New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bio Atac Seq Enhancer Gene Linking

by GPTomics in GPTomics/bioSkills

Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero.

MITAuto-check passedResearch & Science

Install Bio Atac Seq Enhancer Gene Linking

skills CLI
$ npx skills add GPTomics/bioSkills --skill bio-atac-seq-enhancer-gene-linking -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GPTomics/bioSkills bio-atac-seq-enhancer-gene-linking --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/atac-seq/enhancer-gene-linking .claude/skills/bio-atac-seq-enhancer-gene-linking && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bio-atac-seq-enhancer-gene-linking
GitHub stars
1.2k
Used in
2 other repos
Token cost
~4.6k tokens
SKILL.md length
1,749 words
Files
3
Skills in repo
559
Repo updated
First seen
Licence
MIT

At a glance

Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero.

  • Works in 4 steps: Design sgRNAs tiling each candidate… → Transduce CRISPRi-expressing cells; FACS… → Sequence sgRNAs in low- vs… → …
  • Linking distal enhancers to target genes
  • SKILL.md covers Version Compatibility, Algorithmic Taxonomy, ABC Mathematics and ENCODE-rE2G Differences from ABC, plus 10 more sections
  • Runs Shell scripts from its folder; calls python, git and pip; reaches github.com

What it does

Bio Atac Seq Enhancer Gene Linking is an agent skill from GPTomics/bioSkills. Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero. Use when linking distal enhancers to target genes, choosing between contact-aware (ABC, ENCODE-rE2G), accessibility-only (Cicero), and orthogonal (HiChIP H3K27ac, EpiMap) approaches, validating predictions against CRISPRi-FlowFISH gold-standard, or building cell-type-specific regulatory maps for fine-mapping or therapeutic target discovery.

Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `examples/run_abc.sh` and `usage-guide.md`).

It sits in Research & Science, covering Bioinformatics. The repository describes itself as: a set of SKILLS.md for doing bioinformatics with agents like claude code. The licence is MIT.

When your agent uses it

  • Linking distal enhancers to target genes
  • Choosing between contact-aware (ABC
  • Accessibility-only (Cicero)
  • Orthogonal (HiChIP H3K27ac

Example prompts

  • “/bio-atac-seq-enhancer-gene-linking”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Design sgRNAs tiling each candidate enhancer
  2. Transduce CRISPRi-expressing cells; FACS by gene expression (FlowFISH for endogenous; reporter for ectopic)
  3. Sequence sgRNAs in low- vs high-expression bins; compute log2 enrichment per sgRNA
  4. Significance: meta-test across sgRNAs in same enhancer

What it can do on your machine

Read from SKILL.md and the folder at commit d91ed3d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • git
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bio Atac Seq Enhancer Gene Linking loads about 4.6k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 1,749 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 1,749 words, ~4,617 tokens.

Download SKILL.mdSave it as .claude/skills/bio-atac-seq-enhancer-gene-linking/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
bio-atac-seq-enhancer-gene-linking
description
Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero. Use when linking distal enhancers to target genes, choosing between contact-aware (ABC, ENCODE-rE2G), accessibility-only (Cicero), and orthogonal (HiChIP H3K27ac, EpiMap) approaches, validating predictions against CRISPRi-FlowFISH gold-standard, or building cell-type-specific regulatory maps for fine-mapping or therapeutic target discovery.
tool_type
mixed
primary_tool
ABC-Enhancer-Gene-Prediction

Version Compatibility

Reference examples tested with: ABC-Enhancer-Gene-Prediction 0.2.2+ (Engreitz lab), ENCODE-rE2G v1.0+ (EngreitzLab), Cicero 1.20+, GenomicInteractions 1.36+, FitHiChIP 9.1+, HiC-Pro 3.1+, FAN-C 0.9+, MACS3 3.0+, samtools 1.19+, bedtools 2.31+.

Verify before use:

  • CLI: <tool> --version then <tool> --help to confirm flags
  • R: packageVersion('<pkg>') then ?function_name to verify parameters
  • Python: pip show <package> then help(module.function) to check signatures

If code throws unexpected errors, introspect the installed package and adapt rather than retrying.

Enhancer-Gene Linking

"Which gene does this distal accessible region regulate?" -> Predict the enhancer's target gene using a model that combines accessibility activity, 3D contact frequency, and (optionally) sequence-based chromatin predictions. Output is a per-(enhancer, gene) score that can be thresholded for high-confidence calls.

