bio-splice-variant-prediction
Predicts whether a DNA variant alters mRNA splicing using sequence-based deep-learning tools — SpliceAI (10kb context dilated CNN, clinical default), Pangolin (multi-tissue), MMSplice (modular per-region CNN with calibrated ΔPSI), SpliceTransformer/TrASPr (tissue-aware transformers), SpliceVault (empirical 300K-RNA lookup of likely mis-splicing outcomes), CADD-Splice (composite score). Applies the ClinGen SVI 2023 framework for ACMG/AMP variant interpretation (PVS1, PP3, BP4 evidence codes), HGVS splicing nomenclature (c.123+1G>A, c.123-3T>G, r.spl?), extended-window scoring for deep-intronic
npx skills add BioTender-max/awesome-bio-agent-skills --skill splice-variant-prediction --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.
What it does
Predicts whether a DNA variant alters mRNA splicing using multiple sequence-based tools and ClinGen SVI 2023 framework guidance, to aid interpretation of clinical variants and ASO design.
How it works
- Advises running SpliceAI to annotate variants with per-variant delta scores and provides example CLI usage, including a default window (-D 50) and an extended window option (-D 500 to 2000) for deep-intronic variants.
- Recommends Pangolin for tissue-specific predictions when the disease-tissue is known, producing per-tissue outputs across brain, heart, liver, and testis, with fallback to SpliceAI for unseen tissues.
- Uses SpliceVault to predict empirical mis-splicing outcomes and MMSplice to estimate calibrated ΔPSI across splicing regions, with example code for data loading and prediction.
- Includes HGVS splicing nomenclature guidance and example annotations for notation like c.123+1G>A, c.124-3T>G, r.spl?, and validations via VariantValidator or Mutalyzer.
- Describes extended-window scoring for deep-intronic variants and shows how to compare concordance across SpliceAI, Pangolin, and MMSplice to interpret results.
- Mentions branchpoint detection tools (BPHunter, LaBranchoR, etc.) and notes that SpliceAI may miss branchpoint effects; suggests additional screening when relevant.
- Provides a workflow for Splice-switching ASO design context: perform SpliceAI on masked sequences and consider RNA accessibility analyses.
When to use it
Use when interpreting splice impact of clinical variants, prioritizing VUS, identifying deep-intronic pathogenic variants, or designing ASOs. Use extended window for deep-intronic evaluation or when canonical-site disruption alone is insufficient.
What it can touch
- Tools described: SpliceAI, Pangolin, MMSplice, SpliceTransformer, TrASPr (as part of methodology), SpliceVault, CADD-Splice, BPHunter, LaBranchoR, BPP, SVM-BPfinder, RNAfold (in ASO design context), CI-SpliceAI.
- Code snippets reference commands and Python code for data handling and predictions, as shown in the examples.
Caveats
- Emphasizes concordance across SpliceAI + Pangolin + MMSplice as gold-standard evidence; discordance flags RNA validation.
- SpliceAI alone is not sufficient for PVS1 without gene-level LoF context.
- Extended-window predictions increase sensitivity but may raise false positives; verify with RNA data where possible.
- Version compatibility notes specify specific tool versions and API considerations; ensure installed versions match.
## Version Compatibility Reference examples tested with: SpliceAI 1.3+, Pangolin 1.0+, MMSplice 2.4+, pyensembl 2.3+, pysam 0.22+, pandas 2.2+, gffutils 0.13+, tensorflow 2.15+ Before using code patterns, verify installed versions match. If versions differ: - Python: `pip show <package>` then `help(module.function)` to check signatures - CLI: `<tool> --version` then `<tool> --help` to confirm flags If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying. # Splice Variant Prediction Predict whether a DNA variant alters mRNA splicing. **Distinct from "variant pathogenicity" generally**: a variant can be a strong splice disruptor without being pathogenic for the gene's standard mechanism, or pathogenic for reasons orthogonal to splicing. Splice prediction asks specifically: does this variant change splice-site usage? ## Predictor Taxonomy | Family | Architecture | Output | Fails when | |--------|--------------|--------|------------| | Context-aware CNN | 10 kb dilated ResNet | Per-position donor/acceptor probability | Long-range (>5 kb) regulatory effects; tissue-specific events | | T
- Version Compatibility
- Predictor Taxonomy
- Tool Selection Matrix
- Decision Tree by Use Case
- ClinGen SVI 2023 Framework
- SpliceAI Workflow
- Pangolin for Tissue-Specific Prediction
- SpliceVault for Empirical Mis-Splicing Outcomes
- MMSplice for Calibrated ΔPSI
- HGVS Splicing Nomenclature
- Extended-Window Scoring for Deep-Intronic Variants
- Concordance Across Predictors
- Branchpoint Variant Detection
- Splice-Switching ASO Design
spliceai \
spliceai -I input.vcf -O output_extended.vcf -R genome.fa -A grch38 -D 500 -M 1
python -c "import gffutils; gffutils.create_db('gencode.v45.annotation.gff3', 'gencode.db', force=True)"
pangolin \
input.vcf \
GRCh38.primary_assembly.genome.fa \
gencode.db \
pangolin_output \
Recompute with extended window
spliceai -I input.vcf -O output_2kb.vcf -R genome.fa -A grch38 -D 2000What does the bio-splice-variant-prediction skill do?
Predicts whether a DNA variant alters mRNA splicing using sequence-based deep-learning tools — SpliceAI (10kb context dilated CNN, clinical default), Pangolin (multi-tissue), MMSplice (modular per-region CNN with calibrated ΔPSI), SpliceTransformer/TrASPr (tissue-aware transformers), SpliceVault (empirical 300K-RNA lookup of likely mis-splicing outcomes), CADD-Splice (composite score). Applies the ClinGen SVI 2023 framework for ACMG/AMP variant interpretation (PVS1, PP3, BP4 evidence codes), HGVS splicing nomenclature (c.123+1G>A, c.123-3T>G, r.spl?), extended-window scoring for deep-intronic
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill splice-variant-prediction --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.