geniml
Analyze Genomic Intervals with Geniml
Genomic interval analysis needs consistent tokenization, embedding training, and quality checks across BED datasets. This skill guides Geniml workflows for Region2Vec, BEDspace, scEmbed, consensus peaks, and evaluation.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "geniml" from https://skillstore.io/skills/davila7-geniml.md and its manifest at https://skillstore.io/api/skills/davila7-geniml/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "geniml". I have 200 ATAC-seq BED files and no labels.
Expected outcome:
A Region2Vec plan with universe preparation, hard tokenization, coverage checks, training settings, and embedding evaluation steps.
Using "geniml". I have scATAC-seq data in AnnData and want clusters.
Expected outcome:
A scEmbed workflow covering peak coordinates, tokenized cells, model training, embedding storage in AnnData, neighbors, Leiden, and UMAP.
Using "geniml". I need a shared search space for regions and tissue labels.
Expected outcome:
A BEDspace plan with preprocessing, metadata formatting, training, distance calculation, query type selection, and result interpretation.
Security Audit
SafeAI adjudication found no malicious intent, prompt injection, or unauthorized data exfiltration. The static findings are documentation examples, Markdown fences, public reference links, local Geniml CLI usage, and an explicit BBClient cache path for BED data.
Risk Factors
⚡ Contains scripts (1)
📁 Filesystem access (4)
⚙️ External commands (20)
🌐 Network access (4)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/davila7-geniml/audits/15?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/davila7-geniml?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/davila7-geniml?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-geniml/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/davila7-geniml.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
davila7. (2026). geniml security audit report (audit version 15) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-geniml/audits/15BibTeX citation
@techreport{davila7-davila7-geniml-2026,
author = {davila7},
title = {geniml security audit report (audit version 15)},
institution = {Skillstore},
year = {2026},
number = {15},
url = {https://skillstore.io/skills/davila7-geniml/audits/15},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "geniml security audit report (audit version 15)"
version: "unspecified"
type: report
authors:
- name: "davila7"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/davila7-geniml/audits/15"
identifiers:
- type: other
value: "skillstore:davila7-geniml:audit:15"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
davila7-geniml
2026-08-21
k-dense-ai-geniml
2026-08-21
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Plan Region Embedding Studies
Choose a Region2Vec workflow for bulk genomic BED collections and define tokenization, training, and evaluation steps.
Analyze Single-Cell Accessibility
Prepare scEmbed workflows for scATAC-seq data, including tokenization, model training, clustering, and scanpy integration.
Build Searchable Genomic Collections
Use BEDspace and Text2BedNN concepts to connect region sets, metadata labels, and similarity search workflows.
Try These Prompts
Choose the best Geniml workflow for my BED files. Compare Region2Vec, BEDspace, scEmbed, and consensus peak building.
Create a Region2Vec plan for BED files, including universe selection, tokenization checks, training parameters, and evaluation metrics.
Design a scEmbed workflow for an scATAC-seq AnnData object. Include pre-tokenization, model training, embedding export, clustering, and validation.
Compare CC, CCF, ML, and HMM consensus peak methods for my project. Recommend parameters for assay type, peak width, and compute limits.
Best Practices
- Build and validate a high-quality universe before training embeddings.
- Record parameters, random seeds, genome assembly, and software versions for reproducibility.
- Evaluate embeddings with quantitative metrics and biological labels when available.
Avoid
- Do not train embeddings before checking tokenization coverage.
- Do not mix genome assemblies within one universe or model.
- Do not treat similarity search results as validated biological findings.
Frequently Asked Questions
What data does this skill work with?
Can it help choose between Region2Vec and BEDspace?
Does it replace Geniml documentation?
Can it create a consensus peak universe?
Does it handle single-cell ATAC-seq?
What dependencies are needed?
Developer Details
Author
davila7License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
b959ebfd1043a07c0c4378ab94ca4342cb0259f5
Maintenance freshness
7/20/2026
Usage
6 downloads · 389 views
File structure