  • CLI: ABC pipeline (run.neighborhoods.py, predict.py from Engreitz lab)
  • CLI: ENCODE-rE2G (Snakemake-based; ENCODE 4 enhancer-gene standard)
  • R: Cicero (ATAC-only; covered in atac-seq/co-accessibility)
  • CLI: FitHiChIP / hichipper for HiChIP H3K27ac loops
  • Database: EpiMap (Boix 2021), GeneHancer, FANTOM5 (pre-computed reference)

ABC and ENCODE-rE2G are the canonical predictors when Hi-C/Micro-C data is available. Cicero is the ATAC-only fallback. CRISPRi-FlowFISH (Fulco 2019) is the gold-standard experimental validation.

Algorithmic Taxonomy

MethodInputsMathematicsStrengthFails when
ABC (Fulco 2019, Nasser 2021)ATAC + H3K27ac + Hi-C/Micro-CABC = (Activity_E x Contact_E,G) / sum_e(Activity_e x Contact_e,G); threshold typically >= 0.02Mechanistically grounded; published gold-standard for human cell linesRequires matched Hi-C / Micro-C; cell-type-specific; default contact uses average across 10 ENCODE cell types if Hi-C not available
ENCODE-rE2G (Gschwind 2023)ATAC + H3K27ac + (Hi-C optional)Logistic regression trained on CRISPRi-FlowFISH ground truth; uses ABC features + sequence features + distanceENCODE 4 standard; pre-trained models for many cell typesPre-trained models only available for ENCODE cell types; retraining requires CRISPRi data
Cicero (Pliner 2018)scATAC peak-cell matrixGraphical lasso on metacell co-accessibilityATAC-only; works without Hi-CLess concordant with Hi-C than ABC; cis-distance-limited; alpha-sensitive
HiChIP H3K27ac + FitHiChIPH3K27ac HiChIPStatistically significant loops at FDR < 0.05Direct experimental loop measurement; cell-type-specific; orthogonal to ATACRequires HiChIP wet-lab; only captures loops within HiChIP resolution (~10 kb)
Hi-C + HiCCUPSBulk Hi-CFold-enrichment loop callingMost-validated 3D contact methodResolution typically 5-25 kb; misses sub-loop fine structure
Capture Hi-C / PCHi-C (CHiCAGO)Promoter Capture Hi-CAsymptotic CHiCAGO scoreHigh-resolution promoter-anchoredWet-lab cost; promoter capture only
EpiMap (Boix 2021) referenceNone (pre-computed lookup)Bulk-derived enhancer-gene predictions in 833 epigenomesFast, comprehensiveCell-type-agnostic for tissues outside the reference set
GeneHancer / FANTOM5 (legacy)None (pre-computed lookup)Pre-computed; varied methods per databaseComprehensive lookup; widely citedOlder; less reliable than ABC for cell-type-specific

Methodology evolves; verify against current Engreitz lab releases (ABC), ENCODE 4 publications (ENCODE-rE2G), and Mumbach 2017 (HiChIP) before locking pipelines.

ABC Mathematics

For each candidate (enhancer E, gene G) pair within the cis window (default 5 Mb):

ABC(E -> G) = Activity_E * Contact_E,G / sum_{all e in window}(Activity_e * Contact_e,G)
  • Activity_E = ATAC reads at E * H3K27ac reads at E (geometric mean of normalized signals; reflects "enhancer strength")
  • Contact_E,G = Hi-C/Micro-C contact frequency from E to G's TSS (after distance-correction)
  • Window = +/- 5 Mb cis (default; ENCODE-rE2G uses 1 Mb)

Threshold typical: ABC >= 0.02 for high-confidence; >= 0.01 for exploratory.

When Hi-C is unavailable, ABC uses an "average contact" averaged across 10 ENCODE Hi-C cell types as proxy (Nasser 2021); it performs comparably to cell-type-matched Hi-C. The alternative powerlaw approximation of contact-vs-distance is the Fulco 2019 fallback.

