci, and prioritize non-coding variants by predicted track delta.
Run the 'borzoi' skill with the command 'predict_tracks(dna_sequence)'. Ensure you have a CUDA-enabled Python environment with Python 3.11 or higher, and CUDA 12.1 or later.
High-intent search queries and answers about installing and using this skill.
To predict genomic functional tracks from a DNA sequence, you can use the Borzoi model to process input sequences and generate predicted coverage tracks for specific loci. It outputs tracks for RNA-seq, CAGE, DNase, and ChIP data.
Yes, you can score non-coding variant regulatory effects using machine learning by calculating predicted track deltas with the Borzoi model. This allows you to assess the impact of variants on gene expression or accessibility.
Yes, you need a CUDA-enabled GPU to run Borzoi genomic analysis. The model requires a Python environment with Python 3.11 or higher and CUDA 12.1 or later to predict functional tracks.
Functional tracks predicted from DNA sequences include RNA-seq, CAGE, DNase, and ChIP tracks. The Borzoi model generates these predictions to facilitate locus coverage prediction and genomic analysis.
To prioritize non-coding variants based on predicted track changes, calculate the track delta between reference and alternative sequences using the Borzoi model. Variants with larger deltas are prioritized for further experiments.
PKU-YuanGroupScore, embed, and generate DNA sequences with a genomic foundation model.
PKU-YuanGroupPredict RNA-seq, CAGE, DNase, and ChIP tracks from DNA sequences.
ovachieverProvides Python-based bioinformatics tools for analyzing DNA, RNA, and protein sequences.
pradyumnasagarPredict transcription factor binding and variant effects from genomic sequences.
