Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Bulk RNA-seq DESeq2 analysis with omicverse · FreedomIntelligence | DecimalAI

Bulk Rna Seq Deseq2 Analysis With Omicverse

SkillScore78Maintained

bulk-rna-seq-deseq2-analysis-with-omicverse

Walk Claude through PyDESeq2-based differential expression, including ID mapping, DE testing, fold-change thresholding, and enrichment visualisation.

scienceby FreedomIntelligence

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/bulk-rna-seq-deseq2-analysis-with-omicverse/SKILL.md

decimalai skills pull bulk-rna-seq-deseq2-analysis-with-omicverse --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/bulk-rna-seq-deseq2-analysis-with-omicverse/SKILL.md https://app.decimal.ai/s/bulk-rna-seq-deseq2-analysis-with-omicverse/SKILL.md

Raw file: /s/bulk-rna-seq-deseq2-analysis-with-omicverse/SKILL.md ↗ · machine-readable summary at /s/bulk-rna-seq-deseq2-analysis-with-omicverse.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 59d ago

Yes — +70% lift-12% tokens0% turns78% of whole cases pass with skill (18/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	—	—
case-15	✗→✓	▲ Improved	—	—
case-17	✗→✓	▲ Improved	—	—
case-01	✗→✓	▲ Improved	—	—
case-18	✗→✓	▲ Improved	—	—

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/bulk-deseq2-analysis/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

Skill contents

SKILL.md

Bulk RNA-seq DESeq2 analysis with omicverse

Overview

Use this skill when a user wants to reproduce the DESeq2 workflow showcased in t_deseq2.ipynb. It covers loading raw featureCounts matrices, mapping Ensembl IDs to symbols, running PyDESeq2 via ov.bulk.pyDEG, and exploring downstream enrichment plots.

Instructions

Import and format the expression matrix

Call import omicverse as ov and ov.utils.ov_plot_set() to standardise visuals.
Read tab-separated count data from featureCounts using ov.utils.read(..., index_col=0, header=1).
Strip trailing .bam from column names with [c.split('/')[-1].replace('.bam', '') for c in data.columns].

Map gene identifiers

Ensure the appropriate mapping pair exists by running ov.utils.download_geneid_annotation_pair().
Replace gene_id with gene symbols using ov.bulk.Matrix_ID_mapping(data, 'genesets/pair_<GENOME>.tsv').

Initialise the DEG object

Create dds = ov.bulk.pyDEG(data) from the mapped counts.
Resolve duplicate gene names with dds.drop_duplicates_index() and confirm success in logs.

Define contrasts and run DESeq2

Collect sample labels into treatment_groups and control_groups lists that match column names exactly.
Execute dds.deg_analysis(treatment_groups, control_groups, method='DEseq2') to invoke PyDESeq2.

Filter and tune thresholds

Inspect result shape (dds.result.shape) and optionally filter low-expression genes, e.g. dds.result.loc[dds.result['log2(BaseMean)'] > 1].
Set thresholds via dds.foldchange_set(fc_threshold=-1, pval_threshold=0.05, logp_max=6) to auto-pick fold-change cutoffs.

Visualise differential genes

Draw volcano plots with dds.plot_volcano(...) and summarise key genes.
Produce per-gene boxplots: dds.plot_boxplot(genes=[...], treatment_groups=..., control_groups=..., figsize=(2, 3)).

Run enrichment analyses (optional)

Download enrichment libraries using ov.utils.download_pathway_database() and load them through ov.utils.geneset_prepare.
Rank genes for GSEA with rnk = dds.ranking2gsea().
Instantiate gsea_obj = ov.bulk.pyGSEA(rnk, pathway_dict) and call gsea_obj.enrichment() to compute terms.
Plot enrichment bubble charts via gsea_obj.plot_enrichment(...) and GSEA curves with gsea_obj.plot_gsea(term_num=..., ...).

Troubleshooting

If PyDESeq2 raises errors about size factors, remind users to provide raw counts (not log-transformed data).
gene_id mapping depends on species; direct them to download the correct genome pair when results look sparse.
Large pathway libraries may require raising recursion limits or filtering to the top N terms before plotting.

Examples

"Run PyDESeq2 on treated vs control replicates and highlight the top enriched WikiPathways terms."
"Filter DEGs to genes with log2(BaseMean) > 1, auto-select fold-change cutoffs, and create volcano and boxplots."
"Generate the ranked gene list for GSEA and plot the enrichment curve for the top pathway."