ENCODE-rE2G Differences from ABC

ENCODE-rE2G (Gschwind et al 2023, bioRxiv) is a reformulation:

  • Logistic regression trained on CRISPRi-FlowFISH ground truth (~10 cell types)
  • Features: ABC score components + 3D contact + distance + activity ratios
  • Multiple feature configurations: "abc-features", "no-hic-features" for cells without 3D data
  • Output: Per-pair probability of regulatory connection
  • Pre-trained models for ENCODE cell lines; logistic params vary by cell type

ENCODE-rE2G generally outperforms ABC at CRISPRi recall, especially at modest distances (50-500 kb). For ENCODE cell types, prefer ENCODE-rE2G; for novel cell types, ABC remains the default.

Per-Tool Failure Modes

ABC -- Wrong cell-type-matched Hi-C

Trigger: Using K562 Hi-C contact when actual cell type is GM12878.

Mechanism: Contact frequencies differ across cell types at compartment and TAD boundaries; using mismatched Hi-C produces wrong ABC scores.

Symptom: ABC predictions concentrate at known K562-specific loci even when ATAC data is from GM12878.

Fix: Use cell-type-matched Hi-C or Micro-C. If unavailable, ABC's "average HiC" (10-cell-type pooled) is the documented fallback with acknowledged degradation. Document the proxy in methods.

ABC -- H3K27ac normalization

Trigger: H3K27ac ChIP-seq with different sequencing depth than ATAC.

Mechanism: ABC's "Activity" is the geometric mean of accessibility and H3K27ac signals; both must be normalized to the same scale.

Symptom: Activity scores skewed; some peaks have very high activity from H3K27ac alone, others from ATAC alone.

Fix: Normalize both signals to reads-per-million in peaks (RPM-IP) before combining. Use ABC's --qnorm flag with a quantile-normalization reference file (e.g. --qnorm reference/EnhancersQNormRef.K562.txt from the ABC repo).

ENCODE-rE2G -- Cell type not in pre-trained set

Trigger: Running pre-trained model on a primary cell type not in CRISPRi training.

Mechanism: Logistic regression coefficients learned from ENCODE cell types may not transfer to primary tissues.

Fix: Use the closest ENCODE cell type (myeloid lineage -> K562; lymphoid -> GM12878; hepatic -> HepG2). Document the proxy. For high-stakes use, custom retraining requires CRISPRi-FlowFISH data.

Cicero -- No Hi-C concordance benchmark

Trigger: Reporting Cicero connections as enhancer-gene calls without external validation.

Mechanism: Cicero is statistical co-accessibility; correlation with Hi-C 3D contacts is ~30-50%. Many strong Cicero connections are NOT Hi-C-validated.

Fix: When Hi-C is available, cross-validate; report both. When only ATAC, use Cicero with the explicit caveat that connections are co-accessibility hypotheses, not contact predictions.

HiChIP -- Loop calling threshold

Trigger: Default FitHiChIP at FDR < 0.05.

Mechanism: HiChIP loops are abundant (10k-100k per dataset); FDR alone produces a long tail of weak loops.

Fix: Threshold at FDR < 0.05 AND number of contacts per loop >= 5; or use the top N most significant where N = expected number of loops based on cell type.

EpiMap / GeneHancer -- Cell-type-agnostic limitation

Trigger: Using EpiMap or GeneHancer pre-computed pairs for a specific cell type.

Mechanism: These references aggregate across many tissues / experiments; cell-type-specific connections are diluted.

Fix: Use as a baseline / sanity check, not as the primary call. ABC or ENCODE-rE2G in the actual cell type is preferred.

Decision Tree by Available Data

Available dataRecommended method
ATAC + H3K27ac + matched Hi-C/Micro-CABC or ENCODE-rE2G (with cell-type-matched contact)
ATAC + H3K27ac, no Hi-CABC with average HiC fallback; or ENCODE-rE2G no-hic model
ATAC only, no H3K27acCicero (atac-seq/co-accessibility); ABC with synthetic activity
ATAC + H3K27ac HiChIPFitHiChIP loops + ABC; intersect for high confidence
Multiome (ATAC + RNA same cell)LinkPeaks (Signac) for direct correlation; SCENIC+ for TF networks
ENCODE cell typePre-computed ENCODE-rE2G predictions (download)
Tissue with limited public dataABC + acknowledge proxy; do not rely on EpiMap
Multi-cell-type scATACscBasset (atac-seq/deep-learning-atac) for sequence-based per-cell
Want experimental validationCRISPRi-FlowFISH design; use predictions as targeted hypotheses
Show full SKILL.md (660 more words)Show less

ABC Standard Pipeline

Goal: Compute per-(enhancer, gene) ABC scores combining ATAC accessibility, H3K27ac activity, and Hi-C contact.

