bio-atac-seq-deep-learning-atac
Sequence-based deep learning for ATAC-seq using chromBPNet, BPNet, scBasset, or EnFormer. Use when correcting Tn5 bias with neural networks beyond k-mer models, predicting per-base accessibility profiles, scoring in silico variant effects at GWAS or rare-variant SNPs, discovering motifs via DeepLIFT/TF-MoDISco from a trained model, or generating cell-type-specific accessibility predictions for unobserved cell states.
npx skills add BioTender-max/awesome-bio-agent-skills --skill deep-learning-atac --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Version Compatibility Reference examples tested with: chrombpnet 0.1.7+, bpnet-lite 0.6+ (DOI 10.5281/zenodo.7011327), scBasset 0.1.0+ (basenji2 fork), tangermeme 0.1+, tfmodisco-lite 2.2+, DeepLIFT 0.6+, captum 0.7+, tensorflow 2.13+, pytorch 2.1+, kipoi 0.8+. Verify before use: - Python: `pip show <package>` then `help(module.function)` to check signatures - CLI: `<tool> --version` then `<tool> --help` to confirm flags If code throws unexpected errors, introspect the installed package and adapt rather than retrying. Deep-learning tooling evolves rapidly; method papers post 2023 may have superseded reference implementations. # Sequence-Based Deep Learning for ATAC-seq **"Score the effect of a GWAS SNP on chromatin accessibility"** -> Train (or use pre-trained) sequence-to-accessibility CNNs that take 1-5 kb DNA windows and predict per-base Tn5 cleavage profiles. Outputs include: bias-corrected accessibility, single-base mutation effect predictions, and DeepLIFT contribution scores convertible to motifs via TF-MoDISco. - CLI: `chrombpnet pipeline --bigwig signal.bw --bigwig-bias bias.bw ...` - Python: `bpnet-lite` for custom architectures; `tangermeme` for fast scoring - Python
- Version Compatibility
- Algorithmic Taxonomy
- When Deep Learning Helps vs When Classical Pipelines Suffice
- Per-Tool Failure Modes
- chromBPNet -- Bias model mismatch
- chromBPNet -- Insufficient training data
- BPNet / chromBPNet -- DeepLIFT vs Integrated Gradients confusion
- scBasset -- Cell projection layer instability
- EnFormer -- Pre-trained models lack target cell type
- tangermeme -- Marginal vs in silico mutagenesis confusion
- Decision Tree by Goal
- chromBPNet Standard Pipeline
- DeepLIFT + TF-MoDISco for Motif Discovery
- In Silico Variant Effect Prediction
chrombpnet prep splits \ Train chromosomes are auto-inferred (whatever is not in -tcr/-vcr). The `-tecr` flag does NOT exist. chrombpnet bias pipeline \ chrombpnet pipeline \ git clone https://github.com/kundajelab/variant-scorer python variant-scorer/src/variant_scoring.py \ Generate one-hot sequence and SHAP / DeepLIFT contribution score arrays from chromBPNet Run TF-MoDISco-lite via its CLI modisco motifs \ Generate HTML report with discovered motifs matched to known databases
What does the bio-atac-seq-deep-learning-atac skill do?
Sequence-based deep learning for ATAC-seq using chromBPNet, BPNet, scBasset, or EnFormer. Use when correcting Tn5 bias with neural networks beyond k-mer models, predicting per-base accessibility profiles, scoring in silico variant effects at GWAS or rare-variant SNPs, discovering motifs via DeepLIFT/TF-MoDISco from a trained model, or generating cell-type-specific accessibility predictions for unobserved cell states.
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill deep-learning-atac --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.