Build genomic interval embeddings and search workflows from BED files.
npx skills add https://github.com/dralkh/seerai --skill geniml-dralkh
Please help me install this Agent Skill. Skill: geniml Source: https://github.com/dralkh/seerai/tree/main/skills/geniml Command: npx skills add https://github.com/dralkh/seerai --skill geniml-dralkh
This Skill turns collections of genomic intervals into machine-learning-ready representations so researchers can compare regions, search datasets, and build reproducible analysis workflows without manual feature engineering.
Use the geniml skill to analyze my BED files, build an appropriate universe, and recommend the right embedding workflow for my genomic research task.
High-intent search queries and answers about installing and using this skill.
To generate embeddings for genomic regions in BED files, you can use Region2Vec to learn numerical representations that capture region similarity for downstream clustering and modeling tasks without manual feature engineering.
To cluster single-cell ATAC-seq data, you can train scEmbed models to generate cell embeddings, which can then be integrated with scanpy-based analysis workflows for cell annotation and clustering.
Universe-based tokenization standardizes multiple BED file inputs into consensus peaks, creating a shared vocabulary that enables robust comparisons and reproducible machine learning across different genomic interval datasets.
Yes, you can use BEDspace to perform metadata-aware search, connecting genomic regions with biological labels such as cell type, tissue, or condition to enable cross-modal dataset retrieval.
The best way to compare genomic regions across multiple ATAC-seq experiments is to build a shared consensus universe, tokenize the datasets, train Region2Vec or scEmbed models, and evaluate which regions best explain biological variation.
No, you do not need to manually engineer features for genomic region similarity analysis; this workflow builds machine-learning-ready representations directly from BED files using Region2Vec and BEDspace training.
jasrajtulsiBuild embeddings and search workflows for genomic interval data from BED files and scATAC-seq datasets.
K-Dense-AIAutomates end-to-end RNA-seq workflow to extract QC metrics clusters and cell-type annotations using Scanpy.
StarlitnightlyAutomate single-cell RNA-seq preprocessing with omicverse notebooks for QC, HVG detection, and embeddings.
LogauaEngstromLearn unsupervised embeddings from genomic interval data for region-level similarity and clustering.