Approach: Define non-promoter candidate enhancers from ATAC peaks, run ABC neighborhoods (which counts reads directly from the ATAC/H3K27ac BAMs) to compute per-candidate activity, then run ABC predict against a Hi-C contact matrix and threshold the per-pair ABC score.

bash
# 1. (Optional, browser tracks only) ATAC/H3K27ac bigWigs -- ABC neighborhoods below reads the BAMs directly, not bigWigs
bamCoverage --bam atac.bam --outFileName atac.bw --binSize 50 --normalizeUsing RPGC \
    --effectiveGenomeSize 2701495711 --numberOfProcessors 8

# 2. Define enhancer candidates (typically MACS narrowPeak from ATAC)
# Filter to non-promoter regions
bedtools intersect -v -a atac_peaks.narrowPeak -b promoter_regions.bed > candidate_enhancers.bed

# 3. Run ABC neighborhoods (compute Activity per candidate)
# Script path: legacy ABC = src/run.neighborhoods.py; Snakemake-based modern = workflow/scripts/run.neighborhoods.py
python /path/ABC-Enhancer-Gene-Prediction/workflow/scripts/run.neighborhoods.py \
    --candidate_enhancer_regions candidate_enhancers.bed \
    --genes refseq_protein_coding.bed \
    --H3K27ac h3k27ac.bam \
    --DHS atac.bam \
    --chrom_sizes hg38.chrom.sizes \
    --chrom_sizes_bed hg38.chrom.sizes.bed \
    --ubiquitously_expressed_genes Genes.ubiquitously_expressed.txt \
    --cellType MyCellType \
    --outdir abc_out/

# 4. Run ABC predictions (Activity * Contact) -- generates ALL unthresholded links
python /path/ABC-Enhancer-Gene-Prediction/workflow/scripts/predict.py \
    --enhancers abc_out/EnhancerList.txt \
    --genes abc_out/GeneList.txt \
    --hic_file hic_data/ \
    --hic_type avg \
    `# --hic_type choices: hic | juicebox | bedpe | avg -- must match the Hi-C input format` \
    --hic_resolution 5000 \
    --hic_pseudocount_distance 5000 \
    `# --hic_pseudocount_distance (required): powerlaw fit at this distance is added as a pseudocount (config default 5000)` \
    --chrom_sizes hg38.chrom.sizes \
    --score_column ABC.Score \
    --cellType MyCellType \
    --outdir abc_out/Predictions/

# predict.py writes EnhancerPredictionsAllPutative.tsv.gz (all unthresholded E-G links).
# 5. Threshold at ABC.Score >= 0.02. The ABC Snakemake pipeline runs filter_predictions.py with its
# full set of --output_* arguments; for a standalone cut, select by the ABC.Score column (by header):
zcat abc_out/Predictions/EnhancerPredictionsAllPutative.tsv.gz | \
    awk -F'\t' 'NR==1{for(i=1;i<=NF;i++)if($i=="ABC.Score")c=i; print; next} $c>=0.02' \
    > abc_out/Predictions/EnhancerPredictions_thresholded.tsv

ABC.Score >= 0.02 is the standard threshold validated in Fulco 2019 against CRISPRi-FlowFISH; >= 0.04 is a stricter cut sometimes used in the ABC pipeline documentation for higher precision (no separate primary-paper calibration).

ENCODE-rE2G

bash
# Snakemake-based; clone the ENCODE-rE2G repo
git clone https://github.com/EngreitzLab/ENCODE_rE2G
cd ENCODE_rE2G

# Inputs are supplied through config/config.yaml, whose ABC_BIOSAMPLES field points to
# an ABC biosamples TSV carrying the cell type and the ATAC / H3K27ac / Hi-C paths --
# there is no cell_type=/atac_bw= --config override interface.
snakemake -j1 --use-conda

# Output: encode_e2g_predictions.tsv.gz with per-pair ENCODE-rE2G.Score and thresholded predictions

Pre-trained models are at https://github.com/EngreitzLab/ENCODE_rE2G/tree/main/models. Choose by tissue similarity if exact cell type not present.