References

Tutorial notebook: t_deseq2.ipynb
Sample featureCounts matrix: sample/counts.txt
Quick copy/paste commands: reference.md

Illustrative Want to see what bulk-rna-seq-deseq2-analysis-with-omicverse would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

7/24/2026, 18:36 UTC · 23 cases

Lift

+70%

78% vs 9%

Agent turns

0%

1.0 vs 1.0

Tokens

-12%

1,873.17 vs 2,136.74

fail → pass · 16pass → pass · 2fail → fail · 5

Per-case results (23)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-09 When invoking PyDESeq2 via pyDEG, how must the experimental groups be specified in the argument list?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-15 What utility function downloads gene set pathway collections for downstream enrichment analysis in omicverse?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-17 How do I generate a ranked gene metric series from differential expression results to use as input for GSEA?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-01 I have raw featureCounts count data from a bulk RNA-seq experiment comparing 'treated' vs 'control' samples, with BAM path suffixes in the column headers. Could you guide me through processing this using omicverse to map Ensembl IDs to gene symbols, execute DESeq2 differential expression analysis, set standard cutoffs, and generate both volcano plots and individual gene expression boxplots?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-18 How do I initialize a GSEA calculation object given a ranked gene series and a pathway dictionary?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-11 In the differential expression results table, how can I filter out genes that have a mean normalized expression below a log2 threshold of 1?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-20 PyDESeq2 raises an error during size factor estimation on my transcriptomics dataset. What is the most likely cause related to the input matrix values?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-12 How do I configure statistical significance and fold-change cutoffs on my pyDEG analysis object so that upregulated and downregulated categories are automatically assigned?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-04 I am working with a featureCounts output table in tab-separated format for bulk RNA-seq. How should I load this matrix in Python to ensure proper index and header parsing for transcriptomics analysis?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-13 What method on the pyDEG object renders a volcano plot displaying fold changes versus statistical significance?	pass→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-08 After mapping Ensembl IDs to gene names, my counts table has duplicated gene symbol row labels. What method removes duplicate index entries on the pyDEG object?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-22 How do I build a STAR genome index and align raw FASTQ paired-end reads to generate BAM alignment files?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-16 After downloading pathway databases, which utility parses and prepares the gene sets into a compatible dictionary structure?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-21 I have single-cell RNA-seq 10x Genomics matrix data in AnnData format. How do I perform Leiden clustering and UMAP dimensional reduction?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-10 I want to explicitly specify the DESeq2 algorithm when calling the differential expression analysis method on a pyDEG object. Which argument flag sets this?	pass→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-07 After mapping gene identifiers on a count DataFrame, how do I instantiate the differential expression analysis class in omicverse?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-23 What command line tool and parameters should I use to call peaks on ATAC-seq alignment BAM files?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-14 I want to visualize expression distributions for a custom list of genes across my treatment and control groups using a boxplot. What function should I call?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-03 Could you help me set up a differential expression analysis pipeline using omicverse for my transcriptomics raw counts? I want to compare treated against control conditions, filter out low-expression transcripts, run PyDESeq2, auto-select fold-change thresholds, and produce volcano plots alongside boxplots for key differentially expressed genes.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-06 Which function converts the index of a gene counts DataFrame from Ensembl identifiers to gene symbols using a downloaded annotation pair file?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-19 Once a pyGSEA object is instantiated, which method executes the permutation and enrichment score calculation?	fail→fail	—	—	—	—	—	—	—	—	—	—	—	—
case-02 I need to analyze my bulk RNA-seq dataset comparing mutant and wild-type replicates using PyDESeq2 in omicverse. Please clean up the sample column names, convert Ensembl identifiers to gene names, resolve any duplicate gene symbols, perform the contrast analysis, and generate a ranked gene list along with GSEA pathway enrichment curves and bubble plots.	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—
case-05 Before converting Ensembl IDs to official gene symbols in my transcriptomics dataset, what function handles retrieving the necessary reference mapping pair files?	fail→pass	—	—	—	—	—	—	—	—	—	—	—	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

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. 23 cases were attempted. The headline lift of +70 percentage points is the difference between those two pass rates over the 23 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 8.7%
Pass rate with the skill: 78.3%
Cases attempted: 23
Cases counted toward lift: 23
Cases that regressed: 0
Skill version measured: v1
Run completed: 7/24/2026, 18:36 UTC

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.

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run78

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns-5% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 59 days ago

Other measured skills in the registry, with their headline benchmark lift.