Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyzes isoform switching events and functional consequences using IsoformSwitchAnalyzeR. Predicts protein domain changes, NMD sensitivity, ORF alterations, and coding potential shifts between conditions. Use when investigating how splicing changes affect protein function.
.claude/skills/bio-isoform-switching/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
Reference examples tested with: Salmon 1.10+
Before using code patterns, verify installed versions match. If versions differ:
packageVersion('<pkg>') then ?function_name to verify parametersIf code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.
Identify isoform switches and predict their functional consequences on protein structure and function.
Goal: Identify genes where the dominant isoform switches between conditions.
Approach: Import Salmon quantification, filter low-expression isoforms, and test for isoform usage changes with DEXSeq-based statistics.
"Analyze isoform switching" -> Import transcript quantification, test for dominant isoform changes, and assess functional consequences.
IsoformSwitchAnalyzeR (importRdata + isoformSwitchTestDEXSeq)rlibrary(IsoformSwitchAnalyzeR) # Import transcript quantification from Salmon salmonQuant <- importIsoformExpression( parentDir = 'salmon_quant/', addIsofomIdAsColumn = TRUE ) # Create switch analysis object switchAnalyzeRlist <- importRdata( isoformCountMatrix = salmonQuant$counts, isoformRepExpression = salmonQuant$abundance, designMatrix = data.frame( sampleID = colnames(salmonQuant$counts), condition = c('control', 'control', 'control', 'treatment', 'treatment', 'treatment') ), isoformExonAnnoation = 'annotation.gtf', isoformNtFasta = 'transcripts.fa' ) # Filter lowly expressed isoforms switchAnalyzeRlist <- preFilter( switchAnalyzeRlist, geneExpressionCutoff = 1, # Minimum TPM isoformExpressionCutoff = 0, removeSingleIsoformGenes = TRUE ) # Test for isoform switches switchAnalyzeRlist <- isoformSwitchTestDEXSeq( switchAnalyzeRlist, reduceToSwitchingGenes = TRUE )
Goal: Predict how isoform switches alter protein domains, coding potential, and localization.
Approach: Extract isoform sequences, run external annotation tools (CPC2, Pfam, SignalP, IUPred2), and import results back into the switch analysis object.
r# Extract sequences for external analysis switchAnalyzeRlist <- extractSequence( switchAnalyzeRlist, pathToOutput = 'sequences/', writeToFile = TRUE ) # Run external tools and import results: # - CPC2 for coding potential # - Pfam for protein domains # - SignalP for signal peptides # - IUPred2 for intrinsic disorder # After running external tools, import results switchAnalyzeRlist <- analyzeCPC2( switchAnalyzeRlist, pathToCPC2resultFile = 'cpc2_results.txt', removeNoncodinORFs = TRUE ) switchAnalyzeRlist <- analyzePFAM( switchAnalyzeRlist, pathToPFAMresultFile = 'pfam_results.txt' ) switchAnalyzeRlist <- analyzeSignalP( switchAnalyzeRlist, pathToSignalPresultFile = 'signalp_results.txt' ) switchAnalyzeRlist <- analyzeIUPred2A( switchAnalyzeRlist, pathToIUPred2AresultFile = 'iupred2_results.txt' )
Goal: Determine which isoform switches cause functional changes (NMD, domain loss, coding potential shifts).
Approach: Run analyzeSwitchConsequences across multiple consequence types and extract switches with confirmed functional impact.
r# Analyze functional consequences of switches switchAnalyzeRlist <- analyzeSwitchConsequences( switchAnalyzeRlist, consequencesToAnalyze = c( 'intron_retention', 'coding_potential', 'ORF_seq_similarity', 'NMD_status', 'domains_identified', 'signal_peptide_identified' ), dIFcutoff = 0.1, # Minimum isoform fraction change showProgress = TRUE ) # Extract significant switches significantSwitches <- extractSwitchSummary( switchAnalyzeRlist, filterForConsequences = TRUE ) print(significantSwitches)
Goal: Visualize isoform switch events and summarize functional consequence patterns.
Approach: Generate per-gene switch plots showing isoform usage changes, and create global summaries of consequence enrichment.
r# Plot individual gene switches switchPlot( switchAnalyzeRlist, gene = 'GENE_OF_INTEREST', condition1 = 'control', condition2 = 'treatment' ) # Summary of consequence types extractConsequenceSummary( switchAnalyzeRlist, consequencesToAnalyze = 'all', plotGenes = FALSE ) # Enrichment of consequences extractConsequenceEnrichment( switchAnalyzeRlist, consequencesToAnalyze = 'all' )
| Parameter | Default | Description | |-----------|---------|-------------| | Switch q-value | < 0.05 | Significance of isoform switch | | dIF (delta isoform fraction) | > 0.1 | Minimum usage change | | Consequence q-value | < 0.05 | Significance of consequence |
| Consequence | Impact | |-------------|--------| | NMD sensitive | Transcript targeted for degradation | | Domain loss/gain | Altered protein function | | ORF disruption | Truncated/altered protein | | Signal peptide loss | Changed localization | | Coding potential loss | Switch to non-coding |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.