CRISPRi-FlowFISH Validation Framework

CRISPRi-FlowFISH (Fulco 2019) is the experimental gold-standard:

  1. Design sgRNAs tiling each candidate enhancer
  2. Transduce CRISPRi-expressing cells; FACS by gene expression (FlowFISH for endogenous; reporter for ectopic)
  3. Sequence sgRNAs in low- vs high-expression bins; compute log2 enrichment per sgRNA
  4. Significance: meta-test across sgRNAs in same enhancer

A 2-fold expression decrease (p < 0.05) confirms the enhancer regulates the gene.

For predictions to be publication-grade, ENCODE 4 expects:

  • Test set sensitivity / specificity against published CRISPR enhancer-screen catalogs (Fulco 2019: K562 FlowFISH; Gasperini 2019: K562; Schraivogel 2020: K562 TAP-seq)
  • Effect-size correlation between predicted score and observed expression effect
  • Distance bias check (predictors over-rank close-distance pairs)

Reconciling Methods

PatternLikely causeAction
ABC and ENCODE-rE2G disagreeDifferent feature weighting; different training distributionsBoth valid; report intersection as high-confidence
ABC strong, Cicero weakCo-accessibility sparse for that cell typeTrust ABC if Hi-C is matched
HiChIP loop with no ABC predictionLoop is below ABC threshold; or peak set too narrowLower threshold or expand candidate enhancers
ENCODE-rE2G high probability, no CRISPRi supportCould be context-dependent biology or false positivePrioritize for follow-up; not a publishable claim alone
EpiMap pair not in ABCPre-computed reference is cell-type-aggregatedUse ABC for cell-type-specific

Operational rule for high-confidence reporting: Predictions used for therapeutic target nomination must be (a) above ABC >= 0.02 OR ENCODE-rE2G >= 0.5, AND (b) consistent across two methods (ABC + ENCODE-rE2G or ABC + HiChIP), AND (c) validated experimentally (CRISPRi-FlowFISH preferred). Single-method high-score predictions are exploratory hypotheses.

Combining Multiple Predictions

Goal: Build a high-confidence enhancer-gene set by intersecting ABC, ENCODE-rE2G, and HiChIP evidence.

Approach: Load each method's output, merge ABC and ENCODE-rE2G on enhancer-gene pair above per-method thresholds, then flag pairs with HiChIP loop support for triple-method evidence.

python
import pandas as pd
abc = pd.read_csv('abc_predictions.tsv', sep='\t')
re2g = pd.read_csv('encode_re2g.tsv.gz', sep='\t')
hichip = pd.read_csv('fithichip_loops.bedpe', sep='\t', header=None,
                     names=['chr1','s1','e1','chr2','s2','e2','name','score'])

# High-confidence intersection
high_conf = abc[abc['ABC.Score'] >= 0.02].merge(
    re2g[re2g['ENCODE-rE2G.Score'] >= 0.5],
    on=['enhancer_id', 'gene'])

# Add HiChIP support flag
hichip_anchors = ...    # extract enhancer/gene pairs from HiChIP loops
high_conf['hichip_support'] = high_conf['enhancer_id'].isin(hichip_anchors)

Common Errors

Error / symptomCauseSolution
ABC predictions concentrate at TSSsDid not exclude promoter regions from candidatesPre-filter bedtools intersect -v against promoters
Activity scores all very smallH3K27ac or ATAC bigWig in wrong scaleUse RPGC normalization
ENCODE-rE2G model not convergingPre-trained model loaded for wrong cell typeMatch training cell type via cell_type config
Cicero connections used as enhancer-gene callsMethod confusion (co-accessibility vs contact)Switch to ABC if Hi-C available; or document as co-accessibility hypothesis
Hi-C resolution too coarseDefault 25 kb resolution masks fine ABC structureUse 5 kb or 10 kb if Micro-C available
FitHiChIP many loops, low specificityDefault FDR aloneAdd contact count threshold; or use ENCODE-rE2G HiChIP-trained model
GeneHancer / FANTOM5 used as primary callCell-type-agnostic limitationUse as baseline only

References

  • Fulco CP et al 2019 Nat Genet 51:1664 (ABC; CRISPRi-FlowFISH validation)
  • Nasser J et al 2021 Nature 593:238 (ABC genome-wide application)
  • Gschwind AR et al 2023 bioRxiv 2023.11.09.563812 (ENCODE-rE2G; encyclopedia of enhancer-gene regulatory interactions; preprint)
  • Mumbach MR et al 2017 Nat Genet 49:1602 (HiChIP H3K27ac)
  • Bhattacharyya S et al 2019 Nature Communications 10:4221 (FitHiChIP)
  • Boix CA et al 2021 Nature 590:300 (EpiMap reference)
  • Gasperini M et al 2019 Cell 176:377 (CRISPRi at scale)
  • Schraivogel D et al 2020 Nat Methods 17:629 (TAP-seq targeted Perturb-seq enhancer screen, K562; scRNA-seq readout)
  • Pliner HA et al 2018 Mol Cell 71:858 (Cicero co-accessibility)
  • atac-seq/co-accessibility - Cicero (ATAC-only enhancer-promoter inference)
  • atac-seq/atac-peak-calling - Generate enhancer candidates
  • atac-seq/consensus-peakset - Fixed-width enhancer regions
  • atac-seq/deep-learning-atac - chromBPNet variant effect at predicted enhancers
  • atac-seq/single-cell-atac - Per-cell-type scATAC inputs
  • hi-c-analysis/loop-calling - Hi-C / Micro-C contact prediction
  • hi-c-analysis/contact-pairs - Hi-C / Micro-C input
  • chip-seq/peak-calling - H3K27ac peaks
  • gene-regulatory-networks/scenic-regulons - Downstream TF -> target inference

© GPTomics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in atac-seq/enhancer-gene-linking of GPTomics/bioSkills.

  • SKILL.md
  • examples/run_abc.sh
  • usage-guide.md

Open the folder on GitHubat commit d91ed3d

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Bio Atac Seq Enhancer Gene Linking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bio Atac Seq Enhancer Gene Linking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bio Atac Seq Enhancer Gene Linking this skillGPTomics/bioSkills1.2k2 repos~4.6kAutomated safety check: PassMIT
Spatial S5 DownstreamQING1105/ezST101—~513Automated safety check: PassMIT
Bio Proteomics Ptm AnalysisFreedomIntelligence/OpenClaw-Medical-Skills3.1k1 repos~1.2kAutomated safety check: PassNone
Plannotate Plasmid Annotationjaechang-hits/SciAgent-Skills3741 repos~4.7kAutomated safety check: PassGPL-3.0
Bio Atac Seq Motif DeviationFreedomIntelligence/OpenClaw-Medical-Skills3.1k—~2.3kAutomated safety check: PassNone
Viennarna Structure Predictionjaechang-hits/SciAgent-Skills3741 repos~5.4kAutomated safety check: PassMIT

Similar skills

  • Spatial S5 Downstream

    QING1105/ezST

    Stage 5 of the spatial transcriptomics workflow — neighborhood enrichment and cell-cell communication analysis.

    101 GitHub stars~513 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Bio Proteomics Ptm Analysis

    FreedomIntelligence/OpenClaw-Medical-Skills

    Post-translational modification analysis including phosphorylation, acetylation, and ubiquitination.

    3.1k GitHub starsUsed in 1 repo~1.2k tokens
    Research & ScienceAuto-check passed

  • Plannotate Plasmid Annotation

    jaechang-hits/SciAgent-Skills

    Auto-annotate plasmids with features (promoters, terminators, resistance, origins, tags, fluorescent proteins) via BLAST against curated DBs (Addgene, fpbase, SnapGene).

    374 GitHub starsUsed in 1 repo~4.7k tokens
    Research & ScienceAuto-check passed

  • Bio Atac Seq Motif Deviation

    FreedomIntelligence/OpenClaw-Medical-Skills

    Analyze transcription factor motif accessibility variability using chromVAR.

    3.1k GitHub stars~2.3k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

  • Viennarna Structure Prediction

    jaechang-hits/SciAgent-Skills

    Predict RNA secondary structure, MFE folding, base-pair probabilities, RNA-RNA interactions via ViennaRNA Python bindings.

    374 GitHub starsUsed in 1 repo~5.4k tokens
    Research & ScienceAuto-check passed

  • Alphagenome Single Variant Analysis

    google-deepmind/science-skills

    Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.

    3.2k GitHub starsUsed in 2 repos~3k tokens
    Research & ScienceAuto-check: notes

More from GPTomics/bioSkills

All 559 skills in this repo

  • Bio Alignment Io

    GPTomics/bioSkills

    Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.

    1.2k GitHub starsUsed in 3 repos~4.9k tokens
    Auto-check passed

  • bioSkills Installer

    GPTomics/bioSkills

    Installs the bioSkills collection of 425 bioinformatics skills in one step, or only chosen categories, so sequencing, RNA-seq, single-cell and variant tasks get specialized help.

    1.2k GitHub starsUsed in 1 repo~789 tokens
    Auto-check passed

  • Bio Write Sequences

    GPTomics/bioSkills

    Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.

    1.2k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed

  • Amplicon Primer Clipping

    GPTomics/bioSkills

    Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.

    1.2k GitHub starsUsed in 2 repos~2.2k tokens
    Auto-check passed

  • Alignment Filtering with samtools and pysam

    GPTomics/bioSkills

    Filters BAM alignments by FLAG bits, mapping quality and regions with samtools view or pysam, with recipes for common keep and drop cases.

    1.2k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed

  • Bio Alignment Indexing

    GPTomics/bioSkills

    Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.

    1.2k GitHub starsUsed in 2 repos~2.4k tokens
    Auto-check passed

Categories

Questions about Bio Atac Seq Enhancer Gene Linking

What does Bio Atac Seq Enhancer Gene Linking do?

Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero. Bio Atac Seq Enhancer Gene Linking is an agent skill from GPTomics/bioSkills. Predict enhancer-gene regulatory connections from ATAC-seq using ABC, ENCODE-rE2G, HiChIP, or Cicero.

When should I use Bio Atac Seq Enhancer Gene Linking?

Bio Atac Seq Enhancer Gene Linking fits situations like: linking distal enhancers to target genes; choosing between contact-aware (ABC; accessibility-only (Cicero); orthogonal (HiChIP H3K27ac.

How do I install Bio Atac Seq Enhancer Gene Linking in Claude Code?

Run `npx skills add GPTomics/bioSkills --skill bio-atac-seq-enhancer-gene-linking -a claude-code`. Or copy the skill folder (atac-seq/enhancer-gene-linking in GPTomics/bioSkills) into .claude/skills/bio-atac-seq-enhancer-gene-linking in your project. Claude Code loads it when a task matches its description.

How do I install Bio Atac Seq Enhancer Gene Linking in Codex?

Run `npx skills add GPTomics/bioSkills --skill bio-atac-seq-enhancer-gene-linking -a codex`. Or copy the skill folder (atac-seq/enhancer-gene-linking in GPTomics/bioSkills) into .agents/skills/bio-atac-seq-enhancer-gene-linking in your project. Codex loads it when a task matches its description.

Can I use Bio Atac Seq Enhancer Gene Linking in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GPTomics/bioSkills --skill bio-atac-seq-enhancer-gene-linking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bio-atac-seq-enhancer-gene-linking, .gemini/skills/bio-atac-seq-enhancer-gene-linking, .github/skills/bio-atac-seq-enhancer-gene-linking and .opencode/skills/bio-atac-seq-enhancer-gene-linking in your project.

What does Bio Atac Seq Enhancer Gene Linking need to run?

Going by SKILL.md and its folder, Bio Atac Seq Enhancer Gene Linking needs a shell for the scripts in its folder and the command-line tools its instructions call (python, git and pip). Our summary lists: Python 3; A Bash shell.

Does Bio Atac Seq Enhancer Gene Linking access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Bio Atac Seq Enhancer Gene Linking safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Bio Atac Seq Enhancer Gene Linking use?

Bio Atac Seq Enhancer Gene Linking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bio Atac Seq Enhancer Gene Linking use?

About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bio Atac Seq Enhancer Gene Linking?

Skills that share tags, products or a category with Bio Atac Seq Enhancer Gene Linking: Spatial S5 Downstream (QING1105/ezST, 101 stars), Bio Proteomics Ptm Analysis (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Plannotate Plasmid Annotation (jaechang-hits/SciAgent-Skills, 374 stars) and Bio Atac Seq Motif Deviation (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bio Atac Seq Enhancer Gene Linking?

GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,218 GitHub stars. The repository holds 559 skills in this directory. The repository was last updated on August 15, 2026.

Source: GPTomics/bioSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.